TELEPHONE SERVICE SYSTEM WITH INSTANT COMMUNICATION EXTENSIONS

PROCEDURE AND SYSTEMS FOR THE TRANSLATION OF LANGUAGE

MULTI-VOICE COMMUNICATION SYSTEM AND - PROCEDURES

TRANSLATION AND ANNOUNCEMENT OF TEXT IN A PICTURE

ELECTRONIC MECHANISM FOR LANGUAGE TRANSLATION

SYSTEM AND PROCEDURE FOR THE PROCESSING A MEANS MOBILE ONE COMPUTER EQUIPMENT OF A SENT MESSAGE IN A SERVER OF A COMPUTER NETWORK

TRANSLATION SYSTEM AND MULTI-FUNCTIONAL COMPUTER, IN PARTICULAR FOR THE TREATMENT OF TEXTS AND THE TRANSLATION ON PAPER

PROCEDURE AND EQUIPMENT FOR TRANSLATING A SPARCHE INTO ANOTHER

INTEGRATED DRAFT AND TRANSLATION SYSTEM

Computer system for calculating translation costs

The present disclosure relates to a computer system, computer program product and computer implemented method for automatically calculating translation costs based upon translation memory analysis. This involves receiving an original document and a source-target language pair, comparing the original document with previously translated text or the translation memory database corresponding to the source- target language pair and computing a modified word count reflecting the degree of overlap between the original document and the previously translated text based on the comparison. Further, a per word translation rate corresponding to the source- target language pair is identified in a viewable database and a modified translation cost is calculated from the per translation rate and the modified word count.

REAL TIME ORGANIZATION PULSE GATHERING AND ANALYSIS USING MACHINE LEARNING AND ARTIFICIAL INTELLIGENCE

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for natural language processing of unstructured text are disclosed. In one aspect, a method includes the actions of receiving one or more unstructured data entries that each include one or more sentences, are each associated with an entity, and are each from a user. The actions further include parsing the one or more sentences. The actions further include determining one or more classifications of each unstructured data entry. The actions further include determining a sentiment. The actions further include accessing structured data. The actions further include defining one or more groups of users based on the structured data, wherein each of the one or more groups shares a common characteristic in the structured data. The actions further include determining sentiments to associate with the group. ~ ~' ol (.0) a)C o:C C N Q a) Cm 3 a) o ...

Cross-language communication between proximate mobile devices

A system facilitates cross-language communication among users of respective wireless communication devices. Two or more mutually-agreeing users establish and participate in a cross- language communication session, without revealing private information, such as their telephone numbers. Once the session has been established, each user enters text into her wireless communication device, and a translated version of the entered text is displayed on a screen of the other user's wireless communication device. The text may be entered, such as by typing on a keyboard on the wireless communication device or by speaking inputs into a microphone and automatically recognizing the speech. Optionally, the translated text may be spoken by a speech synthesizer. No permanent information about the participants need be stored in the respective wireless communication devices, so once the communication session ends, no further communication between or among the participants is possible, without establishing ...

INTEGRATED NATIVE LANGUAGE TRANSLATION

A method and apparatus provide for performing language translation by obtaining a selection of a language preference for presentation of text and/or speech on an electronic device. When data is received that includes content in a language other than the preferred language, a decision whether translation is required may be reached by analyzing the context of the language or metadata associated with the language, such as. HTML tags, or language data included in a particular protocol, e.g. HTTP headers. A selection may be made of billing level, determined at least in part by the languages involved, desired accuracy, latency and volume of translation. If necessary, the data may be routed to a translation host or service before final presentation.

TRANSLATION SYSTEM

A translating system has either a first translation mode for translating sentences in units of one sentence or a second translation mode for translating sentences in a package. The desired mode can be selected by an operator. Sentences to be translated can be entered either by a direct data entry device such as a keyboard, or by an indirect data entry device such as an external memory.

VOICE ACTIVATED LANGUAGE TRANSLATION

A voice activated language translation system that is accessed by telephones where voice messages of a caller are translated into a selected language and returned to the caller or optionally sent to another caller. A voice recognition system converts the voice messages into text of a first language. The text is then translated into text of the selected language. The text of the selected language is then converted into voice.

A SYSTEM AND METHOD FOR ACCESSING SERVICES AND/OR APPLICATIONS AND/OR CONTENT ON A COMMUNICATION NETWORK

Published without an Abstract ...

VOICE ACTIVATED LANGUAGE TRANSLATION

A voice activated language translation system that is accessed by telephones where voice messages of a caller are translated into a selected language and returned to the caller or optionally sent to another caller. A voice recognition system converts the voice messages into text of a first language. The text is then translated into text of the selected language. The text of the selected language is then converted into voice.

SYSTEM AND METHOD FOR MULTI-LINGUAL TRANSLATION

The present invention relates to the translation of a portion of text to be communicated in a text-based communication in a communications network. A communications device for composing the text-based communication queries a translation service with a portion of text in a first language to obtain a replacement for the portion in a second language. A user may trigger a replacement query by composing the portion using at least one trigger symbol monitored by the communications device. Replacement may be confirmed with the user and at least one alternative replacement sought in response to the confirmation. The communications network may comprise a wireless network and the communications device a wireless mobile communications device.

NATURAL LANGUAGE ANALYSING APPARATUS AND METHOD

NATURAL LANGUAGE ANALYZING APPARATUS AND METHOD A natural language (NL) analyzing system is provided with a capability to analyze NL expressions and to resolve ambiguities and present them to the user for verification of correct interpretation. An essential feature of the invention is the use of a conceptual model of the system relevant to the application in which the invention is implemented. The model is created (customizing the system) by the user, and is stored as a conceptual schema. The schema is built of logical facts representing entities (concepts) and relationships between entities, forming a description of the universe of discourse or object system in question. The entities of the schema have at least one external connection, namely to natural language terms in a vocabulary. The schema itself is completely language independent, though the components of it may have "names" expressed in a natural language such as English. There may be a second connection to the entities, namely ...

TEXT PROCESSING PLANT.

Spoken text conversion method for providing written notes has spoken text stored before conversion into written document and transmission for provision of corresponding written notes

The spoken text conversion method has the spoken text entered in a central memory before conversion of the spoken text into a written document and transmission of the latter, e.g. via a fax machine, or a computer modem, with written notes provided from the transmitted document, an additional electronic step incorporated for data protection.

Electronic translation equipment.

Method and device for helping to understand a message sensory hearing by turning it into a visual message.

La présente invention concerne un procédé pour aider un malentendant à comprendre un message sensoriel auditif en transformant le message auditif en un message visuel et, en projetant ce message sur un support dans le champ visuel du malentendant. Elle concerne également un dispositif (10) comportant des moyens pour transformer ledit message sensoriel auditif en un message visuel et des moyens pour le projeter sur une surface positionnée dans le champ visuel dudit utilisateur. Ce dispositif comporte un support (11) portant un capteur en forme de microphones (16, 17) pour capter ledit message, des moyens d’enregistrement et de mémorisation (19) pour enregistrer, mémoriser en temps réel le message auditif, et le transformer en message visuel, un écran (18) placé dans le champ visuel de l’utilisateur, au moins un projecteur (20, 21) pour projeter le message visuel sur ledit écran ainsi qu’un capteur d’un mouvement pupillaire de l’utilisateur, des moyens pour interpréter le mouvement pupillaire ...

CREATION OF DATA BASE LINKS BETWEEN REPRESENTATION SYMBOL

СПОСОБ ОБРАБОТКИ ИНФОРМАЦИИ И ПРЕДОСТАВЛЕНИЯ ПЕРЕВОДА С МОБИЛЬНОГО ИЛИ СТАЦИОНАРНОГО ТЕЛЕФОНА

Способ обработки информации и предоставления перевода с мобильного или стационарного телефона, в котором потребитель набирает цифровой код доступа к соответствующему серверу и автоматически включает систему «Мобильный перевод» и цифровой код, соответствующий выбранному языку.

Objective transformation method based on attention mechanism

An image capture system for a vehicle using translation of different languages

Automatic translating method and machine

Context-note recording

Use of statistical flow data for machine translations between different languages

Data processing method, apparatus thereof, and device for data processing

A terminology discovery method for translation and a system thereof

Simultaneous translation method and device, smart car-mounted terminal and storage medium

WEB page translation device and WEB page translation method

A WEB page translation method includes a description language identification means 33 for discriminating whether the translation target portion of the WEB page accessed by a user via a terminal device 1 is described in HTML, a first translation means 35 for translating the character string displayed on the WEB page into another language on a translation target portion discriminated to be described in HTML by the description language identification means 33, and a second translation means 36 for translating the character string displayed on the WEB page into another language on a translation target portion discriminated to be described not in HTML by the description language identification means 33.

Subtitle voice precise synchronizing system and method, and information data processing terminal

Method and device for translating program language resources

Natural language processing device and method

User training by intelligent digital assistant

Automatic translation method for e.g. telecommunication industry, involves minimizing semantic entropy of phrase of text by minimizing cost of journey between departure point and arrival point using shortest path of graph

La présente invention se rapporte à un procédé de calcul des plus courts chemins en termes de coût et de nombre d'arêtes dans un graphe valué comportant des sommets et une matrice d'adjacence en utilisant des moyens de calcul comprenant des ressources mémoires et un processeur. Selon un autre aspect, l'invention concerne un procédé et un système de traduction automatique, mis en oeuvre sur un équipement informatique comportant des moyens de calcul et notamment au moins un processeur et au moins une mémoire, le procédé comportant une première étape d'établissement d'un graphe valué selon le sous-procédé suivant : pour une phrase (ou bien pour tout un texte), chaque sommet correspond à un sens S(i,n), qui est le ième sens du nième mot significatif, ce qui permet d'avoir une distance sémantique d(i,n, j, n+1) entre S(i,n) et S(j, n+1) puis est choisi un sommet fictif de départ, relié avec un coût nul à chacun des sens du premier mot et un sommet fictif d'arrivée, relié avec un coût nul à chacun ...

PROCESS, DEVICE Of ADAPTATION OF NUMERICAL FILES

AUTOMATIC SIMULTANEOUS INTERPRETATION SYSTEM.

PROCESS, DEVICE Of ADAPTATION OF NUMERICAL FILES

La présente invention concerne un procédé et un dispositif d'adaptation de fichiers numériques consistant à repérer des chaînes de caractères à adapter dans un fichier source et à remplacer les sources constituées des chaînes de caractères par des données de substitution. Selon l'invention, on repère de façon particulière chaque présence de source dans le fichier source en définissant des cibles par : 1° division du fichier source en sections identifiées par un identifiant unique de section; 2° sélection d'une source dans une section; 3° sélection d'une zone de contexte incluant la source sélectionnée; 4° affectation d'un rang d'occurrence, dans la section, à la zone de contexte sélectionnée; 5° affectation d'un rang d'occurrence, dans la zone de contexte sélectionnée, à la source sélectionnée, l'identifiant de section, la source sélectionnée et son rang d'occurrence, la zone de contexte sélectionnée et son rang d'occurrence constituant les attributs de chaque cible. La définition de cibles ...

PROCESS AND DEVICE OF TRANSLATION

La présente invention concerne un procédé et un dispositif de traduction, caractérisé en ce que, pour chaque mot ou expression dans au moins une langue d'origine, ils fournissent simultanément plusieurs écritures phonétiques de sa traduction dans au moins une langue de destination.

Process and device to transform a first text message in a first language, in a vocal secondmessage pronounced in one second predetermined language

On effectue les opérations suivantes: a) on fait, par reconnaissance vocale automatique par ordinateur, une analyse vocale d'un premier message vocal pour le transformer en un premier message écrit dans une première langue; b) on transforme par traduction automatique par ordinateur ce premier message écrit dans la première langue en un second message écrit dans une seconde langue prédéterminée; c) on transforme par synthèse vocale par ordinateur ce second message écrit en un second message vocal prononcé dans la seconde langue. La réponse prend un chemin identique.

Smart card terminal for use with ATMs, phone systems, where the instructions are readily displayed in a local language even if the character set in not Latin, has local language memory on board the smart card

Le terminal (1) est radiotéléphonique ou bancaire par exemple et est relié à un réseau de télécommunications (RR). Des mémoires (13, 14) du terminal contiennent des signes graphiques selon un alphabet d'une langue usuelle, par exemple l'anglais afin d'être compatible avec de nombreux réseaux dans le monde. Des mémoires (21-23) dans la carte contiennent un fichier de règles de grammaire (FRG) selon une deuxième langue (NL) par exemple l'hindi ou le thaï. Le terminal comprend un moteur de grammaire (18) pour convertir des données, transmises sous forme de premiers signes indépendants dans la deuxième langue par exemple par un réseau local, selon les règles de grammaire lues dans la carte afin d'afficher des deuxièmes signes corrects grammaticalement dans l'afficheur (17) et lisibles dans la langue du possesseur de la carte.

SMART DEVICE HAVING OPTICAL RECOGNITION FUNCTION

The present invention relates to a smart device having an optical recognition function, which comprises: a pointing module for displaying a pointer at one point on an object having a character marked thereon; a range determination module for determining a range of a first region with respect to a point where the pointer is displayed, in the object; a data acquiring module for acquiring image data of the first region; a recognition module for recognizing the character from the image data acquired by the data acquiring module; and an output module for outputting any one of a recognition result of the recognition module, a search result obtained by searching the recognition result in a search server, and a dictionary search result of the recognition result. Accordingly, a character included in a region desired by a user can be recognized by only a simple and intuitive manipulation to be provided to the user. COPYRIGHT KIPO 2018 (210) Pointing module (220) Range determining module (230) Data ...

E-MAIL PROCESSING SYSTEM, PROCESSING METHOD AND PROCESSING DEVICE

MULTILINGUAL TRANSLATION DEVICE AND MULTILINGUAL TRANSLATION METHOD

TRANSLATION DEVICE USING A TRANSLATION TREE STRUCTURE OF A PORTABLE TERMINAL AND A METHOD THEREOF CAPABLE OF EXPRESSING AMBIGUOUS WORDS THROUGH A TREE STRUCTURE

PURPOSE: A translation device using a translation tree structure of a portable terminal and a method thereof are provided to confirm the accuracy of translation by displaying meanings and speech parts of homonym with a translated sentence. CONSTITUTION: An input unit of a first portable terminal receives a first language from a user who uses the first language. A translation engine(102) translates the first language into a second language by using a database stored in the first portable terminal. An output unit(108) displays the second language through a tree structure, and a selection unit selects one word of the second language which is displayed as a translation tree structure. A communication module(109) transmits the selected second language to a second portable terminal which uses the second language. The database is a user database stored in the first portable terminal or a common database received from the server. COPYRIGHT KIPO 2013 [Reference numerals] (101) Control unit; (102 ...

온라인 음성 번역 방법 및 장치

... 온라인 음성 번역 방법 및 장치에 있어서, 상기 방법은, 제1 사용자가 입력하는 제1 음성정보에 대하여 음성식별을 진행하여, 제1 식별정보를 획득하는 단계; 제1 식별정보의 신뢰도를 확정하는 단계; 제1 식별정보의 신뢰도에 근거하여 제1 사용자가 제1 식별정보를 확인하도록 프롬프팅하는 단계; 확인된 제1 식별정보를 번역하여 제1 번역정보를 획득하고 출력하는 단계; 제2 사용자가 피드백한 제2 정보에 근거하여 제1 번역정보의 관련정보를 추출하는 단계; 관련정보에 근거하여 제1 번역정보를 수정하고 출력하는 단계;를 포함한다. 온라인 음성 번역 방법 및 장치를 통해, 언어간의 원활한 교류를 보장할 수 있다.

AUTOMATIC SPEECH TRANSLATION APPARATUS AND METHOD THEREOF

The present invention relates to an automatic speech translation apparatus and a method thereof, capable of translating a part of a sentence that is not a complete sentence and providing the part to a user if a predetermined condition is satisfied. According to embodiments of the present invention, the automatic speech translation apparatus includes: a speech input unit for receiving a speech spoken by a speaker; a speech processing unit for converting speech data received from the speech input unit into text data through a speech recognition process; a speech analysis unit for analyzing the speech data to identify an end of a sentence, and generating end-point detector (EPD) information indicating the end of the sentence; a semantic unit determination unit for determining a semantic unit and the end of the sentence in the text data by using at least one of the EPD information and morpheme information of words included in the text data, and dividing the text data based on the semantic unit ...

METHOD AND SYSTEM FOR TRANSLATING LANGUAGES THROUGH NETWORK

PURPOSE: A method and a system for translating languages through the network are provided to offer a mobile device with a translation function for facilitating talk between persons using different languages. CONSTITUTION: A server(302) provides the translation service to a client(304) through the network. Application items for enabling a user to use the client are transmitted from the server. The application items include an independent language translation engine and at least one language dependent translation database. The language dependent translation database includes a set of translation templates and translation dictionaries. The user requests a specified database and the language dependent database to the server if necessary. The translation is performed by applying the language dependent translation database and the specified database to the translation engine. © KIPO 2005 ...

METHOD AND AN APPARATUS FOR A VOICE IMPROVING MULTI-SENSOR OF A MOBILE DEVICE, ESPECIALLY FOR PROVIDING A MOBILE DEVICE INCLUDING AN ALTERNATIVE SENSOR FOR PROVIDING AN ALTERNATIVE SENSOR SIGNAL REPRESENTING A VOICE AND AN AIR CONDUCTION MICROPHONE

PURPOSE: A method and an apparatus for a voice improving multi-sensor of a mobile device are provided to improve the accuracy of a voice recognition appropriately used in a noisy environment. CONSTITUTION: An air conduction microphone converts sound waves into an electric microphone signal. An alternative sensor provides an electric alternative sensor signal including information about a voice. A communication interface allows a mobile device to directly communicate with other mobile devices. The communication interface allows multiple types of communication with other mobile devices. One of the multiple types of communication includes one-to-one communication that allows one mobile device to communicate with a different mobile device even when two or more mobile devices are available for communication. © KIPO 2006 ...

REAL TIME AUTO TRANSLATION SYSTEM AND METHOD, REAL TIME TRANSLATING TERMINAL

The present invention relates to a real time auto translation device, a real time translating terminal, and a real time auto translation method thereof. Characters to be translated are extracted from the image of a foreign document photographed by using a camera installed to the mobile phone of a user, a personal digital assistant (PDA), and a smart phone. The extracted characters are compared with stored data. The meaning of the characters is recognized. The recognized meaning is translated into the language of the user, and is displayed. COPYRIGHT KIPO 2016 (100) User terminal (110) Image photographing part (200) Real time auto translation device (300) Communication network ...

SYSTEM AND METHOD FOR PROCESSING INTERACTIVE REAL-TIME TRANSLATION SERVICE FOR HOTEL RESERVATION

Provided are a method and apparatus for processing an interactive real-time translation service for a hotel reservation and a method and apparatus for providing the service. The method for processing the service by an information processing apparatus according to an embodiment of the present invention may comprise: translating an original text input by a host terminal in accordance with language setting information of a guest and transmitting the translated text to a guest terminal in a first case that language setting information of a host and the language setting information of the guest are different and the original text is input by the host terminal; translating an original text input by the guest terminal in accordance with the language setting information of the host and transmitting the translated text to the host terminal in a second case that the language setting information of the host and the language setting information of the guest are different from each other and the original ...

SYSTEM AND METHOD FOR ANALYSING KOREAN RELATION USING CONCEPTNET

METHOD AND SYSTEM OF CLASSIFICATION IN A NATURAL LANGUAGE USER INTERFACE

A method and system are provided for processing natural language user queries for commanding a user interface to perform functions. Individual user queries are classified in accordance with the types of functions and a plurality of user queries may be related to define a particular command. To assist with classification, a query type for each user query is determined where the query type is one of a functional query requesting a particular new command to perform a particular type of function, an entity query relating to an entity associated with the particular new command having the particular type of function and a clarification query responding to a clarification question posed to clarify a prior user query having the particular type of function. Functional queries may be processed using a plurality of natural language processing techniques and scores from each technique combined to determine which type of function is commanded.

MESSAGING CENTER, USER EQUIPMENT, AND METHODS FOR MESSAGE TRANSLATION

A messaging center (e.g. SMS, MMS, IM, email center), User Equipment (UE) and methods are provided to facilitate delivery of messages to recipients in the language used by those recipients. A message written in a first language (202) is first delivered to a recipient (218), optionally including a delivery report request. The recipient's UE (104) determines if proper message delivery took place based (220), for example, on a match between the first language (and/or it character set) and a second language (and/or its character set) used by the recipient's UE. In case of a mismatch, the recipient's UE (104) sends back to the messaging center (116) an improper delivery report (222) optionally including an indication of the second language (and/or character set). The messaging center (116) determines the second language based on the indication or via other means (227), translates the message into the second language, and re- sends it to the recipient's UE (104).

NETWORK-BASED TRANSLATION SYSTEM AND METHOD

Translation system of the type with a connecting structure with intercommunicating net/internet: (NET), whose net includes a plurality of interconnected servers (Servl.Serv2.Serv3...Ser CUz), comprising: a) at least one net-communicator microprocessor user-apparatus (Cuz) for net communication (CUl.CU2.CU3 ...) which comprises connecting means to the net and/or via net/internet (ServCTRn-net), and b) at least one net-service-server (ServerCTRn) connected to said intercommunicating net/internet (NET) comprising an indefinite number of servers (Servi.2...); c) said net service-server (ServerCTRn) including or connecting to at least one net­service database (Db); and d) a plurality of translatorcomputers and/or translator-servers (Ctrn) comprising at least one automatic translation system inside for a plurality of languages in various combinations, each said translator-computer and/or translator-server (Ctrn) including furthermore: I. connecting means to said intercommunicating net/internet ...

AUTOMATIC TRANSLATION DEVICE AND AUTOMATIC TRANSLATION METHOD

Le dispositif de traduction automatique de l’invention comprend un premier module d’analyse de la parole pour analyser une parole prononcée dans une première langue et générer une parole dans une première langue intermédiaire, un module de synthèse de la parole pour reconvertir la parole de la première langue intermédiaire vers la parole de la première langue et générer un signal de parole, un premier module de traduction pour convertir la parole de la première langue intermédiaire vers une parole dans une deuxième langue, et un module générateur de caractères pour afficher la parole sur un écran. Les informations de conversation sont oralement transmises à la personne parlant la première langue et portant ce dispositif de traduction automatique et visuellement transmises à la personne parlant la deuxième langue. Pour chaque forme de transmission, le contenu parlé par l’une des personnes peut être vérifié par la personne elle-même.

METHOD AND SYSTEM FOR PROVIDING REMOTE TRANSLATIONS

A method and system for enabling a user at a remote location to obtain various types of translation services. The user utilizes a remote device (Fig. 2, 220) to communicate with a translation engine (Fig. 2, 230) to perform text-to-text, text-to-voice, and voice-to-voice translations. Advertisements can be provided to the user in connection with the translations. (Fig. 2, 240) ...

TELECOMMUNICATION NETWORK FOR TRANSMITTING TRANSLITERATED TEXT MESSAGES AND METHOD THEREFOR

A telecommunication network supporting a text transmission service (TTS), wherein at least one of the end user units connected to the network does not support display of at least a portion of the characters which are allowable in TTS text messages, the network including: at least one transliteration module for transliterating at least a portion of a TTS text message to characters supported for display by the at least one end user unit; and at least one display module included in the at least one end user unit for displaying the TTS text message including the transliterated portion, if any.

PRE-TRANSLATED MULTI-LINGUAL ONLINE SEARCH SYSTEM, METHOD, AND COMPUTER PROGRAM PRODUCT

A system, method and computer program product for generating a multilingual database including generating a unique identifier (UID) code for a term; translating the term into a plurality of languages yielding a plurality of translated terms corresponding to the term; associating the term and the plurality of translated terms with the UID; and storing the term, the plurality of translated terms, and the UID, in a UID database. In another embodiment, a system, method and computer program product for retrieving documents including receiving a multi-lingual query from a user (such as, e.g., an enduser, a computer, or a search engine); parsing the multi-lingual query into a plurality of search terms; determining a unique identifier (UID) code corresponding to a first search term of the plurality of search terms; determining remaining UIDs, for each remaining search term of the plurality of search terms; querying a database using the UID and the remaining UIDs, resulting in a list of links pre-associated ...

APPARATUS AND METHOD FOR TRANSLATION USING A TRANSLATION TREE STRUCTURE IN A PORTABLE TERMINAL

A method for translation using a translation tree structure in a portable terminal includes inputting, by a user speaking in a first language, one or more first language words to a first portable terminal; translating the inputted first language words into one or more second language words using a database of the first portable terminal; displaying the translated second language words according to the translation tree structure; selecting one of words of the second language words displayed in the translation tree structure; and transmitting the selected second language words to a server and a second portable terminal which uses the second language.

METHOD, SYSTEM AND RECORDING MEDIUM FOR PROVIDING DICTIONARY FUNCTION AND FILE DISTRIBUTION SYSTEM

A method of providing a dictionary service may include configuring a first area of a display to receive a keyword as an input thereto and a second area of the display to display a dictionary search result of the keyword when the user terminal is operating in a dictionary mode; switching from the dictionary mode to a translation mode in response to the keyword input into the first area being greater than or equal to a threshold length; and setting the extended keyword as a source text to translate and display in a third area of the display.

Translation device, translation program, and translation method

A translation device has a translation processing unit that outputs character-area-character data by performing a translation process on the character-area-character data of an input image representing a figure-containing document, and outputting figure-area-character data by performing a translation process on the figure-area-character data of an input image representing a figure-containing document, a figure identification information searching unit that searches figure identification information used to identify a figure contained in a character area of the figure-containing-translation data, a linked page number searching unit that searches a page number in a character area of the figure-containing-translation data, a page number extracting unit that extracts a page number of a page included in figure area of is figure identification information, and a page number rewriting unit that rewrites the searched page number linked to the figure identification information to the extracted page ...

Translation System And Method

The invention relates a translation system for a portable communication apparatus and a method thereof. The translation system includes a storage unit, an input unit, a processing module, and a display unit. The storage unit stores an inquiry datum being one of a short message and an e-mail transceived by the portable communication apparatus. The input unit provides a conditional command and determines whether the inquiry datum is to be translated. The processing module transforms the inquiry datum into a translation datum based on the conditional command and a dictionary datum, and the display unit shows the translation datum.

Architecture and methodology of redirection for dynamic new URL links

An architecture and methodology of redirection for dynamic new URL Links uses a first server device to get information flow content from a second server device. By inserting an application into the information flow content retrieved from the second server device, the first server device replaces the web objects, which may generate dynamic new URL links, with the redirect functions in the code and sends the content to the browser. The browser will execute the code automatically. Whenever the browser generates new dynamic new URL links, it would call the provided redirect functions, and thus redirect them and retrace back to the first server device.

Billing system for services provided via instant communications

Systems, methods and program products are disclosed for determining billable usage of a communication system (10) wherein services are provided via instant communications (14). In some embodiments, the present invention provides for authorizing the fulfillment of service requests based upon information pertaining to a billable account.

MACHINE TRANSLATION FEEDBACK

WIRELESS TERMINALS, LANGUAGE TRANSLATION SERVERS, AND METHODS FOR TRANSLATING SPEECH BETWEEN LANGUAGES

Character input device, mobile terminal, and character input program

A character input device is disclosed. The device includes a character input section including a plurality of character keys; a display section that displays an input character(s); and a next word prediction section that predicts a respective word being subsequently input in an event of input-word reception in the character input section and that displays the word as a next word candidate on the display section. The next word prediction section stores usage history information indicative of whether the next word candidate for the respective input-received word was used by a user, and determines in accordance with the usage history information of words as of a time point of the event of input-word reception of the word whether to display the next word candidate on the display section.

Translation display apparatus and method

In a translation display apparatus, a display section displays a plurality of original sentences of a first language. A user designates an area of the original sentences to be translated on the display through a translation area designation section. An area extraction section extracts the original sentences in the area designated by the translation area designation section. A translation section translates the original sentence extracted by the area extraction section from the first language to a second language. The display section displays the translated sentences translated by the translation section in the area designated by the translation area designation section.

Translating apparatus and method, and recording medium used therewith

A translating apparatus includes a speech recognition unit, a machine translation unit, a speech synthesizing unit, and a dialog management unit. The speech recognition unit recognizes input speech, and supplies the result of the speech recognition to the machine translation unit. The machine translation unit translates the result of the speech recognition. When a Japanese-speaking user and an English-speaking user speak to each other, the dialog management unit stores a history of dialogs, and determines based on the dialog history and prestored knowledge whether the result of the translation by the machine translation unit is unnatural compared with the flow of the dialog. When the result of the translation is unnatural, the dialog management unit outputs, to the machine translation unit, information representing the unnatural result. This controls the machine translation unit to perform translation again.

SYSTEM AND METHOD FOR NETWORK-BASED TELETRANSLATION

A network-based teletranslation system and method for translating documents from one natural language to another natural language. Ine one embodiment, the teletranslation system comprises a client application layer having a plurality of client applications, the client application layer receiving translation documents from one or more software applications and outputting a translated text, a server layer having a plurality of servers, each server having a plurality of filters, the server layer calling a plurality of filters in an appropriate order based on the translation request and existing parameters, each filter preprocessing a translation document to facilitate further preprocessing by subsequent filters, at least one of the filters processing the translation request and returning the translated document, and an intermediate layer coupling the client application layer to the server layer and arbitrating the translation documents among the servers in the server layer, wherein the teletranslation ...

Natural language analyzing apparatus and method

A system for natural language (NL) analyzis is provided which comprises apparatus and method. It has the capability to analyze NL expressions and to resolve ambiguities and present them to the user for verification of correct interpretation. The invention is based on a language independent model of the contents of a data base. The model contains records of information defining entity types and relations between such entity types. The model is created (customizing the system) by the user, and is stored as a conceptual schema. The entities of the schema are linked or connected to natural language terms in a vocabulary. The entities represent objects in the data base, and there is a link or connection between the entities and those objects of the data base. The actual analysis of NL expressions is performed by a Natural Language Engine (NLE) in cooperation with an Analysis Grammar and the schema. The analysis results in an intermediate, language independent logic form representation of the ...

AN ELECTRONIC DEVICE AND METHOD FOR VISUAL TEXT INTERPRETATION

ELECTRONIC DEVICE

PURPOSE: To obtain the structures and functions for retrieval of dictionary and study of language based on the conjugation for each part of speech, by specifying the retrieval information with collation between the input words and the selected parts of speech and codes of parts of speech obtained by a selecting means for part of speech. CONSTITUTION: The information on English words is stored in a read-only memory (EROM 7; while the information on the Japanese translation words is stored in a read-only memory (JROM) 8, respectively. An area A of the EROM 7 stores the spellings of ordinary English words, and an area B has the value which can be traced on the EROM 7 for different spellings in case the spelling differs for each part of speech. An area C stores a logical address of the JROM 8. The areas D and E of the JROM 8 store the Japanese translation words and the codes of parts of speech which specify the part of speech to which the Japanese translation words belong respectively. For ...

INFORMATION RETRIEVING DEVICE

PURPOSE: To retrieve all pieces of information in a short time by arraying the pieces of information in the order based upon a specific rule and making uniform numbers of pieces of information into blocks. CONSTITUTION: A microprocessor 5 outputs a key strobe signal KS to an input part 2 and reads an input signal KI to discriminate an operated key. Further, it specifies an address of a memory 6 to read its contents. A display control part 7 incorporates a memory stored with set and reset states of respective dots of a display part 3, and outputs a display signal for a specific display corresponding to the contents of the memory continuously to the display part 3 once information corresponding to the display pattern until next information is written. A voice synthesizing part 8 once receiving a voice output indication for a word generates the specific voice signal and outputs it to a speaker driving circuit 9. COPYRIGHT: (C)1984,JPO&Japio ...

СПОСОБ ЛИНГВО-ЛОГИЧЕСКОГО ПРЕОБРАЗОВАНИЯ СТРУКТУРИРОВАННОГО МАССИВА ДАННЫХ, СОДЕРЖАЩЕГО ЛИНГВИСТИЧЕСКОЕ ПРЕДЛОЖЕНИЕ

Изобретение относится к области вычислительной техники для обработки массивов данных. Технический результат заключается в повышении точности предварительной обработки текста на естественном языке для его последующей индексации и обработки. Технический результат достигается за счет формирования первой структуры данных, на котором формируют первую структуру данных СМД, содержащую элементы упомянутой первой структуры данных, формирования базы данных лингвистических признаков (БДЛП), на котором выявляют лингвистические признаки текстовых элементов (ТЭ) лингвистического предложения, из которых формируют базу данных, представляющую собой БДЛП текстовых элементов лингвистического предложения; формирования второй структуры данных, на котором формируют вторую структуру данных СМД, содержащую элементы упомянутой второй структуры данных; формирования третьей структуры данных, на котором формируют третью структуру данных СМД, содержащую элементы упомянутой третьей структуры данных; и формирования четвертой ...

PROCEDURE FOR COMMUNICATING INFORMATION IN A PREFERENTIAL LANGUAGE OF A SERVER ABOUT MOBILES A COMMUNICATIONS EQUIPMENT

MESSAGE ANSWER SYSTEM

COMMUNICATION GATEWAY WITH MESSAGE COMMUNICATION INTERFACE

CONNECTION OVER INSTANTCOMMUNICATIONS CLIENTS

INFORMATIONSWIEDERGABE I/O PROCEDURE WITH POINT SAMPLE AND INFORMATION RENDITION MECHANISM

CONCLUSION OF CONNECTIONS WITH EXTENDED SERVICES

METHODS AND SYSTEMS FOR LANGUAGE TRANSLATION

SYSTEM AND METHOD FOR ENHANCING DOCUMENT TRANSLATABILITY

A teletranslation system and method for enhancing document translatability. The teletranslation system translates a document from one natural language to another. The system comprises an aggregate filter having a plurality of sections, each section performing a specific process or processes on the document in a predetermined order, each section having at least one atomic filter, and at least one MT engine for translating the processed document. The aggregate filter comprises a format conversion section, a text improvement section, a word tagging section, and a translation section. The aggregate filter analyzes the document based on a source text, format information, and a target language. The method further comprises the step of gathering specific data on the document at some atomic filters during the preprocessing step of their first pass, and using such specific data during the post-processing step of their second pass.

FILE TRANSLATION

A solution for translating translatable components in a file containing structured information from a source language to one or more selected destination languages is disclosed. In an embodiment, the translatable components in the original file may be identified by an identifier. Such an identifier may be, for example, a prefix character string which may be located using a suitable parser. The file and its translatable components may then be separated into a structural base or "skeleton" file, and an "isolated" file containing the translatable components. The translatable components in the isolated file may then be translated from the source language to a selected destination language to form translated components. These translated components in the isolated file may then be merged with the skeletal file to create a new file having substantially the same structure as the original file, but with the translatable components translated into the selected destination language.

SYSTEM AND METHOD FOR DISTRIBUTING MULTILINGUAL DOCUMENTS

A method and apparatus is disclosed for generating and distributing multilingual documents. The multilingual documents are comprised of primary information consisting of human-readable text and secondary information consisting of machine-readable data such that a translation of the text is accomplished by converting the human-readable text into a second language through the use of the decoded machine-readable data. The machine- readable data is comprised of a code that describes a set of editing operations that can be applied to the human- readable text to convert it into at least a second language. In a preferred embodiment, the machine-readable data is embedded in the image using an unobtrusive code on the document such as Xerox DATAGLYPH codes.

DISPLAYING AND CORRECTING METHOD FOR MACHINE TRANSLATION SYSTEM

FILE TRANSLATION

A solution for translating translatable components in a file containing structured information from a source language to one or more selected destination languages is disclosed. In an embodiment, the translatable components in the original file may be identified by an identifier. Such an identifier may be, for example, a prefix character string which may be located using a suitable parser. The file and its translatable components may then be separated into a structural base or "skeleton" file, and an "isolated" file containing the translatable components. The translatable components in the isolated file may then be translated from the source language to a selected destination language to form translated components. These translated components in the isolated file may then be merged with the skeletal file to create a new file having substantially the same structure as the original file, but with the translatable components translated into the selected destination language.

TRANSLATION INPUT METHOD

Translation Input Method (TIM) is an input method that was designed to input words and phrases by entering the same meaning characters of another language through a translation mechanism. This method can be typically applied in computer area for keyboard input.

METHOD AND APPARATUS FOR MULTI-SENSORY SPEECH ENHANCEMENT ON A MOBILE DEVICE

A mobile device includes an air conduction microphone and an alternative sensor that provides an alternative sensor signal indicative of speech. A communication interface permits the mobile device to communicate directly with other mobile devices.

POINTER INITIATED INSTANT BILINGUAL ANNOTATION ON TEXTUAL INFORMATION IN AN ELECTRONIC DOCUMENT

This invention provides a system and method for providing a user an artificial intelligence based bilingual annotation, displayed in a callout associated with the user's mouse pointer, on a piece of textual information contained in a segment of text adjacent to, or overlaid by, the user's mouse pointer while the user is reading an electronic document on the computer screen.

DOCUMENT REVISING SYSTEM FOR USE WITH DOCUMENT READING AND TRANSLATING SYSTEM

An image-to-character-position-correspondence-table producing unit produces image-to-character-position-correspondence-table composed of a set comprising an-image-of-a-document, a characterrecognized document and a translated document. A candidate character producing unit produces candidate c h a r a c t e r s f o r b a c k i n g u p t h e r e v i s i o n o f misrecognized characters. A Japanese-document-to-translated-document correspondence table stores a correspondence relationship between an original Japanese document and a translated document in the form of a table. When misrecognized characters are being revised, the image-to-character-position-correspondence-table is displayed by the image-to-character-position-correspondence-table. A revising unit prompts a user to specify a misrecognized portion in the translated document of the image-to-character-position-correspondence-table. Next, the revising unit refers to the Japanese-document-to-translated-document correspondence table to ...

DOCUMENT REVISING SYSTEM FOR USE WITH DOCUMENT READING AND TRANSLATING SYSTEM

INTEGRATED AUTHORING AND TRANSLATION SYSTEM

The present invention is a system of integrated, computer-based processes for monolingual information development and multilingual translation. An interactive text editor (140) enforces lexical and grammatical constraints on a natural language subset used by the authors (160) to create their text, which they help disambiguate to ensure translatability. The resulting translatable source language text undergoes machine translation into any one of a set of target languages, without the translated text requiring any postediting.

DEVICE FOR INTRODUCING SYMBOLS

СОЗДАНИЕ БАЗЫ ДАННЫХ СВЯЗЕЙ МЕЖДУ ПОНЯТИЯМИ

Предложены способ и устройство создания базы данных связей между понятиями. База данных связей между понятиями обеспечивает взаимосвязь слов и фраз на одном языке, соответствующих информации, находящейся в одном состоянии, со словами и фразами на втором языке, соответствующими информации, находящейся во втором состоянии. Способ содержит следующие этапы: принимают содержимое, выраженное в виде первого состояния, и принимают содержимое, выраженное в виде второго состояния, анализируют содержимое, выраженное в виде вышеупомянутого первого состояния, с вышеупомянутым содержимым, выраженным в виде вышеупомянутого второго состояния. При операции анализа используют фрагменты содержимого, выраженного в виде первого состояния, и фрагменты содержимого, выраженного в виде вышеупомянутого второго состояния. Способ также содержит этапы создания базы данных связей содержимого, находящегося в вышеупомянутом первом состоянии, с вышеупомянутым содержимым, находящимся в вышеупомянутом втором состоянии.

METHOD OF INTERACTION OF VIRTUAL FACIAL GESTURES WITH MESSAGE

It is claimed the method of interaction of virtual facial gestures with message wherein at replacing voice message (hereinafter referred to as VM1) which is pronounced or has been pronounced by displayed person on fully or partially another voice message (hereinafter referred to as VM2) instead of displaying part of face of specified person or part of face of specified person and at least one subject and/or at least one part of at least one subject from subjects, wholly or partially located on the face of specified person virtual facial gestures, which correspond to facial gestures at pronouncing VM2, are displayed. 1. A method of interaction of virtual facial gestures with message wherein at replacing voice message (hereinafter referred to as VM1) which is pronounced or has been pronounced by displayed person on fully or partially another voice message (hereinafter referred to as VM2) instead of displaying part of face of specified person or part of face of specified person and at least one subject and/or at least one part of at least one subject from subjects , wholly or partially located on the face of specified person , virtual facial gestures , which correspond to facial gestures at pronouncing VM2 , are displayed.2. The method according to claim 1 , wherein VM2 is a translation of VM1 from one speech language to another speech language.3. The method according to claim 1 , wherein VM2 is pronounced after pronouncing VM1 or VM2 is pronounced partially during pronunciation of VM1 and partially after pronunciation of VM1 claim 1 , or VM2 is pronounced during pronunciation of VM1.5. The method according to claim 1 , wherein at pronouncing VM 1 or VM 2: a) are additionally displayed person who is pronouncing or has pronounced VM 1 claim 1 , and/or b) at another display are in addition displayed person who is pronouncing or has pronounced VM 1 claim 1 , herewith to specified additionally displayed person and/or to specified person displayed at another display virtual ...

SYSTEM AND METHOD FOR MULTILANGUAGE TEXT INPUT IN A HANDHELD ELECTRONIC DEVICE

A system provides multilanguage text input in a handheld electronic device. The system includes one or more applications implemented in the handheld electronic device. The applications include a text input application requiring access to language data usable thereby. One or more language databases contain language data from a plurality of different languages usable by at least one of the applications including the text input application. An interface provides the applications with access to at least some of the different languages of the language data of the one or more language databases, in order that the applications including the text input application receive the different languages.

Systems and Methods for Determining the Language to Use for Speech Generated by a Text to Speech Engine

Algorithms for synthesizing speech used to identify media assets are provided. Speech may be selectively synthesized from text strings associated with media assets, where each text string can be associated with a native string language (e.g., the language of the string). When several text strings are associated with at least two distinct languages, a series of rules can be applied to the strings to identify a single voice language to use for synthesizing the speech content from the text strings. In some embodiments, a prioritization scheme can be applied to the text strings to identify the more important text strings. The rules can include, for example, selecting a voice language based on the prioritization scheme, a default language associated with an electronic device, the ability of a voice language to speak text in a different language, or any other suitable rule. 1. A method for synthesizing speech content based on a plurality of text strings , the method implemented by at least one computing device having at least one processor and at least one program stored in memory , the method comprising:identifying a respective language associated with each respective one of the plurality of text strings;distinguishing at least two different identified languages; andusing one or more rules to select a single language for generating the speech content for the plurality of text strings.2. The method of claim 1 , further comprising assigning a priority to each of the plurality of text strings claim 1 , including at assigning at least high priority text string and at least one low priority text string.3. The method of claim 2 , further comprising:identifying a default language associated with an electronic device providing the speech content;determining whether the identified languages are speakable in the default language; andin accordance with a determination that the identified languages are speakable in the default language, generating the speech content using the ...

Translation of a Selected Text Fragment of a Screen

Disclosed is a method for translating text fragments displayed on a screen from an input language into an output language and displaying the result. Translation may use electronic dictionaries, machine translation, natural language processing, control systems, information searches, (e.g., search engine via an Internet protocol), semantic searches, computer-aided learning, and expert systems. For a word combination, appropriate local or network accessible dictionaries are consulted. The disclosed method provides a translation in grammatical agreement in accordance with grammatical rules of the output language in consideration of the context of the text.

LANGUAGE IDENTIFICATION FOR DOCUMENTS CONTAINING MULTIPLE LANGUAGES

Multiple nonoverlapping languages within a single document can be identified. In one embodiment, for each of a set of candidate languages, a set of non-overlapping languages is defined. The document is analyzed under the hypothesis that the whole document is in one language and that part of the document is in one language while the rest is in a different, non-overlapping language. Language(s) of the document are identified based on comparing these competing hypotheses across a number of language pairs. In another embodiment, transitions between non-overlapping character sets are used to segment a document, and each segment is scored separately for a subset of candidate languages. Language(s) of the document are identified based on the segment scores. 119-. (canceled)20. A method of identifying one or more languages for a document , the languages being selected from a set of candidate languages , the method comprising:dividing the set of candidate languages into a plurality of disjoint subsets, wherein any two languages that are in different disjoint subsets do not overlap with each other;{'sub': 't', 'segmenting the document into one or more segments (t) of consecutive characters, wherein each segment t contains n-grams that have greater than a default probability of occurrence only for languages in an active one of the disjoint subsets (A);'}{'sub': t', 't, 'for each segment t, generating a segment score (S(L)) for each language (L) in the active one of the disjoint subsets A;'}{'sub': 't', 'identifying, by a processor, one or more languages as being languages of the document based on the segment scores S(L) for all of the segments t and languages L; and'}storing, in a computer readable storage device, information indicating the one or more languages of the document.21. The method of wherein two languages do not have overlap with each other in the event that the two languages have no characters in common with each other.22. The method of wherein two languages do ...

Quasi Natural Language Man-Machine Conversation Device Base on Semantic Logic

The presented is a tool and method for language presentation, browsing, editing, translation and communication based on Semantic Web, to be utilized as interface for collaborating software products and services or human-machine interaction. The conceptual system is extended to further include such objects as language components, sentence patterns or syntax rules, to get solutions for semantic logic representation devices, language presentation devices, semantic-language converting devices, the registry and delegation system, in forming a language-component-based system for browsing, editing, conversion and communication. It is always allowed to bring need-based control over the conceptual system and the registry with their scope and scale being kept at appropriate level; with a widespread community participation, the establishment of semantic-language converting device ecosystem will be important guarantee of a flexible and diversified language expression system; therefore to constitute the core of those pragmatic standards or specifications for machine translation, human-machine interface and the web system. 1111144111111111141. A semantic logic representation device () comprising one or more sets of symbols and markups representing conceptual objects and set of program codes associated with information processing device , wherein the said device () provides services integrating the conceptual objects according to their semantic relationships , the said device includes a function () to create language presentation devices () , the function being operable to create one or more language presentation devices () abiding by different grammar or syntax rules; the method to create the said device () includes establishing a semantic logic representation device () for each types of language component; in harness the hierarchical and containing relationship existing in the language components conceptual system , this process may be simplified by taking advantage of object- ...

Method and Apparatus for Cross-Lingual Communication

A system and method for a highly interactive style of speech-to-speech translation is provided. The interactive procedures enable a user to recognize, and if necessary correct, errors in both speech recognition and translation, thus providing robust translation output than would otherwise be possible. The interactive techniques for monitoring and correcting word ambiguity errors during automatic translation, search, or other natural language processing tasks depend upon the correlation of Meaning Cues and their alignment with, or mapping into, the word senses of third party lexical resources, such as those of a machine translation or search lexicon. This correlation and mapping can be carried out through the creation and use of a database of Meaning Cues, i.e., SELECT. Embodiments described above permit the intelligent building and application of this database, which can be viewed as an interlingua, or language-neutral set of meaning symbols, applicable for many purposes. Innovative techniques for interactive correction of server-based speech recognition are also described. 1. A method enabling cross linguistic communication through speech and text machine translation , comprising method operations of:receiving a first and a second language selection;receiving an expression in the first language;presenting the expression in the first language for verification;translating the verified expression into an expression in the second language;confirming the meaning of terms within the verified expression in the first language;back-translating the expression in the second language to a back-translated expression in the first language; andverifying the back-translated expression in the first language.2. The method of claim 1 , wherein the method operation of confirming the meaning of terms within the verified expression in the first language includes claim 1 ,receiving a selection of one of the terms;accessing a database supplying Meaning Cues associated with the one of the ...

DYNAMIC LANGUAGE TRANSLATION OF WEB SITE CONTENT

A method, system and computer program product for providing translated web content is disclosed. The method includes receiving a request from a user on a web site, the web site having a first web content in a first language, wherein the request calls for a second web content in a second language. The method further includes dividing the first web content into a plurality of translatable components and generating a unique identifier for each translatable component. The method further includes identifying a plurality of translated components of the second web content using the unique identifier of each of the plurality of translatable components of the first web content and putting the plurality of translated components of the second web content to preserve a format that corresponds to the first web content. The method further includes providing the second web content in response to the request that was received. 121-. (canceled)22. A computer-implemented method for providing translated web content , comprising the steps of:receiving a request from a user for content in a second language translated from content in a first language from a first Internet source;obtaining the content in the first language from the first Internet source;dividing the content in the first language into a plurality of translatable components, wherein a translatable component includes a segment of text;determining whether one or more translatable components have been previously translated with translated components, via human translation, into the second language, wherein each segment of text is translated as a unit;if there are one ore more translatable components previously translated generating the content in the second language by modifying the content in the first language so that at least some translatable components are replaced with corresponding translated components; andsending the content in the second language to the user as a response to the request. This non-provisional ...

SPEECH TRANSLATION APPARATUS, SPEECH TRANSLATION METHOD AND PROGRAM PRODUCT FOR SPEECH TRANSLATION

According to one embodiment, a speech translation apparatus includes a first input unit configured to input a first speech of a first speaker; a second input unit configured to input a second speech of a second speaker that is different from the first speaker; a first translation unit configured to translate the first speech to a first target language sentence; a second translation unit configured to translate the second speech to a second target language sentence; a first output unit configured to output the first target language sentence; a second output unit configured to output the second target language sentence; a speech detecting unit configured to detect a first speech duration from the first speech and detect a second speech duration from the second speech; and an output timing adjustment unit configured to adjust at least one of the first output unit and the second output unit, when the first speech duration and the second speech duration overlap each other. 1. A speech translation apparatus comprising:a processor;a first input unit configured to input a first speech of a first speaker;a second input unit configured to input a second speech of a second speaker that is different from the first speaker;a first translation unit configured to translate the first speech to a first target language sentence;a second translation unit configured to translate the second speech to a second target language sentence;a first output unit configured to output the first target language sentence;a second output unit configured to output the second target language sentence;a speech detecting unit configured to detect a first speech duration from the first speech and detect a second speech duration from the second speech; andan output timing adjustment unit configured to adjust at least one of the first output unit and the second output unit, when the first speech duration and the second speech duration overlap each other.2. The apparatus according to claim 1 , wherein the ...

Apparatus and method for interpreting korean keyword search phrase

An apparatus and method for interpreting a Korean keyword search phrase is provided. The apparatus for interpreting the Korean keyword search phrase may include an interface to receive a search phrase and to extract keywords from the search phrase, and a processor to classify the extracted keywords into at least one of a class, an instance, a property, and an attribute, based on a Korean sentence structure, and to obtain semantic information associated with the search phrase from a database, based on a result of the classifying.

DECONSTRUCTION AND CONSTRUCTION OF WORDS OF A POLYSYNTHETIC LANGUAGE FOR TRANSLATION PURPOSES

For facilitating subsequent translation of words in a target polysynthetic language (e.g. Cherokee) to or from a user language (e.g. English), a method of generating a language parsing reference database, assisted by a computer having a processor, including the steps of organizing the parsing reference database to include polysynthetic word parts WHO is doing an action, WHAT action is being done, HOW an action is happening and WHEN an action is happening. In one embodiment an internet website hosted on a computer server is established, the website being accessible to users via the internet. The computer server runs or executes server side software referencing the parsing reference database, and is operable to translate a word in the target polysynthetic language to the user language, or to construct a word in the target polysynthetic language from a sentence in a user language. 1. For facilitating subsequent translation of words in a target polysynthetic language to or from a user language , a method of generating a language parsing reference database , assisted by a computer having a processor , said method comprising:organizing the parsing reference database to include polysynthetic word parts WHO is doing an action, WHAT action is being done, HOW an action is happening and WHEN an action is happening;finding exemplars of polysynthetic words of the target polysynthetic language expressed in a selected system of orthography; andproviding as input to a deconstructor, as exemplars, a plurality of words in the polysynthetic language, employing the deconstructor to determine a character string common to the plurality of polysynthctic words as a likely character string in the target polysynthetic language for WHO, WHAT, HOW and WHEN in the user language, and storing the character string in the target polysynthetic language with the user language equivalent as a pair in the parsing reference database.2. The method of claim 1 , wherein said step of employing the ...

MACHINE TRANSLATION DEVICE AND MACHINE TRANSLATION METHOD IN WHICH A SYNTAX CONVERSION MODEL AND A WORD TRANSLATION MODEL ARE COMBINED

The present invention relates to statistical machine translation, and provides a machine translation device and a machine translation method that acquire a creation probability for a target language from a single corpus while extracting respective conversion probabilities by extracting syntax conversion knowledge and word translation knowledge from a parallel corpus, model a weighted translation model by allowing each of the conversion knowledge and each of the probabilities to learn using a translation model learning device, and generate a target sentence through decoding processes of a syntax converter and a word translator by applying the translation model to a source sentence input in real time, thereby resolving disadvantages of the existing phrase-based SMT and syntax-based SMT and combining advantages thereof. 1. A statistical machine translation device , comprising:a translation model constructor extracting syntax conversion knowledge and word translation knowledge of a target sentence by using word reordering information and syntax analysis information between a source sentence and the target sentence in a plurality of parallel corpora, and calculating conversion probabilities with respect to the respective extracted knowledges;a translation model learning device generating a syntax conversion model and a word translation model by learning the respective translation knowledges and conversion probabilities extracted through the translation model constructor; anda translated sentence generator decoding the source sentence into the target sentence by applying the syntax conversion model and the word translation model learned through the translation model learning device with respect to a source sentence input in real time.2. The statistical machine translation device of claim 1 , wherein:the translation model constructor further includesa language model generator generating a language model by extracting a creation probability of a target vocabulary string ...

ELECTRONIC DEVICE WITH A DICTIONARY FUNCTION AND DICTIONARY INFORMATION DISPLAY METHOD

An electronic device with a dictionary function includes a dictionary data memory, a dictionary search section which makes a dictionary search on the basis of a user operation, a series process storage section which stores data items representing the ones in a series of dictionary search processes performed at the dictionary search section, a detection section which detects an instruction to point in a direction given by a user operation, and a series process reproduction section which reads the series of processed data items stored in the series process storage section in response to the detection of an instruction to point in a specific direction at the detection section and displays a display screen corresponding to each of the processes on a display section. 1. An electronic device with a dictionary function comprising:a dictionary data memory which stores dictionary data;a dictionary search section which makes a dictionary search using the dictionary data on the basis of a user operation;a series process storage section which stores data items representing the ones in a series of dictionary search processes performed at the dictionary search section;a detection section which detects an instruction to point in a direction given by a user operation; anda process reproduction section which reads the series of processed data items stored in the series process storage section in response to the detection of an instruction to point in a specific direction given by a user operation at the detection section and displays a display screen corresponding to each of the processes on a display section.2. The electronic device of claim 1 , further comprising:a process history recording section which records, in sequence temporarily, data items representing processes involved in the series of dictionary search processes; anda process retracing section which sequentially reads data items representing the processes temporarily recorded in the process history recording section on ...

Enhanced Messaging with Language Translation Feature

A method for creating and managing a distribution list can include creating a distribution list at a voicemail system. The distribution list can include at least one recipient and at least one language preference for one or more of the at least one recipients. The method can further include selecting the created distribution list and recording an audio message to be sent to the at least one recipient. Translating the audio message into the at least one language preference for one or more of the at least one recipients thereby creating at least one translated audio message and sending the at least one translated audio message to the at least one recipient.

HANDHELD ELECTRONIC DEVICE AND ASSOCIATED METHOD ENABLING THE GENERATION OF A PROPOSED CHARACTER INTERPRETATION OF A PHONETIC TEXT INPUT IN A TEXT DISAMBIGUATION ENVIRONMENT

An improved handheld electronic device and associated method enable the phonetic inputting of text using a reduced keyboard and transformation algorithm. The handheld electronic device and method advantageously enable the inputting of languages such as Chinese, Japanese, Korean, and the like without limitation. The transformation algorithm subjects each of a number of linguistic element permutations to an algorithm such as the Maximum Matching Algorithm or other algorithm to generate a string of words. The transformation algorithm then selects one string of words as a default textual output based on at least one of its minimal number of words and its relatively high attributed frequency value. 18-. (canceled)9. A method of enabling input on an electronic device , the method comprising:detecting an ambiguous text input comprising a set of key selections, at least some of the keys each having a number of linguistic elements assigned thereto;determining a plurality of linguistic element permutations of the ambiguous input; generating a string of language objects that corresponds with at least an initial portion of the linguistic element permutation, and', 'generating a character interpretation string that comprises a number of words comprising characters that correspond with the string of language objects;, 'for each of a plurality of linguistic element permutations of the ambiguous inputselecting from among the generated character interpretation strings a set of generated character interpretation strings having the smallest number of words;if the set includes more than one generated character interpretation string then determining an attributed frequency value for each of the selected character interpretation strings, and selecting the character interpretation string with greatest attributed frequency; andoutputting, as at least partial output, the selected character interpretation string.10. The method of claim 9 , wherein the step of selecting a generated character ...

TRANSLATION APPARATUS AND METHOD THEREOF

Disclosed herein are a translation apparatus and a translation method. The translation apparatus includes: a speech input unit that receives a speech of a first language from a user; a control unit that generates sentences to be translated of the first language from the speech of the first language input from the speech input unit; a communication unit that transmits the sentences to be translated of the first language to a translation server and receives the sentences to be translated of a second language from the translation server; a display unit that displays the translated sentences of the second language along with previously translated sentences; a memory that stores a translation history including the sentences to be translated of the first language and the translated sentences of the second language; and a user input unit that receives an operation input of the previously translated sentences from a user. 1. A translation apparatus , comprising:a speech input unit that receives a speech of a first language from a user;a control unit that generates sentences to be translated of the first language from the speech of the first language input from the speech input unit;a communication unit that transmits the sentences to be translated of the first language to a translation server and receives the sentences to be translated of a second language from the translation server;a display unit that displays the translated sentences of the second language along with previously translated sentences;a memory that stores a translation history including the sentences to be translated of the first language and the translated sentences of the second language; anda user input unit that receives an operation input of the previously translated sentences from a user.2. The translation apparatus of claim 1 , further comprising:a speech output unit that converts the translated sentences of the second language into a speech and outputs the translated sentences of the second language ...

Instant Translation System

A method of, and corresponding headset computer for, performing instant speech translation including, establishing a local network including a link between a first and a second headset computer in which preferred language settings of each headset computer are exchanged, transmitting captured speech in a first language from a first headset computer to a network-based speech recognition service to recognize and transcribe the captured speech as text, receiving the text at the first headset computer, broadcasting the text over the local network to at least the second headset computer, receiving the text at the second headset computer, transmitting the received text from the second headset computer to a network-based text translation service to translate the text to a text in a second language, receiving the text in the second language at the second headset computer from the network-based text translation service, and displaying the translated text at the second headset computer. 1. A method of performing instant speech translation , the method comprising:establishing a local communications network including a link between at least a first and a second headset computer;capturing speech in a first language at the first headset computer;transmitting the captured speech in the first language from the first headset computer to a network-based speech recognition service to recognize and transcribe the captured speech as text in the first language;receiving the text in the first language at the first headset computer from the network-based speech recognition service;broadcasting the text in the first language over the local network to at least the second headset computer;receiving the text in the first language at the second headset computer;transmitting the received broadcast text in the first language from the second headset computer to a network-based text translation service to translate the text in the first language to a text in a second language;receiving the text in ...

CHINESE CHARACTER INFORMATION PROCESSING METHOD AND CHINESE CHARACTER INFORMATION PROCESSING DEVICE

A Chinese character information processing method and a Chinese character information processing device. The method comprises: an application determining a machine code of a Chinese character inputted by a user; determining Chinese character information of the Chinese character inputted by the user according to a correlation between a pre-stored machine code and pre-stored Chinese character information, the Chinese character information comprising a pronunciation of the Chinese character inputted by the user; when determining that the number of pronunciations of the Chinese character is multiple according to the Chinese character information of the Chinese character inputted by the user, determining a current pronunciation of the Chinese character inputted by the user from the multiple pronunciations; and storing the Chinese character information comprising the pronunciation being the determined current pronunciation and the machine code of the Chinese character. With the technical solution, when Chinese character information is stored in an application, a polyphonic character may be distinguished. 1. A Chinese character information processing method , comprising:determining a machine code of a Chinese character inputted by a user;determining Chinese character information of the Chinese character inputted by the user according to a pre-stored correspondence between a machine code and Chinese character information, the Chinese character information comprising a pronunciation of the Chinese character;when it is determined according to the determined Chinese character information that the Chinese character inputted by the user has a plurality of pronunciations, determining a current pronunciation of the Chinese character inputted by the user from the plurality of pronunciations; andstoring the machine code and the Chinese character information comprising the current pronunciation of the Chinese character inputted by the user.2. The method according to claim 1 , wherein ...

APPARATUS AND METHOD FOR PROVIDING TWO-WAY AUTOMATIC INTERPRETATION AND TRANSLATION SERVICE

The present invention relates to an apparatus and method for providing a two-way automatic interpretation and translation service. The apparatus includes a first interpretation and translation unit for interpreting and translating a first language into a second language. A second interpretation and translation unit interprets and translates the second language into the first language. A context information management unit receives conversational context and translation history information, and shares and manages the conversational context and translation history information. Each of the first and second interpretation and translation units provides an interpretation service for receiving an input conversation in the first or second language in speech and outputting results of interpretation in speech in the second or first language, and a translation service for receiving an input conversation in the first or second language in text and outputting results of translation in text in the second or first language. 1. An apparatus for providing a two-way automatic interpretation and translation service , comprising:a first interpretation and translation unit for interpreting and translating a first language into a second language;a second interpretation and translation unit for interpreting and translating the second language into the first language; anda context information management unit for receiving conversational context and translation history information processed when translation is performed from the first and second interpretation and translation units, and sharing and managing the conversational context and translation history information,wherein each of the first and second interpretation and translation units provides an interpretation service for receiving an input conversation in the first language or the second language in a form of speech and outputting results of interpretation of the input conversation in the form of speech in the second language or ...

MULTIPLE INPUT LANGUAGE SELECTION

Multiple language inputs may be provided to various applications programs and/or threads in a computer system. Such inputs may be directed to various software systems on the computer for further processing, wherein the software systems provide language-specific processing. Each application program and/or thread within an application program accessible by the computer may have a different selected input language. More specifically, systems, methods, and computer-readable media for this process may include: (a) determining an input language for a first application program accepting input through a computer; and (b) selecting at least one software system capable of accepting or operating on at least some of the input based, at least in part, on the input language determined for the first application program. In some examples, the input language of various software systems on the computer may be tied to the input language of another software system, such as the soft keyboard. 1determining an input language for a first application program accepting input through a computer; andrendering a soft keyboard on a display of the computer, wherein the soft keyboard is configured based, at least in part, on the input language determined for the first application program, wherein the input language is different from a system language of the computer.. A method, comprising: This application is a continuation of, and claims priority from, U.S. patent application Ser. No. 10/436,232, filed May 13, 2003, entitled “MULTIPLE INPUT LANGUAGE SELECTION,” which is incorporated herein by reference in its entirety.This invention generally relates to systems, methods, and computer-readable media for allowing multiple language input to various applications programs and/or threads active on a computer system. Such input maybe directed to various software systems on and/or accessible by the computer for further processing, wherein the software systems provide language-specific processing. The ...

TRANSLATION INTERFACING APPARATUS AND METHOD USING VISION TRACKING

Disclosed herein are a translation interfacing apparatus and method using vision tracking. The translation interfacing apparatus includes a vision tracking unit, a comparison unit, a sentence detection unit, a sentence translation unit, and a sentence output unit. The vision tracking unit tracks a user's eyes based on one or more images input via the camera of a portable terminal, and extracts time information about a period for which the user's eyes have been fixed and location information about a location on which the user's eyes are focused. The comparison unit compares the time information with a preset eye fixation period. The sentence detection unit detects a sentence corresponding to the location information if the time information is equal to or longer than the eye fixation period. The sentence translation unit translates the detected sentence. The sentence output unit outputs a translated sentence onto the screen of the portable terminal 1. A translation interfacing apparatus using vision tracking , comprising:a vision tracking unit configured to track a user's eyes based on one or more images input via a camera of a portable terminal, and to extract time information about a period for which the user's eyes have been fixed and location information about a location on which the user's eyes are focused;a comparison unit configured to compare the time information with a preset eye fixation period;a sentence detection unit configured to, if, as a result of the comparison, the time information is equal to or longer than the eye fixation period, detect a sentence corresponding to the location information;a sentence translation unit configured to translate the detected sentence, and to extract a translated sentence; anda sentence output unit configured to output the translated sentence onto a screen of the portable terminal.2. The translation interfacing apparatus of claim 1 , further comprising a setting unit configured to set the eye fixation period.3. The ...

Dynamic Translation Substitution

Mechanisms are provided for translating messages output by processes associated with the data processing system. Language based user activities occurring via a data processing system are tracked and automatically analyzed to determine a relative priority ordering of one or more languages used by a user performing the user activities. A sequence of preferred language translation substitutions is generated for outputting messages based on results of the analysis and is automatically applied to a received message from a process associated with the data processing system to generate a translated message using one of the preferred language translation substitutions in the sequence of preferred language translation substitutions. The translated message is output via an output device of the data processing system.

INPUT SUPPORT APPARATUS, INPUT SUPPORT METHOD, AND STORAGE MEDIUM CONTAINING INPUT SUPPORT PROGRAM

An input support apparatus includes an example sentence acquiring unit which acquires example sentence data including a plurality of example sentences for each theme; a keyword input unit which inputs a keyword according to user operations; a theme finding unit which finds a theme of an example sentence including the keyword among the example sentences included in the example sentence data; a text input unit which inputs a text according to user operations; and a correspondence example sentence display control unit which extracts one or more example sentences corresponding to the found theme and matching the inputted text from the example sentences for each theme included in the example sentence data, and which controls display of a list of the extracted example sentences. 1. An input support apparatus comprising:an example sentence acquiring unit which acquires example sentence data including a plurality of example sentences for each theme;a keyword input unit which inputs a keyword according to user operations;a theme finding unit which finds a theme of an example sentence including the keyword among the example sentences included in the example sentence data;a text input unit which inputs a text according to user operations; anda correspondence example sentence display control unit which extracts one or more example sentences corresponding to the theme found by the theme finding unit and matching the text inputted by the text input unit from the example sentences for each theme included in the example sentence data, and which controls display of a list of the extracted example sentences.2. The input support apparatus according to claim 1 , whereinthe correspondence example sentence display control unit includes:a keyword example sentence display control unit which extracts one or more example sentences corresponding to the theme found by the theme finding unit and including the keyword or a word relevant to the keyword from the example sentences for each theme ...

SPEECH TRANSLATION APPARATUS, METHOD AND PROGRAM

According to one embodiment, a speech translation apparatus includes a speech recognition unit, a translation unit, a search unit and a selection unit. The speech recognition unit successively performs speech recognition to obtain a first language word string. The translation unit translates the first language word string into a second language word string. The search unit search for at least one similar example and acquires the similar example and a translation example. The selection unit selects, in accordance with a user instruction, at least one of the first language word string associated with the similar example and the second language word string associated with the translation example, as a selected word string. 1. A speech translation apparatus comprising:an acquisition unit configured to acquire speech in a first language as a speech signal;a speech recognition unit configured to successively perform speech recognition on the speech signal to obtain a first language word string which is a result of the speech recognition;a translation unit configured to translate the first language word string into a second language to obtain a second language word string which is a result of translation;a search unit configured to search for at least one similar example for each first language word string, and, if there is the similar example, to acquire the similar example and a translation example which is a result of the translation of the similar example in the second language, the similar example indicating a word string that is similar to the first language word string in the first language;a selection unit configured to select, in accordance with a user instruction, at least one of the first language word string associated with the similar example and the second language word string associated with the translation example, as a selected word string; anda presentation unit configured to present one or more similar examples and one or more translation examples ...

HANDHELD ELECTRONIC DEVICE INCLUDING AUTOMATIC SELECTION OF INPUT LANGUAGE, AND ASSOCIATED METHOD

A method of automatically establishing an input language for a handheld electronic device includes receiving a request to initiate the composition of a new message, receiving a selection of a particular contact that is the intended recipient of the message, and determining whether the particular contact has a stored preferred input language. If a preferred input language is stored, the method includes determining whether the preferred input language is different than the current input language (which may be a pre-established default input language). If the preferred input language is different, the method further includes switching the current input language to the preferred input language. Also provided is an improved handheld electronic device having one or more routines adapted to implement the method. Also provided is a method of indicating a preferred language in association with a call received by or placed to the device. 127-. (canceled)28. A method for a handheld electronic device , comprising:storing address information for a contact and a preferred language associated with the contact;receiving a request to initiate composition of a message addressed to the contact;switching a current text input language of the handheld electronic device to the preferred language based on a determination that the preferred language is different from a default text input language of the handheld electronic device; andswitching the current text input language of the handheld electronic device back to the default language.29. The method of claim 28 , further comprising:creating the message as a reply to a previously received message.30. The method of claim 29 , wherein the previously received message was sent by the contact.31. The method of claim 28 , wherein the stored address information for the contact and the preferred language associated with the contact are stored in an address book.32. The method of claim 28 , wherein the message is one of an email message claim 28 , ...

Computer-Implemented Method, Computer Software and Apparatus for use in a Translation System

A computer-implemented method for use in natural language translation, including, performing in software processes, the steps of: comparing source material with stored material in a first natural language, said stored material having previously been translated from said first natural language to at least a second natural language, identifying at least a ‘part of said source material which has a relationship with at least a part of said stored material, outputting said identified part of source material and said identified part of stored material in a form suitable for review by a user, and replacing said identified part of source material with said identified part of stored material to assist full translation of said source material from said first natural language to at least said second natural language. 1. A method for reusing content from a translation memory comprising:receiving a predetermined correlation level, the predetermined correlation level being a user definable minimum percentage for a fuzzy logic match;comparing source material in a first language with stored material in the first language, the stored material being retrieved from a stored database and having previously been translated from the first language to a second language;identifying a part of the source material which has a relationship in the first language with at least a part of the stored material in the first language, the relationship exceeding the predetermined correlation level; andoutputting in the first language, the identified part of the source material and the related at least a part of the stored material in a form suitable for review by a user.2. The method of wherein the stored database comprises a translation memory.3. The method of wherein the translation memory comprises a plurality of stored segment pairs.4. The method of wherein the stored database comprises a terminology database.5. The method of further comprising dividing the source material into a plurality of source ...

Methods and apparatus for determining a language

According to a first aspect of the present invention there is provided a method of operating a telecommunications network to determine a language to be used for a message that is to be sent to a terminal of a user of the network. The method comprises the steps of inspecting packets sent over the network to and/or from a terminal used by the user in order to identify one or more languages specified within application layer protocol information contained in the packets; and selecting an identified language as the language that is to be used for the message.

Dynamic Language Translation of Web Site Content

Methods, systems, and computer readable medium for providing translated web content with translated URLs. A request is received content in a second language translated from content in a first language. The content in the first language is obtained from the first Internet source. One or more links are identified from the content in the first language. Each original URL is divided into one or more translatable URL components in the first language. Whether the one or more translatable URL components in each original URL have been previously translated into the second language and stored as translated URL components is determined. If there is at least one translatable URL component previously translated and stored as a corresponding translated URL component, a translated URL in the second language for each original URL is generated. The content in the second language with translated URLs is created.

MULTI-MODE INPUT METHOD EDITOR

Methods, systems, and apparatus, including computer program products, in which an input method editor receives composition inputs and determines language context values based on the composition inputs. Candidate selections based on the language context values and the composition inputs are identified. 1. A computer-implemented method , comprising:receiving, at a computing device including one or more processors, a composition input including one or more characters in a source language;determining, at the computing device, candidate selections for two or more target languages based on the composition input;determining, at the computing device, a language context value for each of the two or more target languages by evaluating the candidate selections against language models for the two or more target languages, wherein each language model includes a rule set for a corresponding target language;selecting, at the computing device, a set of the candidate selections based on the language context values, the set of candidate selections including at least one candidate selection in each of the two or more target languages; andoutputting, from the computing device, the set of candidate selections in a single, interleaved list of candidate selections arranged based on a relative likelihood that a specific candidate selection was intended from the composition input.2. The computer-implemented method of claim 1 , wherein outputting the set of candidate selections in the single claim 1 , interleaved list of candidate selections includes outputting a rank for each of the set of candidate selections claim 1 , each rank being indicative of the relative likelihood that its corresponding candidate selection was intended from the composition input.3. The computer-implemented method of claim 1 , wherein the two or more target languages include English and Chinese.4. The computer-implemented method of claim 1 , wherein the language models include a Chinese language model that includes ...

SYSTEM AND METHODS FOR SEMIAUTOMATIC GENERATION AND TUNING OF NATURAL LANGUAGE INTERACTION APPLICATIONS

A system for supervised automatic code generation and tuning for natural language interaction applications, comprising a build environment comprising a developer user interface, automated coding tools, automated testing tools, and automated optimization tools, and an analytics framework software module. Text samples are imported into the build environment and automated clustering is performed to assign them to a plurality of input groups, each input group comprising a plurality of semantically related inputs. Language recognition rules are generated by automated coding tools. Automated testing tools carry out automated testing of language recognition rules and generate recommendations for tuning language recognition rules. The analytics framework performs analysis of interaction log files to identify problems in a candidate natural language interaction application. Optimizations to the candidate natural language interaction application are carried out and an optimized natural language interaction application is deployed into production and stored in the solution data repository. 1. A system for supervised automatic code generation and tuning for natural language interaction applications , the system comprising:a solution data repository component operating on a server computer and comprising a plurality of hierarchical ontological domain models and a plurality of hierarchical language models comprising a preconfigured, hierarchical arrangement of language objects, a plurality of language recognition rules expressed in terms of elements of the plurality of hierarchical language models;a build environment comprising a plurality of software modules stored or operating on a computer, the plurality of software modules comprising a developer user interface, a plurality of automatic text analysis tools, a plurality of automated coding tools, a plurality of automated testing and tuning tools, and a plurality of automated optimization tools; andan analytics framework ...

SYSTEM, METHOD AND COMPUTER PROGRAM FOR CORRECTING MACHINE TRANSLATION INFORMATION

A computer implemented machine translation system and method is provided that improves the accuracy of output from one or more machine translation systems by applying one or more data correction routines. A data correction routine is provided that includes information distance analysis of one or more sets of machine translation information to a set of text elements related to the domain and stored to a database. The system and method generate as output corrected text elements related to a meaning intended by a user from whom the machine translation information was captured. 1. A computer implemented machine translation method , comprising:capturing one or more elements of a source language using a language analysis means, the one or more elements of language relating to a domain;using one or more machine translation utilities so as to generate one or more sets of target language information based on the one or more elements of the source language;applying one or more correction routines to the one or more sets of machine translation information that include information distance analysis of the one or more sets of machine translation information to a set of text elements related to the domain and stored to a database; andconstructing one or more data outputs related to a meaning intended by a user by the one or more elements of source language.2. The method of claim 1 , wherein the information distance analysis comprises:{'sub': 'max', '(a) a max distance D(x,y) operation; and'}(b) a complementary information distance operation to address partial matching and removes irrelevant information3. The method of claim 2 , wherein the complementary information distance operation defines D(x claim 2 ,y)=E(x claim 2 ,y) that when executed yields an information distance between a first set of entities claim 2 , and a second set of entities claim 2 , that determines the most accurate entity by disregarding irrelevant information. where there may be irrelevant information in one ...

Language translation in an environment associated with a virtual application

Methods and apparatus for language translation in a computing environment associated with a virtual application are presented. For example, a method for providing language translation includes determining languages of a user and a correspondent; determining one or more sequences of translators; determining a selected sequence of selected translators from the one or more sequences of the translators; requesting a change in virtual locations, within the computing environment associated with the virtual application, of one or more selected translator virtual representations of the selected translators to a virtual meeting location within the computing environment associated with the virtual application; and changing virtual locations of the one or more selected translator virtual representations to the virtual meeting location. One or more of determining languages, determining one or more sequences, determining a selected sequence, requesting a change in virtual locations, and changing virtual locations occur on a processor device.

On-Demand Language Translation for Television Programs

A method, a system and a machine-readable medium are provided for an on demand translation service. A translation module including at least one language pair module for translating a source language to a target language may be made available for use by a subscriber. The subscriber may be charged a fee for use of the requested on demand translation service or may be provided use of the on demand translation service for free in exchange for displaying commercial messages to the subscriber. A video signal may be received including information in the source language, which may be obtained as text from the video signal and may be translated from the source language to the target language by use of the translation module. Translated information, based on the translated text, may be added into the received video signal. 1. A method comprising:receiving a request from a subscriber to translate a signal from a source language to a target language, wherein the signal comprises audio data and text information in the source language;charging the subscriber a fee for a translation capability during a paid-for period, after which the translation capability expires; andgenerating a translated signal comprising the audio data in the target language and a translated text in the target language based on the text information in the source language during the paid-for period.2. The method of claim 1 , wherein the signal comprises a video portion.3. The method of claim 2 , wherein the text information is extracted by performing speech recognition on the audio portion of the signal.4. The method of claim 2 , wherein generating the translated signal further comprises:embedding the audio data and the translated text in the audio portion of the translated signal.5. The method of claim 1 , wherein the fee is based on an amount of time the on-demand translation service is to be made available to the subscriber.6. The method of claim 1 , wherein the fee is based on a pair of the source ...

Analyzing Web Site for Translation

A system, method and computer readable medium for synchronizing web content is disclosed. The method includes retrieving a first web content in a first language from a web site, the first web content corresponding to a second web content wherein the second web content is a translation in a second language of the first web content. The method further includes dividing the first web content into a plurality of translatable components and generating a unique identifier for each of the plurality of translatable components. The method further includes matching each of the plurality of translatable components to a plurality of translated components of the second web content using the unique identifier of each of the plurality of translatable components. If a translatable component is not matched to a translated component, the method further includes designating the translatable component for translation into the second language. 121-. (canceled)22. A machine implemented method for providing statistics characterizing content for language translation , comprising the steps of:obtaining content in a first language from an Internet source via a publicly accessible network path;identifying a portion of the content in the first language that is not yet translated into a second language; andgenerating statistics based only on the portion of the content in the first language that is not yet translated in order to estimate the amount of work involved in language translation from the first language to the second language. This non-provisional application is a Continuation of U.S. patent application Ser. No. 12/609,834, entitled “ANALYZING WEB SITE FOR TRANSLATION”, filed on Oct. 30, 2009, which is a Continuation of U.S. patent application Ser. No. 10/784,334, entitled “ANALYZING WEB SITE FOR TRANSLATION”, filed on Feb. 23, 2004, which is a continuation-in-part of the provisional patent application Ser. No. 60/449,571 with inventors Enrique Travieso, Adam Rubenstein, and William ...

DISPLAYING ORIGINAL TEXT IN A USER INTERFACE WITH TRANSLATED TEXT

Methods, systems, and apparatus, including computer program products, for user interaction with machine translation. A user interface for receiving requests to translate text and/or documents from a first language text to a second language text. The translated text and/or document is displayed such that the first language text corresponding to a selected portion of the second language text can be accessed and displayed in the same user interface. 1. A method comprising:receiving, using one or more processors, a user request to translate a source document from a first language text to a second language text;obtaining, using the one or more processors, a translated document containing a translation of the source document into the second language text;presenting, using the one or more processors, the translated document to the user; andpresenting, using the one or more processors, the first language text that corresponds to a portion of the translated document in a graphical element overlaying the translated document in response to the user pointing to the portion of the translated document.2. The method of claim 1 , further comprising:presenting, using the one or more processors, the first language text after a predetermined period of time has elapsed after the user points to the portion of the translated document;removing, using the one or more processors, the graphical element after a second predetermined period of time has elapsed after a user ceases to point to the portion of the translated document; andcanceling, using the one or more processors, the removal of the graphical element if the user again points to the portion of the translated document before the second predetermined period of time has elapsed.3. The method of claim 1 , wherein presenting the first language text that corresponds to the portion of the translated document in the graphical element overlaying the translated document comprises transmitting the first language text to a client device for ...

LANGUAGE SEGMENTATION OF MULTILINGUAL TEXTS

The claimed subject matter provides a system and/or method for segmenting a multi-language text. An exemplary method comprises determining an initial probability distribution for sentences in the multi-language text, the initial probability distribution indicating the likelihood of each sentence being in each of a set of languages. A probability of language transitions across sentences may be learned based on the initial probability distribution. Additionally, a highest probability language sequence of sentences in the multi-language text may be determined based on a combination of the probability of language transitions and the prior probability distribution provided by an initial model. Further, web documents are annotated at a sentence by sentence level such that each sentence of a web document is labeled in a given language according to the highest probability language determined. 1. A method of segmenting a multi-language text , comprising:determining, using a processing unit, an initial probability distribution for sentences in a web document in the multi-language text, the initial probability distribution indicating the likelihood of each sentence being in each of a set of languages;learning, using the processing unit, a probability of language transitions across sentences based on the initial probability distribution;determining, using the processing unit, a highest probability language sequence of sentences in the multi-language text based on a combination of the probability of language transitions and a prior probability distribution provided by an initial model; andannotating web documents at a sentence by sentence level such that each sentence of a web document is labeled in a given language according to the highest probability language determined.2. The method recited in claim 1 , comprising using an automatic language detector to determine the sentences in the multi-language text.3. The method recited in claim 1 , wherein learning the probability of ...

COMPUTER IMPLEMENTED METHOD, PROGRAM, AND SYSTEM FOR IDENTIFYING NON-TEXT ELEMENT SUITABLE FOR COMMUNICATION IN MULTI-LANGUAGE ENVIRONMENT

A computer implemented method, a program, and a system for effectively providing versatile non-text information suitable for use in a multi-language environment. The method includes the steps of: receiving search results of a database using a search criterion in a certain language and a search criterion in another language corresponding to the search criterion in which specific language attributes are associated with non-text elements that are included in the search results; scoring the non-text elements included in the search results depending on a similarity to another element with which a different language attribute is associated; and identifying at least one of the non-text elements included in the search results on the basis of the scores. 1. A computer implemented method for identifying a non-text element suitable for communication in a multilanguage environment by using a database in which a non-text element can be searched for , the method comprising the steps of:receiving search results of the database using a search criterion in a certain language and a search criterion in another language corresponding to the search criterion in which specific language attributes are associated with non-text elements that are included in the search results;scoring the non-text elements included in the search results depending on a similarity to another element with which a different language attribute is associated; andidentifying at least one of the non-text elements included in the search results on the basis of the scores.2. The method according to claim 1 , wherein claim 1 , in the scoring step claim 1 , a non-text element having a high similarity to another element with which a different language attribute is associated is given a high score.3. The method according to claim 1 , further comprising the step of translating the search criterion in the certain language by using a translation engine to generate a search criterion in the other language.4. The method ...

WIRELESS COMMUNICATION DEVICE HAVING SPEECH RECOGNITION, SPEECH TRANSLATION, AND HEARING AID FUNCTIONS

Provided is a wireless communication device having speech recognition, speech translation, and hearing aid functions, which includes: an ITE (In-The-Ear) type radio transceiver including a microphone that receives an external voice, an ITE (In-The-Ear) type radio signal processor that processes radio data received from the microphone, a receiver that converts electrical signals from the radio signal processor into sound pressure, a volume controller that controls the intensity of the sound pressure, and a coil antenna for short-range wireless communications; and a portable radio repeater including a portable communication device that relays signals transmitted from the coil antenna of the ITE type radio transceiver, a coil antenna for short-range wireless communications with the ITE type radio transceiver, and a radio frequency (RF) antenna for two-way wireless communications with a portable radio repeater owned by another conversation partner. 1. A wireless communication device having speech recognition , speech translation , and hearing aid functions , the wireless communication device comprising:an ITE (In-The-Ear) type radio transceiver including a microphone that receives an external voice, an ITE (In-The-Ear) type radio signal processor that is attached to a person's ear, and that processes radio data received from the microphone, a receiver that converts electrical signals from the radio signal processor into sound pressure, a volume controller that controls the intensity of the sound pressure output from the radio signal processing unit, and a coil antenna for short-range wireless communications; anda portable radio repeater including a portable communication device that relays signals transmitted from the coil antenna of the ITE type radio transceiver, a coil antenna for short-range wireless communications with the ITE type radio transceiver, and a radio frequency (RF) antenna for two-way wireless communications with a portable radio repeater owned by ...

DESIGNING A WEBSITE TO BE DISPLAYED IN MULTIPLE LANGUAGES

A method for building websites including at least one language translation is provided. The method incorporates a language translation into an individual website having a default display language, wherein the step of incorporating comprises saving the language translation as part of the individual website, and wherein the language translation is available for viewing at the individual website; and adds a language switching feature to the individual website, the language switching feature enabling an end-user to change the default display language of the individual website to the language translation. 1. A method for building websites including at least one language translation , the method comprising:incorporating a language translation into an individual website having a default display language, wherein the step of incorporating comprises saving the language translation as part of the individual website, and wherein the language translation is available for viewing at the individual website; andadding a language switching feature to the individual website, the language switching feature enabling an end-user to change the default display language of the individual website to the language translation.2. The method of claim 1 , wherein the language switching feature comprises a drop-down menu of a plurality of user-selectable language options for the individual website; andwherein the plurality of user-selectable language options comprises one or more languages that have been incorporated into the individual website.3. The method of claim 2 , further comprising:receiving end-user input selecting one of the plurality of user-selectable language options, via the drop-down menu; andchanging the default display language of the website according to the end-user input.4. The method of claim 1 , further comprising:exporting a language file for translation, the language file comprising language data from the website;importing a translation file, the translation file ...

TRANSLATING DIGITAL RECEIPTS BETWEEN WRITTEN LANGUAGES

The present invention extends to methods, systems, and computer program products for translating digital receipts between written languages. In response to a user request, digital receipts (e.g., for retail sales transactions) can be translated from a first written language to a second written language. Translated digital receipts can be presented on a display at a mobile device. Translation can be handled at a receipt data server or at the mobile device. Translation can be performed locally or can be referred to a translation server. Digital receipts can be translated from and/or to any of a variety of different written languages. 1. At a receipt data server for a merchant , the receipt data server including one or more processors and system memory , the receipt data server connected to one or more Point-Of-Sale (POS) systems at each of one or more store locations for the merchant , the receipt data server configured to manage a receipt data for the merchant , a method for transferring translated digital receipt data to a mobile device , the method comprising:receiving digital receipt data for a sales transaction conducted at a Point-Of-Sale (POS) system, the Point-Of-Sale (POS) system at a store location selected from among the one or more store locations, the digital receipt data containing a receipt entry for each of one or more items purchased by a customer in the sales transaction;generating a digital receipt for the sales transaction in a first written language, the digital receipt generated from the digital receipt data, the digital receipt providing proof of the sales transaction, the digital receipt for delivery to a mobile device associated with the customer;storing the digital receipt in the first written language for subsequent access by a mobile device;receiving a request from a mobile device for digital receipts associated with the mobile device, the request requesting digital receipts be returned in a specified second written language;in response to ...

Machine translation apparatus, method and program

According to one embodiment, a machine translation apparatus includes a translation unit, an acquisition unit, a first calculation unit, a reverse translation unit, a second calculation unit and a selection unit. The acquisition unit acquires, at least one second forward-translated word different from the first forward-translated word, to obtain candidate words. The reverse translation unit obtains at least one reverse-translated word for each of the candidate words by reverse-translating each candidate word into the first language. The selection unit selects a corrected forward-translated word to be replaced with the first forward-translated word from among the candidate words based on the semantic similarity and fluency.

LANGUAGE LEARNING PLATFORM USING RELEVANT AND CONTEXTUAL CONTENT

A method and system for displaying translated text for language learning having content in a first language and a translation thereof in a second language. A user can hover over the content with a mouse to display a popup box containing a content component in the second language corresponding to a content component in the first language. The content components are highlighted as the user hovers over them with the mouse to identify corresponding content components between the first language and the second language. Also provided is an electronic flashcard generated by the user from the content. 1. A method comprising:receiving first content information in a first language, the first content information including at least one paragraph, the at least one paragraph comprising at least one sentence, the at least one sentence comprising a first plurality of words;receiving input specifying a phrase included within the first content information wherein the phrase includes ones of the first plurality words;receiving a translated phrase corresponding to the phrase, the translated phrase comprising a second plurality of words in a second language;storing, within a memory, correspondence information mapping one or more of the second plurality of words to one or more of the first plurality of words; andstoring, within the memory, the first content information and the translated phrase in association with the correspondence information so as to form dual language content associated with the first content information.2. The method of further including receiving input specifying additional phrases included within the first content information and additional translated phrases corresponding to the additional phrases;wherein the first content information includes a plurality of paragraphs and wherein the correspondence information includes first correspondence information identifying, for the translated phrase and for each of the additional translated phrases, a corresponding one of ...

INFORMATION REPRODUCING METHOD, INFORMATION INPUTTING / OUTPUTTING METHOD, INFORMATION REPRODUCING DEVICE, PORTABLE INFORMATION INPUTTING/ OUTPUTTING DEVICE AND ELECTRONIC TOY USING DOT PATTERN

The present invention proposes a dot pattern on which code information and x and y coordinate information can be defined even if the dot pattern is extremely small, and proposes an information reproducing method and an information reproducing device based on the dot pattern. More specifically, a medium such as a printed material on which is formed a dot pattern portion by arranging in accordance with a given rule dots generated by a dot code generating algorithm in order to recognize various kinds of multimedia information is scanned as image data by scanning means. Then, the image data is converted into code data. Multimedia information corresponding to the code data is read out of storing means to be reproduced. 1. A dot pattern , of which data content is defined by comprising:dots, a predetermined number of which are equally spaced and arranged in a first straight line direction;dots, a predetermined number of which are equally spaced and arranged in a second straight line direction; andinformation dots that are arranged at positions shifted from intersections of second virtual lines virtually set in parallel to the second straight line direction from the dots arranged in the first straight line direction and first virtual lines virtually set in parallel to the first straight line direction from the dots arranged in the second straight line direction,wherein an orientation of the dot pattern can be recognized by absence of one of the dots arranged in the first straight line direction or one of the dots arranged in the second straight line direction on a third virtual line that connects the dots arranged in the first straight line direction or a fourth virtual line that connects the dots arranged in the second straight line direction.2. A dot pattern , of which data content is defined by comprising:dots, a predetermined number of which are equally spaced and arranged in a first straight line direction;dots, a predetermined number of which are equally spaced and ...

Information reproduction/i/o method using dot pattern, information reproduction device, mobile information i/o device, and electronic toy using dot pattern

The present invention proposes a dot pattern on which code information and x and y coordinate information can be defined even if the dot pattern is extremely small, and proposes an information reproducing method and an information reproducing device based on the dot pattern. More specifically, a medium such as a printed material on which is formed a dot pattern portion by arranging in accordance with a given rule dots generated by a dot code generating algorithm in order to recognize various kinds of multimedia information is scanned as image data by scanning means. Then, the image data is converted into code data. Multimedia information corresponding to the code data is read out of storing means to be reproduced.

PARAMETER ADJUSTMENT METHOD USED FOR STATISTICAL MACHINE TRANSLATION

The present invention relates to a parameter adjustment method. The parameter adjustment method used for statistical machine translation comprises: step using a monolingual corpus to construct a language model required for translation; step using a bilingual parallel corpus to construct a translation model; and step using a target function to adjust a parameter. The method can solve problems in prior art that the parameter is easily over-fit or falls into a local optimum during a parameter adjustment process, and the method is easy to implement and can combine a larger number of features. In addition, the target function is convex; therefore, global optimum can be achieved in a training process. This is a national phase national application of an international patent application number PCT/CN2013/088284 with a filing date of Dec. 2, 2013, which claimed priority of one foreign application which is filed in China: application number 201310029538.0 and filing date Jan. 25, 2013. The contents of these specifications, including any intervening amendments thereto, are incorporated herein by reference.1. Field of InventionThe present invention relates to a method of parameters adjustment.2. Description of Related ArtsWith the rapid development of internet and in-depth economic globalization, interpersonal communications between different nations is more and more frequent. Language issues become the barrier which restricts the free communications between people. In order to use our national language for barrier-free communications with the world, more and more extensive demand for translation services is needed.Written or spoken manual translation by human operator may not only be time consuming, but also costly. The object of machine translation is to achieve an automated translation from one language to another language. At present, a variety methods of machine translation are existed, which includes machine translation based on actual usage examples and machine ...

Bilingual Search Engine for Mobile Devices

We disclose a method for a bilingual search engine producing a top list of concordances ranked by information content, controlled by a query of key words extended with parameters specifying the length of the concordances, the depth of the Internet search and a language of choice for a computer-generated translation of the results. Concordances are ranked by Shannon information using the method of van Putten, U.S. 2013/0191365 and accompanied by images extracted from the originating web pages. The method is particularly useful in creating universal access to the mostly English information on the World Wide Web. 2. A computer implemented method for a bilingual search engine facilitating universal access described in with the property that said method is run from the user's device such as a PC claim 1 , tablet or mobile phone.3. A computer implemented method for a bilingual search engine facilitating universal access described in with the property that said method operated by the user through a web browser claim 1 , where said method is running on a remote server as a software-as-a-service. This invention relates generally to techniques for extracting information from large digital data bases by key word queries. Specifically, it relates to extracting concise text and image information in the form of concordances, ranked by Shannon information using the method of van Putten, U.S. 2013/0191365, and associated images, where the concordances are presented in two languages. The first language is the language of the originating document, and the second language is a language of choice by the reader.Given the continuing exponential growth of the World Wide Web (WWW) and the migration of user access through mobile devices, Internet search engines are facing the challenge of effectively presenting concise information on relatively small screens. Furthermore, most of the web pages on the WWW are in English, while the population at large is mostly non-native English speaking. ...

OBTAINING TRANSLATIONS UTILIZING TEST STEP AND SUBJECT APPLICATION DISPLAYS

In one example of the disclosure, a machine-translation for each of a plurality of strings is determined, the strings for display upon execution of a subject application. A first display of a test step to be performed by a test application during execution of the subject application is caused. A second display of a state for the subject application that includes the plurality of strings is caused concurrent with the first display. A user-translation for each of the strings is obtained, the user-translations provided via a GUI included within the second display. A translation property file associated with the subject application is amended to include the user-translations. 1. A system , comprising:a machine-translation engine, to determine a machine-translation for each of a plurality of strings, the strings for display upon execution of a subject application;a first display engine, to cause a first display of a test step to be performed by a test application during execution of the subject application;a second display engine, to cause, concurrent with the first display, a second display of a state for the subject application that includes the plurality of strings;a user-translation engine, to obtain a user-translation for each of the strings, the user-translations provided via a GUI included within the second display; anda property file engine, to amend a translation property file associated with the subject application to include the user-translations.2. The system of claim 1 , wherein the first display engine is to obtain a user-initiated instruction to begin a quality assurance test upon the subject application claim 1 , and the first display engine is to cause the first display and the second display engine is to cause the second display responsive to receipt of the instruction.3. The system of claim 1 , wherein the test step is performed by the test application concurrent with the provision of the second display.4. The system of claim 1 , wherein the GUI is a ...

PREDICTING FUTURE TRANSLATIONS

Technology is disclosed for snippet pre-translation and dynamic selection of translation systems. Pre-translation uses snippet attributes such as characteristics of a snippet author, snippet topics, snippet context, expected snippet viewers, etc., to predict how many translation requests for the snippet are likely to be received. An appropriate translator can be dynamically selected to produce a translation of a snippet either as a result of the snippet being selected for pre-translation or from another trigger, such as a user requesting a translation of the snippet. Different translators can generate high quality translations after a period of time or other translators can generate lower quality translations earlier. Dynamic selection of translators involves dynamically selecting machine or human translation, e.g., based on a quality of translation that is desired. Translations can be improved over time by employing better machine or human translators, such as when a snippet is identified as being more popular. 120-. (canceled)21. A method for automatically improving a speed of statistical machine translation , the method comprising:receiving a snippet to translate, the snippet comprising a digital representation including one or more words or character groups;determining one or more output languages for the translation of the snippet;computing an expected amount of time before the translation of the snippet in the one or more output languages will be needed; 'wherein the selecting is based on: (A) a measure of time for the selected translator to perform the translation of the snippet and (B) the expected amount of time; and', 'automatically improving statistical machine translation by selecting, from among multiple possible translators, a translator to perform the translation of the snippet,'}using the selected translator to perform the translation of the snippet into the one or more output languages.22. The method of claim 21 , wherein determining the one or more ...

METHOD AND SYSTEM FOR GENERATING A CONVERSATIONAL AGENT BY AUTOMATIC PARAPHRASE GENERATION BASED ON MACHINE TRANSLATION

The present teaching relates to generating a conversational agent. In one example, a plurality of input utterances may be received from a developer. A paraphrase model is obtained. The paraphrase model is generated based on machine translation. For each of the plurality of input utterances, one or more paraphrases of the input utterance are generated based on the paraphrase model. For each of the plurality of input utterances, at least one of the one or more paraphrases is selected based on an instruction from the developer to generate selected paraphrases. The conversational agent is generated based on the plurality of input utterances and the selected paraphrases. 1. A method , implemented on a machine having at least one processor , storage , and a communication platform connected to a network for generating a conversational agent , the method comprising:obtaining, based on a paraphrase model, one or more paraphrases for each of a plurality of input utterances;selecting at least one of the one or more paraphrases for each input utterance based on an intent of the input utterance to generate selected paraphrases; andgenerating a conversational agent based on the plurality of input utterances and the selected paraphrases.2. The method of claim 1 , further comprising:obtaining aggregated training data based on stored user-agent dialogs, the at least one of the one or more paraphrases, or the stored user-agent dialogs and the at least one of the one or more paraphrases.3. The method of claim 2 , further comprising:selecting, based on the aggregated training data, the paraphrase model from a plurality of paraphrase models.4. The method of claim 3 , wherein a plurality of N-grams features are generated from the aggregated training data claim 3 , selecting the paraphrase model comprises:determining, based on the plurality of N-grams, that the aggregated training data comprises new training data related to the paraphrase model, wherein the paraphrase model is updated ...

VIRTUAL PARTICIPANT-BASED REAL-TIME TRANSLATION AND TRANSCRIPTION SYSTEM FOR AUDIO AND VIDEO TELECONFERENCES

The present disclosure describes a teleconferencing system that may use a virtual participant processor to translate language content of the teleconference into each participant's spoken language without additional user inputs. The virtual participant processor may connect to the teleconference as do the other participants. The virtual participant processor may intercept all text or audio data that was previously exchanged between the participants may now be intercepted by the virtual participant processor. Upon obtaining a partial or complete language recognition result or making a language preference determination, the virtual participant processor may call a translation engine appropriate for each of the participants. The virtual participant processor may send the resulting translation to a teleconference management processor. The teleconference management processor may deliver the respective translated text or audio data to the appropriate participant. 1. A method for providing translation services during a teleconference , comprising:receiving a request from one of the participants in the teleconference for the addition of a virtual participant processor to the teleconference, wherein the request includes a location identifier of a teleconference management processor and an identifier of the teleconference session;determining the language preferences of each of the teleconference participants;in response to a participant request for a virtual participant processor received by a teleconference management system, sending a request to the virtual participant processor to join the established teleconference;in response to the request by the teleconference management system, connecting a virtual participant processor to the teleconference session;intercepting speech data from each of the teleconference participants;recognizing a speech language of each of the teleconference participants;translating the intercepted speech data from the recognized speech language of ...

CHINESE NAME TRANSLITERATION

Chinese name transliteration is described. A Chinese name including a surname followed by a given name is received. The received Chinese name is parsed into a surname and a given name by: identifying any dual-character surnames in the received Chinese name, by referencing a list of known Chinese surnames; identifying any single-character surnames in the received Chinese name, by referencing the list of known Chinese surnames; and identifying, among the remaining characters in the received Chinese name, any characters not belonging to a dual-character or a single-character surname as a given name. The identified surname and the identified given name are transliterated into a Mandarin Pinyin representation. The Mandarin Pinyin representation of the surname and the given name is normalized into a pre-determined representation. 1. A computer-implemented method for Chinese name transliteration , comprising:receiving, by a processor, a Chinese name including a surname followed by a given name; identifying any dual-character surnames in the received Chinese name, by referencing a list of known Chinese surnames,', 'identifying any single-character surnames in the received Chinese name, by referencing the list of known Chinese surnames, and', 'identifying, among the remaining characters in the received Chinese name, any characters not belonging to a dual-character or a single-character surname as a given name,, 'parsing, by the processor, the received Chinese name into a surname and a given name bytransliterating, by the processor, the identified surname and the identified given name into a Mandarin Pinyin representation; andnormalizing, by the processor, the Mandarin Pinyin representation of the surname and the given name into a pre-determined representation.2. The method of claim 1 , wherein the transliterating of the surname and given name is performed using an International Components for Unicode Han-Latin module.3. The method of claim 1 , wherein the name parsing uses a ...

OMEGA NAMES: NAME GENERATION AND DERIVATION

In a computing resource environment including at least two different resource name spaces, a method for generating a fully-qualified name for a resource based on a context-based name of that resource and a usage context is disclosed. Method steps include receiving the resource's name schema, its context-based name, and usage context; comparing an entry in the schema and an entry in the context-based name and identifying schema monikers missing from the context-based name. For a missing moniker, determining whether it is an attribute space (aspace) moniker. If it is an aspace moniker, adding it to a full name that includes the context-based name. If it is not an aspace moniker, determining the aspace associated with the missing moniker; searching the usage context for an association between the missing moniker, its aspace, and a value assigned to the missing moniker; and appending the searched-for items to the full name. 1. In a computing resource environment including at least two different resource name spaces , a method of generating a fully qualified resource name for a particular resource based on a context-based name of that resource and a particular usage context , the method comprising:receiving, as inputs, a name schema associated with the resource name, the context-based name, and the usage context;comparing an entry in the name schema and an entry in the context-based name;determining, based on an outcome of said comparing, whether the schema includes a moniker that is missing from the context-based name;in response to a determination that the schema includes a moniker that is missing from the context-based name, determining whether the missing moniker is an attribute space moniker;in response to a determination that the missing moniker is an attribute space moniker, adding the attribute space moniker to a full name that includes the context-based name; determining the attribute space associated with the missing moniker;', 'searching the usage context for ...

Speech Recognition Systems Having Diverse Language Support

A method for providing cross-language automatic speech recognition is provided. The method includes choosing a preferred first language for a speech recognition system. The speech recognition system supports multiple languages. A search operation is initiated using the speech recognition system. A user is prompted to continue the search operation in the first language or a second language. In response to the user selection of continuing in the second language, searching is provided in the second language and interaction is provided with the user in the first language during the search operation. 1. A method for providing cross-language automatic speech recognition , the method comprising:choosing a preferred first language for a speech recognition system, the speech recognition system supporting multiple languages;initiating a search operation using the speech recognition system;prompting a user to continue the search operation in the first language or a second language; andin response to the user selection of continuing in the second language, providing searching in the second language and providing interaction with the user in the first language during the search operation.2. The method of claim 1 , wherein the first language comprises French and the second language comprises English.3. The method of further comprising claim 1 , in response to the user selection of continuing in the first language claim 1 , providing searching and speech interaction with the user in the first language.4. The method of further comprising displaying search results in the second language.5. The method of further comprising searching for an address using the speech recognition system.6. The method of claim 5 , wherein the address is in Quebec claim 5 , Canada.7. The method of claim 1 , wherein the speech recognition system is in a vehicle.8. The method of further comprising using phonetic data to recognize speech in the first and second languages.9. An automatic speech recognition ...

SYSTEM AND METHOD FOR PROVIDING AN INTELLIGENT LANGUAGE LEARNING PLATFORM

A system for providing an intelligent language learning platform may be provided. The system may have one or more servers programmed to execute method steps. The steps may include analyzing content on a display of a mobile device or personal computer to identify text in a first language to be translated into a second language for a user to view and learn; displaying a user interface on the display, the user interface including one or more active regions in which a user may actively engage content and/or enter input, the one or more active regions including the text translated in the second language for the user to engage; sensing, in the content active region, a user engaging the translated text; and in response to the user engagement, generating a further content for user engagement. 1. A method for providing an intelligent language learning platform comprising:accessing content displayed on a device screen;retrieving text and adjacent content on the device screen;retrieving location data for the retrieved text and adjacent content;comparing retrieved text to a database comprising at least one of user data and target words or phrases;identifying at least one target word or phrase based on the comparison;capturing an image of the at least one target word or phrase and adjacent content;editing the image to replace the text of the at least one target word or phrase, which is presented in a first language, with text translated into a second language;overlaying the edited image on the content displayed on the device screen to show the text of the at least one target word or phrase in the second language.2. The method of claim 1 , wherein the process is terminated if the number of target words or phrases in the accessed content is below a pre-determined threshold.3. The method of claim 1 , wherein the overlaid content comprises an active region to initiate an action when engaged by a user.4. The method of claim 3 , wherein the action comprises at least one of reading the ...

METHOD, APPARATUS, DEVICE AND SYSTEM FOR SIGN LANGUAGE TRANSLATION

The present disclosure provides a method, an apparatus, a device and a system for sign language translation, where a server receives video information sent by a terminal device, and preprocesses the video information to obtain at least one sign language action; the at least one sign language action is input into a sign language model for classification and prediction to obtain a word corresponding to the at least one sign language action; each word is input into a language model to determine whether an intention expression is complete; and each word is sent to the terminal device when the intention expression is complete, so that the terminal device displays each word, thereby realizing the translation of the sign language action into text, enabling the ordinary persons to better understand intentions of the hearing impaired, thus improving efficiency of communications. 1. A method for sign language translation , comprising:receiving video information sent by a terminal device and preprocessing the video information to obtain at least one sign language action;inputting the at least one sign language action into a sign language model for classification and prediction to obtain a word corresponding to the at least one sign language action;inputting the each word into a language model to determine whether an intention expression is complete; andsending the each word to the terminal device when the intention expression is complete.2. The method according to claim 1 , wherein the inputting the at least one sign language action into the sign language model for classification and prediction to obtain the word corresponding to the at least one sign language action comprises:generating, for each sign language action, a prediction request corresponding to the sign language action, wherein the prediction request comprises the sign language action and a collecting time corresponding to the sign language action;determining, according to a load condition and a resource condition ...

SELECTIVELY DELIVERING A TRANSLATION FOR A MEDIA ASSET BASED ON USER PROFICIENCY LEVEL IN THE FOREIGN LANGUAGE AND PROFICIENCY LEVEL REQUIRED TO COMPREHEND THE MEDIA ASSET

Methods and systems are described herein for a media guidance application that selectively provides a translation corresponding to a media asset based on a level of proficiency of the language required to comprehend the media asset and a level of proficiency of the user corresponding to the language. The media guidance application provides an output comprising the translation in response to determining that the level of proficiency of the user is lower than the level of proficiency of the language required to comprehend the media asset. 1. A method of delivering a translation , the method comprising:determining a language spoken in a media asset;retrieving a profile for a user viewing the media asset;determining, based on the profile, whether the language is a language native to the user;in response to determining that the language is native to the user, generating an output comprising the media asset; determining a level of proficiency of the language required to comprehend the media asset;', 'identifying, based on the profile, a level of proficiency of the user corresponding to the language;', 'determining whether the level of proficiency of the language required to comprehend the media asset is equal to, higher than, or lower than the level of proficiency of the user;', 'in response to determining that the level of proficiency of the user is equal to or higher than the level of proficiency of the language required to comprehend the media asset, generating an output comprising the media asset;', 'in response to determining that the level of proficiency of the user is lower than the level of proficiency of the language required to comprehend the media asset, requesting a translation to a language native to the user; and', 'in response to receiving the translation, generating an output comprising the translation., 'in response to determining that the language is not native to the user2. The method according to claim 1 , wherein the level of proficiency of the user ...

METHOD FOR PROVIDING FOREIGN LANGUAGE ACQUIREMENT STUDYING SERVICE BASED ON CONTEXT RECOGNITION USING SMART DEVICE

According to the method of the present invention for providing a foreign language acquisition and learning service based on context awareness by using a smart device, a service provider server receives user information from a user terminal, extracts foreign language learning content by using the user information, and transmits same to the user terminal, thereby providing the foreign language learning content that is tailored to the context of the user and the information of the user. 1. A method of providing a context awareness-based foreign language acquisition and learning service using a smart device , the method comprising:(1) receiving, by a service provision server, user information from a user terminal;(2) extracting foreign language learning content using at least any one of context information of a user and the received user information; and(3) transmitting the extracted foreign language learning content to the user terminal; andfurther comprising, before step (2), the step of receiving event information from a scheduler of the user in response to a request from the user terminal,wherein step (2) comprises the step of extracting the foreign language learning content using the received event information as the context information, andwherein the user terminal is a smart device on which an application program for receiving and outputting the foreign language learning content has been installed.2. The method of claim 1 , wherein the user information comprises an age claim 1 , gender claim 1 , vocation claim 1 , foreign language level claim 1 , hobby or field of interest of the user.3. The method of claim 1 , wherein the context information comprises time information claim 1 , season information claim 1 , weather information claim 1 , issue information claim 1 , theme information claim 1 , event information received from the user terminal claim 1 , surrounding environment information claim 1 , emotion information or location information received from the user ...

Language translator module in the middleware tool process integration

A process integration system to interface between a sender system and a receiver system is described. The process integration system has a sender adapter, an integration engine, a receiver adapter, and a language converter module. The sender adapter receives a communication in a first language from the sender system. The communication is in a first format of the sender system. The sender adapter converts the communication into a second format of the process integration system, and the integration engine identifies the receiver system from the communication in the second format. The receiver adapter converts the communication from the second format to a third format of the receiver system, and sends the communication in the third format and in a second language to the receiver system. The language converter module translates the communication in the third format to the second language associated with the receiver system.

VOICE COMMUNICATION DEVICE WITH FOREIGN LANGUAGE TRANSLATION

Methods and devices for voice communications and foreign language translation are disclosed. One method includes selecting one of a plurality of microphones of an earpiece unit, receiving a selected voice communication of a first language from the selected microphone and translating the selected voice communication from the first language to a second language, the second language different from the first to create a translated voice communication, and transducing the translated voice communication at a speaker within the earpiece unit. Preferably the microphones are oriented in different directions and are directional microphones. The present invention further optionally provides for the sensing and transmission of pulse oximeter measurements and temperature measurements. 1: A method for voice translation comprising:providing to a first person a translation device having a housing and a microphone and a speaker within the housing;receiving at the microphone of the translation device a voice communication in a first language from a second person while the translation device is physically with the first person;processing the voice communication in the first language into text in the first language using the translation device;translating the text in the first language to text in a second language;converting the text in the second language to a voice communication in the second language; andtransducing the voice communication in the second language at the speaker of the translation device to the first person.2: The method of wherein the translation device comprises an earpiece.3: The method of wherein the processing the voice communication is performed by a processor of the earpiece.4: The method of wherein the earpiece comprises a plurality of microphones.5: The method of wherein the translating is performed at a remote location.6: A method for voice translation comprising:providing to a first person a translation device having a housing and a microphone and a speaker ...

Audio Bible Players with a Numerical Indexing System and a Multiple Bible Version Playback Function

Audio bible players with a 6-digit numerical indexing system to the chapter level or a 9-digit numerical indexing system to the verse level are disclosed. Users can not only find a particular chapter or verse of the bible quickly, but also can switch to the same chapter or verse of a different translation easily for comparison study. They are easy and convenient to use, and are great tools for bible study, bible memorization, language study, and sharing bible with people in other languages, etc.

EFFICIENT HANDLING OF BI-DIRECTIONAL DATA

A tool for standardized layout transformations of BIDI data exchanged between legacy and modern systems is provided. The tool retrieves client connection information from a client request for data. The tool determines, based, at least in part, on the client connection information, a client application's operating system. The tool determines whether the data requested in the client request is BIDI data. Responsive to a determination that the data requested is BIDI data, the tool initiates a layout transformation of the data requested at a single point within the database server. The tool returns transformed BIDI data to the client application. 1one or more computer readable storage devices and program instructions stored on the one or more computer readable storage devices, the program instructions comprising:program instructions to retrieve client connection information from a client request for data;program instructions to determine based, at least in part, on the client connection information, an operating system of a client application, wherein the determination indicates whether the operating system is a modern operating system;program instructions to determine whether the data requested in the client request is BIDI data, wherein determining includes identifying the data requested and determining whether the data requested exhibits one or more bi-directional properties that indicate BIDI data;program instructions to determine the data requested is BIDI data where the data requested exhibits layout properties indicative of BIDI data;responsive to a determination that the data requested is BIDI data, program instructions to initiate a layout transformation of the data requested at a single point within a database server, wherein initiating includes determining a plurality of data from a connection string of the client request, where the plurality of data indicates a type of bi-directional data transformation for converting the BIDI data into a layout compatible ...

SYMBOL PREDICTION WITH GAPPED SEQUENCE MODELS

A symbol prediction method includes storing a statistic for each of a set of symbols w in at least one context, each context including a string of k preceding symbols and a string of l subsequent symbols, the statistic being based on observations of a string kwl in training data. For an input sequence of symbols, a prediction is computed for at least one symbol in the input sequence, based on the stored statistics. The computing includes, where the symbol is in a context in the sequence not having a stored statistic, computing the prediction for the symbol in that context based on a stored statistic for the symbol in a more general context. 1. In a machine translation system which generates input text sequences of symbols by translation of source sentences or in a dialog system which generates input text sequences of symbols by converting structured representations of text to input sequences in a natural language , a symbol prediction method comprising:storing a statistic for each of a set of symbols w in at least one context, each context including a string of k preceding symbols and a string of l subsequent symbols, where k is at least 1 and l is at least 1, the statistic being based on observations of a string kwl in training data;with a processor, for an input text sequence of symbols, computing a prediction for at least one symbol in the input sequence, based on the stored statistics, the computing including, where the symbol is in a context in the sequence not having a stored statistic, computing the prediction for the symbol in that context based on a stored statistic for the symbol in a more general context;computing a prediction for the input sequence of symbols based on the predictions for the symbols in the input sequence; and a prediction for the input sequence of being in a given language, or', 'a candidate input sequence with a highest prediction from a set of candidate input sequences, the set of candidate input sequences including the input sequence ...

TRANSLATION APPARATUS, TRANSLATION SYSTEM, AND NON-TRANSITORY COMPUTER READABLE MEDIUM

A translation apparatus includes a translation unit which translates content of a document into a different language, a history creating unit which, in translation of the content from a first language into a second language, creates history information including a correspondence between original text in the first language and translated text in the second language, an extraction unit which, in translation of the content from the second language into another language, if content (present content) of the document in the second language is present in the history information, extracts content (absent content) that is not present in the history information, and a combining unit which combines a translation result obtained by translating the present content from the second language into the other language, with a replacement result obtained by replacing the absent content from the second language to the other language based on the history information. 1. A translation apparatus comprising:a translation unit that translates content of a document into a different language;a history creating unit that, when the translation unit translates the content of the document from a first language into a second language, creates history information including a correspondence between original text in the first language and translated text in the second language;an extraction unit that, when the translation unit is to translate the content of the document from the second language into another language, if content of the document written in the second language is present in the history information, extracts content that is not present in the history information; anda combining unit that combines a result of translation with a result of replacement, the result of translation being obtained by the translation unit translating the content that is not present in the history information, the translating being performed from the second language into the other language, the result of ...

ENABLING AN IM USER TO NAVIGATE A VIRTUAL WORLD

A user is enabled to interact with a virtual world environment using an instant messenger application by enabling a user to enter the virtual world environment using the instant messenger application that includes an instant messaging (IM) user interface, generating and managing an avatar to represent the user in the virtual world environment, monitoring a sub-portion of the virtual world environment corresponding to a current location of the user in the virtual world environment, determining descriptions of activities taking place in the sub-portion of the virtual world environment based on the monitoring, and providing the user with the determined descriptions of activities taking place in the sub-portion of the virtual world environment via the IM user interface. 119.-. (canceled)20. A computer-implemented method for enabling electronic communications between users , the method comprising the following operations performed by at least one processor:enabling a first user to navigate a first environment by controlling a representation of the first user in the first environment;capturing a first paralinguistic indicator made by the first user, the first paralinguistic indicator configured for communications in the first environment and reflecting at least one of a facial expression or gesture;translating the first paralinguistic indicator into a message configured for text-based communications in a second environment, the message comprising at least one of a text description of the at least one facial expression or gesture indicated by the first paralinguistic indicator and a second paralinguistic indicator configured for communications in the second environment, the second paralinguistic indicator comprising a graphical object and being different from the first paralinguistic indicator; andproviding the message to a second user.21. The computer-implemented method of claim 20 , the method further comprising the following operation performed by the at least one ...

LEXICON DEVELOPMENT VIA SHARED TRANSLATION DATABASE

A speech translation system and methods for cross-lingual communication that enable users to improve and customize content and usage of the system and easily. The methods include, in response to receiving an utterance including a first term associated with a field, translating the utterance into a second language. In response to receiving an indication to add the first term associated with the field to a first recognition lexicon, adding the first term associated with the field and the determined translation to a first machine translation module and to a shared database for a community associated with the field of the first term associated with the field, wherein the first term associated with the field added to the shared database is accessible by the community. 1. A method comprising:receiving, from a user, an utterance in a first language, the utterance including a first term;determining word class information for the first term;determining an intra-class probability for the first term, the intra-class probability reflecting a relevance of the first term to the user relative to other terms in a lexicon of the user sharing the word class information; andadding the first term, the word class information, and the intra-class probability to the lexicon of the user.2. The method of claim 1 , wherein the intra-class probability is determined based on when the utterance was received from the user.3. The method of claim 1 , wherein the intra-class probability is determined based on reference information about the first term.4. The method of claim 3 , wherein the first term is a name of a city and the reference information is a population of the city.5. The method of claim 3 , wherein the reference information is one or more references to the first term in media.6. The method of claim 1 , wherein the intra-class probability is determined based on one or more activities of the user.7. The method of claim 6 , wherein the one or more activities includes a current location of ...

AUTOMATIC INTERPRETATION METHOD AND APPARATUS

Provided is an automated interpretation method, apparatus, and system. The automated interpretation method includes encoding a voice signal in a first language to generate a first feature vector, decoding the first feature vector to generate a first language sentence in the first language, encoding the first language sentence to generate a second feature vector with respect to a second language, decoding the second feature vector to generate a second language sentence in the second language, controlling a generating of a candidate sentence list based on any one or any combination of the first feature vector, the first language sentence, the second feature vector, and the second language sentence, and selecting, from the candidate sentence list, a final second language sentence as a translation of the voice signal. 1. An automated interpretation method comprising:encoding a voice signal in a first language to generate a first feature vector;decoding the first feature vector to generate a first language sentence in the first language;encoding the first language sentence to generate a second feature vector with respect to a second language;decoding the second feature vector to generate a second language sentence in the second language;controlling a generating of a candidate sentence list based on any one or any combination of the first feature vector, the first language sentence, the second feature vector, and the second language sentence; andselecting, from the candidate sentence list, a final second language sentence as a translation of the voice signal.2. The method of claim 1 , wherein the generating of the candidate sentence list includes acquiring a candidate sentence claim 1 , from a database claim 1 , determined to correspond to any one or any combination of the first feature vector claim 1 , the first language sentence claim 1 , the second feature vector claim 1 , and the second language sentence from a database.3. The method of claim 2 , wherein the acquiring ...

Selection biasing

In some implementations, data indicating a touch received on a proximity-sensitive display is received while the proximity-sensitive display is presenting one or more items. In one aspect, the techniques describe may involve a process for disambiguating touch selections of hypothesized items, such as text or graphical objects that have been generated based on input data, on a proximity-sensitive display. This process may allow a user to more easily select hypothesized items that the user may wish to correct, by determining whether a touch received through the proximity-sensitive display represents a selection of each hypothesized item based at least on a level of confidence that the hypothesized item accurately represents the input data.

TEXT TRANSLATION USING CONTEXTUAL INFORMATION RELATED TO TEXT OBJECTS IN TRANSLATED LANGUAGE

In an example embodiment, input is received from a first user of a computer system. A text object relating to a first item from the input is created, and translated from a first language to a second language. A plurality of text objects, in the second language, having text similar to the translated text object, are located in a database, each text object comprising textual information pertaining to the first item. The plurality of text objects having text similar to the translated text are then ranked based on a comparison of the contextual information about the first item and the contextual information stored in the database for the plurality of text objects having text similar to the translated text object. At least one of the ranked text objects is translated to the first language. 1. (canceled)2. An apparatus comprising:a memory storing a database of text objects pertaining to items, the database further including contextual information about the items;a translation module executable by a processor and configured to translate a text object created from input received from a first user about a first item from a first language to a second language;a context ranking module configured to locate, in the database, a plurality of text objects, in the second language, having text similar to the translated text object, and to rank the plurality of text objects having text similar to the translated text object based on a comparison of contextual information about the first item and the contextual information stored in the database for the plurality of text objects having text similar to the translated text object;the translation module further configured to translate at least one of the ranked text objects to the first language; anda display module presenting the translated at least one of the ranked text objects.3. The apparatus of claim 2 , further comprising a feedback module configured to receive feedback from the first user used to select one of the at least one ...

METHOD AND SYSTEM FOR AUTOMATICALLY TRANSLATING PROCESS INSTRUCTIONS

A method and system automatically translate process instructions. In the method, a process instruction is received in a first language that different from a second language being the operating language of the manufacturing execution system (MES). A text of the received process instruction is extracted in real time by a processing unit using an extraction algorithm. The method continues with searching and finding in real time in a database a translation of the extracted text into the second language. The database includes for all texts of all process instructions expressed in the first language, a translation of said texts into the second language. The texts in the first language and their corresponding translation are preferentially organized in a dictionary. Further, creating a process instruction in the second language from the found text in the second language and automatically displaying in real time the process instruction in the second language. 1. A method for automatically translating , in real time , process instructions within a manufacturing execution system (MES) , the method comprising the following steps:receiving a process instruction in a first language different from a second language that is the operating language of the MES;extracting in real time, by a processing unit using an extraction algorithm, a text from the process instruction to generate an extracted text;searching a database in real time to find a translation of the extracted text into the second language, the database containing a translation into the second language for all texts of all process instructions expressed in the first language;creating in real time a process instruction in the second language from the extracted text; anddisplaying in real time the process instruction in the second language.2. The method according to claim 1 , which comprises carrying out each of the method steps automatically.3. The method according to claim 1 , wherein the texts in the first language and a ...

SPEECH CONVERTER

Disclosed is a speech converter for inter-translation between Chinese and the official language of the other party including a matching card for forming unidirectional matches of a word, a phrase a word group, a short sentence, a common expression and, a sentence expressing the same meaning. The matching cards include a word matching card, a phrase matching card, a word group matching card, a short sentence matching card, a common expression matching card and a sentence matching card. The present invention enables a user to translate what he/she wants to say into a language that a listener can understand immediately, so that the listener can hear and understand these words and answer immediately, and the answer is sent back in mandarin. 1. A speech converter for inter-translation between Chinese and the official language of the other party , comprising a matching card for forming unidirectional matches of a word , a phrase a word group , a short sentence , a common expression and a sentence expressing the same meaning; wherein the matching card comprise a word matching card , a phrase matching card , a word group matching card , a short sentence matching card , a common expression matching card and a sentence matching card;unidirectionality refers to the translation from Chinese to the official language of the other party or the translation from the official language of the other party to Chinese.2. The speech converter according to claim 1 , wherein the matching card is further used for generating corresponding words and phrases in the other party's official language expressing the same meaning in the Chinese words; the matching card is further used for generating corresponding word groups claim 1 , short sentences claim 1 , common expressions claim 1 , sentences in the other party's official language expressing the same meaning in the Chinese word groups claim 1 , short sentences claim 1 , common expressions claim 1 , sentences; the matching card is the ...

METHOD FOR COLLECTING TRANSLATED CONTENT, AND TRANSLATION SERVER

Provided are a method by which a translation server collects translated content from at least one device, and a translation server therefor. The translation server may provide, to users using at least one device, a translation request category for participation in translation, and collect translated content from the users. The translation server may provide rewards to the users providing the translated content. 1. A method by which a server collects translated content , the method comprising:determining translation target content constructed in a first language;determining a translation request category for requesting translation of the determined translation target content;providing a translation request graphical user interface (GUI) corresponding to the determined translation request category to at least one device connected to the server; andacquiring, from the at least one device, translated content translated from the translation target content into a second language,whereinthe translation request GUI comprises a translation request message corresponding to the determined translation request category, andthe translated content is input to the device through the translation request GUI.2. The method of claim 1 , wherein the determining of the translation target content comprises selecting at least one of a corpus claim 1 , a coined word claim 1 , an acronym claim 1 , a proper noun claim 1 , a technical term claim 1 , and a dialogue as translation target content claim 1 , according to a predetermined criterion.3. The method of claim 1 , wherein the translation request category comprises at least one of a direct translation request category claim 1 , a translated content verification category claim 1 , an educational content provision category claim 1 , an audiovisual content provision category claim 1 , and a game content provision category.4. The method of claim 1 , further comprising verifying the acquired translated content claim 1 ,wherein the verifying of ...

MULTI-DIMENSIONAL COMMERCE PLATFORM

Aspects of the present disclosure relate to a multi-dimensional commerce platform that may be utilized for the communication of data. Aspects of the multi-dimensional commerce platform may include various functional components to facilitate a system to receive inventory data at a first server associated with the multi-dimensional commerce platform, provide a second server associated with a third-party (e.g., a third party seller/distributor) access to the inventory data, alter or modify the inventory data based on attributes of the second server, and cause display of a presentation of the modified inventory data at a client device. 1. A method comprising:receiving, at a first server, an inventory that includes at least a first item, the first item having item attributes;providing access to the inventory to a second server, the second server having a server identifier;modifying the item attributes of the first item based on the server identifier of the second server; andcausing display of a presentation of the first item at a client device, the presentation based on the modified item attributes.2. The method of claim 1 , wherein the method further comprises:receiving a transaction request for the first item at the second server;routing the transaction request from the second server to the first server; andcausing a purchase of the first item.3. The method of claim 1 , wherein the item attributes include a price and a first display language claim 1 , and the modifying the item attributes includes:translating the first display language to a second display language; andaltering the price.4. The method of claim 1 , wherein the causing display of the presentation of the first item at the client device includes:receiving, at the second server, a search request that identifies the first item; andgenerating the presentation of the first item based on the modified item attributes.5. The method of claim 1 , wherein the item attributes of the first item include an item ...

BIDIRECTIONAL SPEECH TRANSLATION SYSTEM, BIDIRECTIONAL SPEECH TRANSLATION METHOD AND PROGRAM

A bidirectional speech translation system, a bidirectional speech translation, method and a program are provided for executing speech translation by using a combination of a speech recognition engine, a translation engine, and a speech synthesis engine that are suitable for received speech or a language of the received speech. The bidirectional speech translation system executes processing for synthesizing speech by translating first language speech entered by a first speaker into a second language and processing for synthesizing speech by translating second language speech entered by a second speaker into a first language. The engine determining unit determines a combination of a first speech recognition engine, a first translation engine, and a first speech synthesis engine, and a combination of a second speech recognition engine, a second translation engine, and a second speech synthesis engine based on at least one of the first language, the first language speech entered by the first speaker, the second language, and the second language speech entered by the second speaker. 1. A bidirectional speech translation system comprising:a first determining unit that determines a combination of a first speech recognition engine, a first translation engine, and a first speech synthesis engine, based on at least one of a first language, a first language speech entered by a first speaker, a second language, and a second language speech entered by the second speaker;a first speech recognition unit that executes speech recognition processing implemented by the first speech recognition engine, in response to an entry of the first language speech by the first speaker, to generate text that is a recognition result of the first language speech;a first translation unit that executes translation processing implemented by the first translation engine to generate text by translating the text generated by the first speech recognition unit into the second language;a first speech ...

COMPUTERIZED SIMULTANEOUS INTERPRETATION SYSTEM AND NETWORK FACILITATING REAL-TIME CALLS AND MEETINGS

A computerized VoIP system which provides a computerized service for facilitating face-to-face and/or telephone meetings, in real time, between persons lacking a common language or having language barriers such as accents and dialects e.g. by utilizing or generating a networked worldwide community of Simultaneous Interpreters, using e.g. POTS (Plain Old Telephone Service), Smart Phone or any mobile phone. A platform may thereby be provided for professional simultaneous interpreters and business/private people, where interpreters from all over the world may translate any face-to-face meeting or telephone call between business people in any combination of languages, in real time. 1. A conferencing system which provides a service to conference participants , the system comprising:a teleconference bridge server operative for controlling a telephony provider to facilitate teleconferences between previously defined communicants; and ["a conference definition environment operative to allow conference initiators to define at least one requested conference's time, participants and need, if any, for at least one conference service provider to provide at least one conference service to at least one of said participants at said time; and", ["electronic notification functionality operative to send electronic notification to at least a portion of a population of service providers of at least one desired conference's time and need for at least one conference service provider, as defined via said environment, and", 'at least one processor operative to receive at least one message from at least one individual service provider in the population of service providers, each message confirming intention of the individual service provider to provide said service for said individual conference, and to command the telephony provider, via the teleconference bridge server, to add the individual service provider to the individual conference by establishing at least one audio channel between ...

Photographing Method and Apparatus, and Terminal Device

A terminal device obtains a first instruction triggering a photographing function, presents a viewfinder window on a first screen, obtains a feature parameter of a target image, where the target image is an image presented in the viewfinder window, presents preset playing content on a second screen when the feature parameter of the target image matches a standard feature parameter, and performs a photographing operation. Therefore, after the photographing function is enabled, the viewfinder window is presented, and the preset playing content is played on the second screen, where the playing content may attract attention of a photographed target such that the photographed target is stimulated in a short time to show a vivid expression. 1. A photographing method , wherein the photographing method is applied to a terminal device comprising a first screen and a second screen , and wherein the photographing method comprises:obtaining a first instruction, wherein the first instruction triggers a photographing function of the terminal device;presenting a viewfinder window on the first screen in response to the first instruction;obtaining a feature parameter of a target image, wherein the target image is an image presented in the viewfinder window;presenting preset playing content on the second screen in response to the feature parameter of the target image matching a standard feature parameter; andperforming a photographing operation.2. The photographing method of claim 1 , wherein the standard feature parameter comprises a user-defined standard feature parameter claim 1 , wherein the feature parameter of the target image comprises a first feature parameter claim 1 , and wherein the feature parameter of the target image matches the standard feature parameter when the first feature parameter of the target image matches the user-defined standard feature parameter.3. The photographing method of claim 2 , further comprising:setting the user-defined standard feature parameter; ...

SOCIALLY DERIVED TRANSLATION PROFILES TO ENHANCE TRANSLATION QUALITY OF SOCIAL CONTENT USING A MACHINE TRANSLATION

The present disclosure relates generally to the field of socially derived translation profiles to enhance translation quality of social content using a machine translation. In various embodiments, methodologies may be provided that automatically use socially derived translation profiles to enhance translation quality of social content using a machine translation. 1. A method implemented in a computer system for translating content , wherein the content has an author who is part of a social network , the method comprising:receiving the content by the computer system;retrieving from the social network, by the computer system, contextual information associated with the content;retrieving from the social network, by the computer system, author information associated with the author;creating, by the computer system, a content-specific dictionary based upon the retrieved contextual information and the retrieved author information;creating, by the computer system, a translation profile based upon the retrieved contextual information, the retrieved author information and the created content-specific dictionary;determining, by the computer system, one of a plurality of generic dictionaries to use for the translating, wherein the determination of the one of the plurality of generic dictionaries to use is based upon the translation profile; andtranslating the received content by the computer system, using the content-specific dictionary and the determined one of the plurality of generic dictionaries to use.2. The method of claim 1 , wherein the content comprises a social network post by the author.3. The method of claim 1 , wherein the content comprises words spoken by the author.4. The method of claim 3 , wherein the words spoken by the author are received via a mobile device.5. The method of claim 1 , wherein the contextual information comprises at least one of: (a) one or more descriptions; (b) one or more tags; (c) one or more comments; (d) one or more subjects; (e) one or ...

REAL-TIME INTERPRETING SYSTEMS AND METHODS

Systems, methods and computer program products for the provision and enabling of multi-language and sign language services in real-time are disclosed. System components include a call processing computer/server that receives requests and is in communication with other system components, a video server/computer for processing and relaying video images, user interface devices for making requests and receiving data transmitted between system components and service provider devices for responding to or satisfying requests received. 1. A computer program product comprising a computer usable medium having control logic stored therein for causing a computer to provide multi-language interpretation and sign language services in real-time , said control logic comprising:computer readable program code means for placing at least one service request by at least one user;computer readable program code means for determining the type of said at least one service request;computer readable program code means for sending a command to at least one server based on the type of said at least one request;computer readable program code means for reviewing a real-time database of at least one sign language operator and at least one language interpreter that are available;computer readable program code means for searching said real-time database of at least one service provider;computer readable program code means for aggregating at least one search result obtained as a result of said search; andcomputer readable program code means for establishing a connection between said at least one search result and said at least one user.2. The computer program product of claim 1 , wherein said at least one service provider is a sign language operator.3. The computer program product of claim 1 , wherein said at least one service provider is a language interpreter.4. The computer program product of further comprising:computer readable program code means for determining said at least one service provider ...

SYSTEM FOR TRANSLATING TARGET WORDS BY GESTURE AND METHOD THEREOF

A system for translating a target word by a gesture and a method thereof are provided. By inputting a gesture for text, selecting a target word from the text based on the gesture, and displaying a translation of the target word, the system and method can achieve an effect of obtaining a translation of words conveniently and fast for user of a touch device having the system and method employed therein. 1. A method of translating a target word by gesturing , comprising steps of:inputting a gesture on the text;selecting a target word by the gesture, the target word belonging the text;translating the target word into a second language as a translation; anddisplaying the translation.2. The method as claimed in claim 1 , wherein the step of inputting the gesture on the text claim 1 , comprises a step of sliding over top and below of the target word.3. The method as claimed in claim 1 , wherein the step of inputting the gesture on the text comprises a step of sliding over right and left of the target word.4. The method as claimed in claim 1 , wherein the step of inputting the gesture on the text comprises a step of selecting the range of the target word including a part of the target word slid over top or below and the other part of the target word slid after sliding over top or below the part claim 1 , wherein the other part of the target word is on the next row of the part of the target word.5. The method as claimed in claim 1 , wherein the step of inputting the gesture on the text comprises a step of selecting the range of the target word including a part of the target word slid over top or below and the other part of the target word slid within a set time after slid over top or below the part claim 1 , wherein the other part includes at least one row of the target word following the part.6. The method as claimed in claim 1 , wherein the step of selecting the target word on the gesture claim 1 , comprises a step of selecting the range of the target word according to a ...

MULTI-TIER CUSTOMIZABLE PORTAL DEPLOYMENT SYSTEM

A computing system comprises, in one example, a display system, a portal hierarchy model have a plurality of nodes arranged in hierarchical parent/child relationships, each node representing a set of one or more portals and having associated portal configuration data, and a portal rendering system configured to detect a user request to render content in a given one of the portals and to obtain a set of portal configuration data for the given portal by identifying a first node in the portal hierarchy model that represents the given portal and traversing the portal hierarchy model from the first node to a second node that is a parent of the first node. The computing system also includes a display system controller configured to control the display system to generate portal user interface displays based on the set of portal configuration data. 1. A computing system comprising:a display system;a portal hierarchy model have a plurality of nodes arranged in hierarchical parent/child relationships, each node representing a set of one or more portals and having associated portal configuration data;a portal rendering system configured to detect a user request to render content in a given one of the portals and to obtain a set of portal configuration data for the given portal by identifying a first node in the portal hierarchy model that represents the given portal and traversing the portal hierarchy model from the first node to a second node that is a parent of the first node; anda display system controller configured to control the display system to generate portal user interface displays based on the set of portal configuration data.2. The computing system of claim 1 , wherein the first node comprises a leaf node in the portal hierarchy model.3. The computing system of claim 2 , wherein the portal hierarchy model comprises a plurality of leaf nodes each representing a different portal.4. The computing system of claim 1 , wherein the second node represents a plurality of ...

DATA PROCESSING SYSTEMS, DEVICES, AND METHODS FOR CONTENT ANALYSIS

Systems, devices and methods operative for identifying a reference within a figure and an identifier in a text associated with the figure, the reference referring to an element depicted in the figure, the reference corresponding to the identifier, the identifier identifying the element in the text, placing the identifier on the figure at a distance from the reference, the identifier visually associated with the reference upon the placing, the placing of the identifier on the figure is irrespective of the distance between the identifier and the reference. 1. A method comprising:serving, via a server, over a network, a content to a browser running on an operating system of a client, wherein the content comprises a figure portion and a text portion, wherein the figure portion comprises a figure comprising an object, a line, and a first alphanumeric string, wherein the line extends between the object and the first alphanumeric string, wherein the text portion comprises a second alphanumeric string, wherein the first alphanumeric string is identical to the second alphanumeric string, wherein the text portion is editable;identifying, via the server, the first alphanumeric string;identifying, via the server, the second alphanumeric string;associating, via the server, the first alphanumeric string with the second alphanumeric string; andtaking, via the server, an action with respect to the second alphanumeric string based at least in part on the associating.2. The method of claim 1 , wherein the first alphanumeric string is hyperlinked to the second alphanumeric string.3. The method of claim 1 , wherein the second alphanumeric string is hyperlinked to the first alphanumeric string.4. The method of claim 1 , wherein the action comprises at least one of:copying, via the server, an alphabetic string positioned adjacent to the second alphanumeric string,performing, via the server, a mode analysis for an alphabetic string positioned adjacent to the second alphanumeric string, ...

SECOND LANGUAGE ACQUISITION SYSTEMS, METHODS, AND DEVICES

Systems, methods, and devices for second language acquisition, using incrementally increasing in-line word and grammar substitution to increase comprehension and retention by presenting new material in an already-understood context. The systems, methods, and devices may be implemented in a range of embodiments, from books to computer systems, and generally use isolated word and phrase substitution with a translated word/phrase in the context of a base language document to convey the meaning of the translated word/phrase to the user by context. 1. A method of partially translating an electronic document comprising:providing a client computer having a display;providing a remote computer server communicatively coupled to said client computer device over a telecommunications network;receiving at said client computer an electronic document comprising written content in a first language;at said client computer, selecting a plurality of words in said written content and, for each such selected word, counting the number of times said word occurs in said written language content;at said client computer, sending to said remote computer a first datagram comprising said selected plurality of words and said count of occurrences of each of said plurality of words; a second plurality of words, said second plurality of words being a subset of said first plurality of words;', 'for each word in said second plurality of words, a corresponding translation of said word into a second language; and, 'receiving from said remote computer a second dam ram comprisingat said client computer, displaying said received electronic document on said display, said displayed electronic document modified such that each occurrence in said displayed electronic document of a word in said second plurality of words is substituted fir said corresponding translation of said word into said second language.2. The method of claim 1 , wherein said client computer is a mobile device.3. The method of claim 2 , ...

LANGUAGE CONTENT TRANSLATION

In an embodiment, a method comprises receiving, at a translation server, a request for translation services from a requesting device for text data associated with a token and a first language; retrieving, at the translation server, a translated version of the text data in a second language from a translation database storing automatically translated text data and manually translated text data, if the token matches a previously processed token; retrieving, at the translation server, the translated version of the text data in the second language from an automated translation service, if the token does not match the previously processed token; retrieving, at the translation server, the translated version of the text data in the second language from the manual translation service; and transmitting, at the translation server, one or more of the automatically translated text data and the manually translated text data to the requesting device.

Language Learning Tool

A technology is described for a language learning tool. An example method may include obtaining a user profile from a data store in response to a request to provide text used to study a target language. Target language words recognized by the user that correspond with a source language words included in the text may then be identified from the user profile. Instances of the source language words may then be replaced in the text with the target language words identified from the user profile and the text may be provided to a client device. A selection of a displayed word may be received from the client device, whereupon a corresponding word in either the source language or the target language may be identified to replace the displayed word in the text displayed on the client device.

Technologies for providing textual information and systems and methods using the same

Technologies for providing textual information are described. In some embodiments the technologies include an audio sensor, a loudspeaker, and a voice to text server. The audio sensor may function to detect an audio input and produce a first signal containing auditory information. The auditory information may be conveyed to the loudspeaker and the voice to text server. The voice to text server may function to convert the auditory information to textual information and transmit the textual information to one or more client devices, e.g., in a text message. Systems, methods, and devices including or utilizing such technology are also described.

METHOD AND DEVICE FOR HELPING TO UNDERSTAND AN AUDITORY SENSORY MESSAGE BY TRANSFORMING IT INTO A VISUAL MESSAGE

A method and a device for helping a hearing-impaired person to understand an auditory sensory message by transforming the auditory message into a visual message and projecting this message on a support in the field of vision of the hearing-impaired person. This device comprises a support () carrying a sensor in the form of microphones () to pick up the message, recording and memorizing module () for recording and memorizing/storing in real time the auditory message, and transforming the message into a visual message. A screen () is placed in the field of vision of the user, and at least one projector () projects the visual message on the screen. A sensor detects pupil movement of the user and mechanism converts pupil movement of the user into a display command for the visual message, and carrying out the command by projecting the visual message. 115-. (canceled)16. A method for helping a hearing-impaired person called a user to understand an auditory sensory message by transforming the auditory sensory message into a visual message and projecting the visual message on a surface positioned in a field of vision of the user , the method comprising:picking up the auditory sensory message by at least one sensor mounted on a support of a spectacle or equivalent component,recording the auditory message in real time to allow re-using the recorded auditory message in deferred time,transforming the auditory sensory message into a visual message,projecting the visual message, following a user command, on a screen integral with the support of the spectacle or equivalent component placed in the field of vision of the user,carrying out the command by at least one pupil movement of the user, andperforming the projection of the visual message in a static or scrolling way, one single time or repeatedly, immediately or with a delay, depending on the user command that is picked up by a member detecting the pupil movement.17. The method for helping the hearing-impaired person according ...

Design time user interface with intelligent text reduction

Disclosed is an improved system for performing intelligent text reduction on text strings for optimal display in a variety of user interface display elements. The system includes a smart text reduction algorithm that can shorten text strings as necessary in response to resizing the user interface or elements therein. The system also includes a design time user interface for application developers (or other users) to design graphical user interfaces in a collaborative workspace. The design time user interface incorporates the smart text reduction algorithm to enable designers to modify user interface display elements and run the text reduction algorithm on any text strings that no longer fit within the modified display elements. The described embodiments can also translate text strings of user interface display elements and can execute the smart text shortening algorithm on the translated text strings accordingly.

EFFICIENT HANDLING OF BI-DIRECTIONAL DATA

A tool for standardized layout transformations of BIDI data exchanged between legacy and modern systems is provided. The tool retrieves client connection information from a client request for data. The tool determines, based, at least in part, on the client connection information, a client application's operating system. The tool determines whether the data requested in the client request is BIDI data. Responsive to a determination that the data requested is BIDI data, the tool initiates a layout transformation of the data requested at a single point within the database server. The tool returns transformed BIDI data to the client application. 1one or more computer processors;one or more computer readable storage devices;program instructions stored on at least one of the one or more computer readable storage devices for execution by at least one of the one or more computer processors, the program instructions comprising:program instructions to retrieve client connection information from a client request for data;program instructions to determine based, at least in part, on the client connection information, an operating system of a client application, wherein the determination indicates whether the operating system is a modern operating system;program instructions to determine whether the data requested in the client request is BIDI data, wherein determining includes identifying the data requested and determining whether the data requested exhibits one or more bi-directional properties that indicate BIDI data;program instructions to determine the data requested is BIDI data where the data requested exhibits layout properties indicative of BIDI data;responsive to a determination that the data requested is BIDI data, program instructions to initiate a layout transformation of the data requested at a single point within a database server, wherein initiating includes determining a plurality of data from a connection string of the client request, where the plurality of ...

TERMINAL EQUIPMENT, TRANSLATION METHOD, AND NON-TRANSITORY COMPUTER READABLE MEDIUM

A terminal equipment comprising: a voice input unit to accept an input of a voice a voice recognition command unit to command a voice recognition unit to convert voices of joined voice data acquired by the voice input unit joining the voice data of the voice to the voice data of the voice accepted previously into character information of a first language at an interval; a character transmission unit to transmit first character information of the first language toward another terminal equipment whenever receiving the first character information of the first language converted; a translation command unit to command a translation unit to translate second character information of a second language into the first language whenever receiving the second character information of the second language and a display unit to display the second character information of the first language together with the second character information of the second language. 1. A terminal equipment comprising:a voice input unit to accept an input of a voice;a voice recognition command unit to command a voice recognition unit to convert voices of joined voice data acquired by the voice input unit joining the voice data of the voice accepted by the voice input unit to the voice data of the voice accepted previously into character information of a first language at an interval of predetermined time;a character transmission unit to transmit first character information of the first language toward another terminal equipment whenever receiving the first character information of the first language converted by the voice recognition unit;a translation command unit to command a translation unit to translate second character information of a second language into the first language whenever receiving the second character information of the second language from another terminal equipment; anda display unit to display the second character information of the first language translated by the translation unit ...

TERMINAL EQUIPMENT, TRANSLATION METHOD, AND NON-TRANSITORY COMPUTER READABLE MEDIUM

A terminal equipment comprising: a voice input unit to accept an input of a voice; a voice recognition command unit to command a voice recognition unit to convert voices of joined voice data acquired by the voice input unit joining the voice data of the voice accepted by the voice input unit to the voice data of the voice accepted previously into character information of a first language at an interval of predetermined time; a translation command unit to command a translation unit to translate first character information of a first language into a second language whenever receiving the first character information of the first language converted by the voice recognition unit; and a display unit to display the first character information of the second language translated by the translation unit together with the first character information of the first language. 1. A terminal equipment comprising:a voice input unit to accept an input of a voice;a voice recognition command unit to command a voice recognition unit to convert voices of joined voice data acquired by the voice input unit joining the voice data of the voice accepted by the voice input unit to the voice data of the voice accepted previously into character information of a first language at an interval of predetermined time;a translation command unit to command a translation unit to translate first character information of a first language into a second language whenever receiving the first character information of the first language converted by the voice recognition unit; anda display unit to display the first character information of the second language translated by the translation unit together with the first character information of the first language.2. A translation method by which a computer executes:accepting an input of a voice;commanding a voice recognition unit to convert voices of joined voice data acquired by the voice input unit joining the voice data of the voice accepted by the voice input ...

TRANSLATION AND DISPLAY OF TEXT IN PICTURE

A method performed by a mobile terminal may include receiving an image that includes text, translating the text into another language and superimposing and displaying the translated text over the received image. 1. A method performed by a mobile terminal comprising:receiving an image that includes text;translating the text into another language; andsuperimposing and displaying the translated text over a portion of the received image.2. The method of claim 1 , further comprising:performing optical character recognition (OCR) processing on the received image.3. The method of claim 2 , further comprisingreceiving input from a user selecting a language for performing the OCR processing.4. The method of claim 1 , further comprising:receiving input from a user selecting the another language.5. The method of claim 1 , wherein the received image includes at least one of a digital image or a video stream.6. The method of claim 1 , wherein the translated text is displayed in a more prominent manner that the text in the received image.7. The method of claim 1 , wherein the translating the text into another language is performed by a server and wherein the displaying the translated text over a portion of the received image is displayed on the mobile terminal.8. A mobile terminal claim 1 , comprising:a camera configured to produce an image;a display; and receive the image from the camera,', 'perform optical character recognition (OCR) on the image to produce text,', 'translate the text into another language, and', 'control the display to display the translated text., 'logic configured to9. The mobile terminal of claim 8 , wherein the logic is further configured to:superimpose and display the translated text over at least a portion of the received image.10. The mobile terminal of claim 8 , wherein the logic is further configured to:receive a selection of a language associated with the OCR processing.11. The mobile terminal of claim 10 , wherein the logic is further configured to: ...

METHOD EXECUTED IN TRANSLATION SYSTEM AND INCLUDING GENERATION OF TRANSLATED TEXT AND GENERATION OF PARALLEL TRANSLATION DATA

A method executed in a translation system includes: (A) receiving source text in a first language; (B) translating the source text into a second language to generate first translated text; (C) acquiring a determination result as to whether or not the first translated text has been correctly translated; (D) in a case where the first translated text has not been correctly translated, generating first parallel translation data that includes the source text and the first translated text; (E) transmitting the first parallel translation data to a terminal device; (F) receiving, from the terminal device, second translated text obtained by the source text being correctly translated into the second language; and (G) registering, into a parallel translation database, second parallel translation data that includes the source text and the second translated text. 1. A method executed in a translation system , the method including:(A) receiving source text in a first language from a user;(B) translating the source text into a second language that is different from the first language to generate first translated text;(C) acquiring a determination result as to whether or not the first translated text has been correctly translated;(D) in a case where the first translated text has not been correctly translated, generating first parallel translation data that includes the source text and the first translated text;(E) transmitting the first parallel translation data to a terminal device;(F) receiving, from the terminal device, second translated text obtained by the source text being correctly translated into the second language; and(G) registering, into a parallel translation database, second parallel translation data that includes the source text and the second translated text.2. The method according to claim 1 , further including:(H) receiving, from the terminal device, a paraphrased text obtained by the source text being paraphrased into a different expression in the first language; ...

ENCODING AND ADAPTIVE, SCALABLE ACCESSING OF DISTRIBUTED MODELS

Systems, methods, and apparatus for accessing distributed models in automated machine processing, including using large language models in machine translation, speech recognition and other applications. 1. (canceled)2. A method comprising:receiving a first segment of text in a source language;obtaining a set of candidate translations of the first segment of text in a target language, each candidate translation in the set of candidate translations comprising one or more tokens in the target language; obtaining, from a translation cache, first language model data about the tokens in the candidate translation, and', 'computing an intermediate translation score using the first language model data;, 'for each candidate translation in the set of candidate translations obtaining, from one or more language model servers, second language model data about the tokens in the candidate translation, and', 'computing a final translation score using the intermediate translation score and the second language model data; and, 'for each of one or more of the candidate translations in the set of candidate translationsselecting the candidate translation with a best final translation score.3. The method of claim 2 , further comprising:prior to obtaining the second language model data from the one or more language model servers, removing one or more candidate translations from the set of candidate translations based on the intermediate translation scores, and only obtaining the second language model data for candidate translations that were not removed from the set.4. The method of claim 2 , wherein the first language model data defines a coarse model of the target language claim 2 , and wherein the second language model data defines a detailed model of the target language.5. The method of claim 2 , wherein the first language model data and the second language model data comprise frequencies of occurrence of sequences of tokens in the target language.6. The method of claim 2 , wherein the ...

PASSENGER HEADS-UP DISPLAYS FOR VEHICLES

Method and apparatus are disclosed for passenger heads-up displays for vehicles. An example vehicle includes a passenger seat, a passenger heads-up display (HUD) to present a virtual interface in front of the passenger seat, and a controller. The controller is to identify a mode selection for the passenger HUD and determine, based on the mode selection, the virtual interface and an apparent distance of the virtual interface for a passenger. The controller also is to present, via the passenger HUD, the virtual interface at the apparent distance for the passenger. 1. A vehicle comprising:a passenger seat;a passenger heads-up display (HUD) to present a virtual interface in front of the passenger seat; and identify a mode selection for the passenger HUD;', 'determine, based on the mode selection, the virtual interface and an apparent distance of the virtual interface for a passenger; and', 'present, via the passenger HUD, the virtual interface at the apparent distance for the passenger., 'a controller to2. The vehicle of claim 1 , wherein the apparent distance is a distance at which the virtual interface appears from a perspective of the passenger.3. The vehicle of claim 1 , further including a windshield claim 1 , wherein the passenger HUD includes a projector that is configured to emit a projection onto the windshield to create the virtual interface claim 1 , wherein the controller utilizes forced perspective to cause the virtual interface to appear farther than the windshield for the passenger.4. The vehicle of claim 1 , wherein the virtual interface presented by the passenger HUD is not viewable from a driver's seat.5. The vehicle of claim 1 , further including a driver's seat for an operator and a driver HUD to present a virtual operator interface in front of the driver's seat to the operator.6. The vehicle of claim 1 , further including a camera configured to capture images of the passenger to enable the controller to detect a gesture of the passenger.7. The ...

CONTEXTUALLY-AWARE RECOMMENDATION AND TRANSLATION ENGINE

The present disclosure involves systems, software, and computer implemented methods for presenting recommendations for suggested activities. One example method includes receiving a first signal from a device that includes a current context of the device that includes location information for the device. The device is associated with a particular profile. A preferred language associated with the device is determined from the profile. The profile is analyzed to determine a contextual activity preference associated with the device. A repository of establishment information is searched to identify an activity that matches the current context associated with the device and the contextual activity preference. An activity description of the identified activity is translated from a foreign language to the preferred language to create a translated activity description. A second signal is transmitted to the device that includes the translated activity description for presentation at the device. 1. A system comprising:a communications module;at least one memory storing instructions, a plurality of profiles, and a repository of establishment information including descriptions of activities that are available to be performed at a plurality of geographic locations; and receive a first signal via the communications module from a device, the first signal including a current context associated with the device including at least location information for a geographic location of the device, the device associated with a particular profile in the plurality of profiles;', 'determine, from the particular profile, a preferred language associated with the device;', 'analyze the particular profile to determine at least one contextual activity preference that matches the current context associated with the device;', 'in response to receiving the first signal, search the repository of establishment information based on the location information, the current context associated with the device, ...

WORD HASH LANGUAGE MODEL

A language model may be used in a variety of natural language processing tasks, such as speech recognition, machine translation, sentence completion, part-of-speech tagging, parsing, handwriting recognition, or information retrieval. A natural language processing task may use a vocabulary of words, and a word hash vector may be created for each word in the vocabulary. A sequence of input words may be received, and a hash vector may be obtained for each word in the sequence. A language model may process the hash vectors for the sequence of input words to generate an output hash vector that describes words that are likely to follow the sequence of input words. One or words may then be selected using the output word hash vector and used for a natural language processing task. 1. A computer-implemented method for implementing a neural network language model , the method comprising:obtaining a word hash vector for each word of a vocabulary of words;receiving a first sequence of words for processing by the neural network language model to select a word to follow the first sequence of words;generating a first sequence of word hash vectors by retrieving a word hash vector for each word of the first sequence of words;processing the first sequence of word hash vectors with a layer of the neural network language model to compute a first output vector;quantizing the first output vector to obtain a first output word hash vector;determining a distance between the first output word hash vector and a first hash vector for a first word in the vocabulary; andselecting the first word from the vocabulary using the distance between the first output word hash vector and the first hash vector for the first word.2. The computer-implemented method of claim 1 , further comprising using the selected first word to perform at least one of: speech recognition claim 1 , machine translation claim 1 , sentence completion claim 1 , part-of-speech tagging claim 1 , parsing claim 1 , handwriting ...

INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND PROGRAM

There is provided an information processing apparatus including: a processing unit configured to perform a summarization process of summarizing content of speech indicated by voice information based on speech of a user on a basis of acquired information indicating a weight related to a summary. 1. An information processing apparatus comprising:a processing unit configured to perform a summarization process of summarizing content of speech indicated by voice information based on speech of a user on a basis of acquired information indicating a weight related to a summary.2. The information processing apparatus according to claim 1 , wherein the processing unit performs the summarization process in a case in which a predetermined start condition is determined to be satisfied.3. The information processing apparatus according to claim 2 , wherein the start condition is a condition related to a non-speaking period in which a state in which speech is not performed continues claim 2 , andin a case in which the non-speaking period exceeds a predetermined period or in a case in which the non-speaking period is equal to or larger than the predetermined period, the processing unit determines that the start condition is satisfied.4. The information processing apparatus according to claim 2 , wherein the start condition is a condition related to a state of voice recognition for acquiring the content of the speech from the voice information claim 2 , andthe processing unit determines that the start condition is satisfied on a basis of detection of a stop request for the voice recognition.5. The information processing apparatus according to claim 2 , wherein the start condition is a condition related to a state of voice recognition for acquiring the content of the speech from the voice information claim 2 , andthe processing unit determines that the start condition is satisfied on a basis of detection of completion of the voice recognition.6. The information processing apparatus ...

AUTOMATIC POST-EDITING MODEL FOR NEURAL MACHINE TRANSLATION

Techniques are disclosed for training and/or utilizing an automatic post-editing model in correcting translation error(s) introduced by a neural machine translation model. The automatic post-editing model can be trained using automatically generated training instances. A training instance is automatically generated by processing text in a first language using a neural machine translation model to generate text in a second language. The text in the second language is processed using a neural machine translation model to generate training text in the first language. A training instance can include the text in the first language as well as the training text in the first language. 1. A method implemented by one or more processors , the method comprising:receiving an automatically generated training instance including training text in a target language and ground truth text in the target language;processing the training text using an automatic post-editing model to generate predicted output, wherein the automatic post-editing model, when trained, is used in correcting one or more translation errors introduced by a neural machine translation model translating text from a source language into the target language;determining a difference between the predicted output and the ground truth training text; andupdating one or more weights in the automatic post-editing model based on the determined difference.2. The method of claim 1 , further comprising automatically generating the training instance claim 1 , wherein automatically generating the training instance comprises:processing the ground truth text in the target language using the neural machine translation model to generate text in the source language; andprocessing the generated text in the source language using the neural machine translation model to generate the training text in the target language.3. The method of claim 2 , wherein the one or more translation errors introduced by the neural machine translation model ...

SEQUENCE GENERATION USING NEURAL NETWORKS WITH CONTINUOUS OUTPUTS

A machine learning system including a continuous embedding output layer is provided. Whereas traditional machine language translation or generation models utilize an output layer that include an single output for each word in the output vocabulary V, the present machine learning system includes a continuous embedding output layer that stores continuous vectors mapped to an m-dimensional vector space, where m is less than V. Accordingly, the present machine learning system processes an input string to produce an output vector and then searches for the continuous vector within the vector space that most closely corresponding to the output vector via, for example, a k-nearest neighbor algorithm. The system then outputs the output string corresponding to the determined continuous vector. The present system can be trained utilizing a cosine-based loss function. 1. A computer system for mapping an input string to an output string from a set of N strings , the computer system comprising:a processor; and [ an encoder;', 'a decoder;', 'a continuous embedding output layer configured to map an output of the decoder to an m-dimensional vector space; and', 'an output embedding table storing a plurality of continuous vectors mapped to the m-dimensional vector space;', 'wherein m Подробнее

INTUITIVE TACTILE DEVICES, SYSTEMS AND METHODS

The present invention provides methods, systems and a device for provision of a tactile language comprising a set of distinguishable tactile instructions to a user, the method including providing the language comprising the plurality of combinations of tactile stimuli, wherein the device is configured to provide unmistakable, distinguished commands, without the need for verbal or visual instructions and wirelessly communicating instructions to the device to activate at least four tactile stimulus components of the device thereby providing the set of distinguishable tactile instructions to the user, wherein the instructions are selected from real instructions and virtual reality instructions and combinations thereof. 1. A method for provision of a tactile language comprising a set of distinguishable tactile instructions to a user , the method comprising:a. providing the language comprising said plurality of combinations of tactile stimuli, wherein each stimulus is provided to a different specific area of skin of the user, and wherein each said tactile stimuli combination provides only one instruction to the user a plurality of tactile stimuli to the user from a device, wherein said device is configured to provide unmistakable, distinguished commands, without the need for verbal or visual instructions; andb. wirelessly communicating instructions to said device to activate at least four tactile stimulus components of said device thereby providing said set of distinguishable tactile instructions to said user, wherein said instructions are selected from real instructions and virtual reality instructions and combinations thereof.2. A method according to claim 1 , wherein said tactile instructions are selected from movement instructions and navigational instructions.3. A method according to claim 2 , wherein said set of distinguishable tactile instructions are directional instructions selected from claim 2 , move forwards claim 2 , move backwards claim 2 , move right claim ...

MULTIPLE DEVICE INTELLIGENT LANGUAGE MODEL SYNCHRONIZATION

Systems and methods for intelligent language models that can be used across multiple devices are provided. Some embodiments provide for a client-server system for integrating change events from each device running a local language processing system into a master language model. The change events can be integrated, not only into the master model, but also into each of the other local language models. As a result, some embodiments enable restoration to new devices as well as synchronization of usage across multiple devices. In addition, real-time messaging can be used on selected messages to ensure that high priority change events are updated quickly across all active devices. Using a subscription model driven by a server infrastructure, utilization logic on the client side can also drive selective language model updates. 1. A method for operating a master language processing system , the method comprising:receiving, at the master language processing system, update messages from multiple local language processing systems, wherein the update messages include change events to local language models detected by the multiple local language processing systems;updating a master language model in the master language processing system based on the change events included in the update messages received from the multiple local language processing systems;generating synchronization messages for each of the multiple local language processing systems to integrate change events from other local language processing systems; andtransmitting the synchronization messages to each of the multiple local language processing systems such that updates to the master language model are propagated to the local language models.2. The method of claim 1 , wherein each update message further includes a priority level reflecting the priority of change events in the update message.3. The method of claim 2 , wherein the update messages received at the master language processing system include groups of ...