ОПТИМИЗАЦИЯ ИЗВЛЕЧЕНИЯ ФАКТА С ИСПОЛЬЗОВАНИЕМ МНОГОЭТАПНОГО ПОДХОДА

Изобретение относится к способу и устройству для проведения информационного поиска. Техническим результатом является повышение достоверности результатов поиска. Из электронных документов извлекаются факты посредством распознавания фактографических описаний с использованием таблицы слов факта, сопоставляемых со словами электронных документов. Слова этих фактографических описаний могут быть обеспечены признаком соответствующей части речи. Далее выполняется более подробный анализ этих фактографических описаний, а не всего электронного документа, и, в частности, текста, окружающего соответствующие слова факта. Анализ может включать в себя идентификацию лингвистических элементов каждого словосочетания и определение их роли как подлежащего или как дополнения. Могут применяться правила исключения для удаления тех словосочетаний, которые, скорее всего, не являются частью фактов, причем эти правила исключения частично основаны на лингвистических элементах. К оставшимся словосочетаниям могут быть ...

СПОСОБ И СИСТЕМА СОЗДАНИЯ КРАТКОГО ИЗЛОЖЕНИЯ ЦИФРОВОГО КОНТЕНТА

Изобретение относится к обработке цифрового контента (в частности, текстовых, аудио- и видеофайлов), а конкретнее к созданию кратких изложений цифрового контента. Техническим результатом является расширение арсенала средств создания кратких изложений цифрового контента. В способе создания краткого изложения цифрового контента получают указание на цифровой контент и выполняют синтаксический анализ текстового представления контента. Разделяют контент на упорядоченное множество фрагментов, включающее в себя первый и второй фрагменты. Выполняют семантический анализ каждого фрагмента и определяют параметр полезности для каждого фрагмента и связи между каждой парой фрагментов. В ответ на то, что параметр полезности второго фрагмента превышает предварительно определенное пороговое значение, включают второй фрагмент в подмножество фрагментов для включения в краткое изложение цифрового контента. В ответ на получение указания на связь второго фрагмента с первым включают первый фрагмент в подмножество ...

ИСПОЛЬЗОВАНИЕ ОТОБРАЖЕНИЯ ДАННЫХ ДЛЯ ПЕРЕДАЧИ СОДЕРЖИМОГО ДОКУМЕНТОВ И УСТАНОВОК РАССЫЛКИ

... 1. Способ генерирования отчета и рассылки отчета множеству получателей, включающий в себя этапы, на которых принимают данные, содержащие множество компонентов данных, извлекают динамический список получателей и соответствующий канал рассылки для каждого получателя, определяют, какие компоненты данных посылать и какому из получателей по списку, генерируют отчет, содержащий определенные компоненты данных, рассылают отчет каждому из определенных получателей через соответствующий канал рассылки. 2. Способ по п.1, дополнительно включающий в себя этап, на котором определяют время или инициирующую совокупность условий для посылки отчета каждому из получателей, причем рассылка отчета представляет собой рассылку отчета в упомянутое время или в ответ на упомянутую совокупность условий. 3. Способ по п.1, в котором определение того, какие компоненты данных посылать получателям, включает в себя этап, на котором принимают соответствие между компонентами данных и получателями. 4. Способ по п.1, в котором ...

СПОСОБ И СИСТЕМА ДЛЯ КЛАССИФИКАЦИИ ДИСПЛЕЙНЫХ СТРАНИЦ С ПОМОЩЬЮ РЕФЕРАТОВ

... 1. Способ в компьютерной системе для классификации web-страниц, содержащий извлечение web-страницы; автоматическую выработку реферата извлеченной web-страницы; и определение классификации для извлеченной web-страницы на основании автоматически выработанного реферата. 2. Способ по п.1, в котором автоматическая выработка реферата включает в себя вычисление коэффициента для каждого предложения web-страницы с помощью множества методов реферирования. 3. Способ по п.2, в котором коэффициент для каждого предложения является линейной комбинацией коэффициентов множества методов реферирования. 4. Способ по п.1, в котором предложения с наивысшими коэффициентами выбираются для формирования реферата. 5. Способ по п.2, в котором методы реферирования включают в себя метод реферирования Люна, метод реферирования на основе латентно-семантического анализа, метод реферирования основной части содержания и метод управляемого реферирования. 6. Способ по п.2, в котором методы реферирования включают в себя любые ...

РЕЗЮМИРОВАНИЕ ПОТОКОВ СООБЩЕНИЙ

... 1. Способ автоматического резюмирования электронного потока сообщений, содержащий этапы, на которых:принимают поток сообщений, состоящий из одного или нескольких электронных сообщений;обрабатывают одно или несколько сообщений, составляющих принятый поток сообщений так, чтобы текстовые компоненты, составляющие эти одно или несколько сообщений, могли быть использованы для генерирования резюме потока сообщений; игенерируют резюме потока сообщений из извлеченных одного или нескольких текстовых компонентов.2. Способ по п. 1, дополнительно содержащий этап, на котором отображают сгенерированное резюме потока сообщений в компоненте пользовательского интерфейса для просмотра пользователем потока сообщений.3. Способ по п. 1, в котором перед генерированием резюме потока сообщений представляют предварительное резюме потока сообщений пользователю извлеченного потока сообщений, чтобы пользователь одобрил предварительное резюме потока как верное резюме потока сообщений.4. Способ по п. 3, в котором, если ...

СПОСОБ ИЗВЛЕЧЕНИЯ ПОЛЕЗНОГО КОНТЕНТА ИЗ УСТАНОВОЧНЫХ ФАЙЛОВ МОБИЛЬНЫХ ПРИЛОЖЕНИЙ ДЛЯ ДАЛЬНЕЙШЕЙ МАШИННОЙ ОБРАБОТКИ ДАННЫХ, В ЧАСТНОСТИ ПОИСКА

... 1. Способ извлечения полезного контента из установочных файлов мобильных приложений для дальнейшей машинной обработки данных, в частности поиска, содержащий этапы на которых:- загружают из Интернета на сервер установочный файл приложения неизвестного формата;- подбирают к нему разархиватор;- разархивируют загруженный установочный файл в каталог с файлами;- анализируют полученный каталог, составляют список файлов, содержащихся в нем;- выбирают из списка файл для дальнейшего анализа;- подбирают программное обеспечение для чтения файла;- анализируют выбранный файл на предмет поиска первичного контента;- формируют список адресов внутреннего размещения первичного контента в виде набора строк;- переходят к анализу следующего файла, до тех пор, пока в каталоге есть файлы;- проводят анализ текстового содержимого списка адресов внутреннего размещения первичного контента, и разделяют текст каждой строки на набор символов, идентифицирующих способ хранения соответствующей единицы контента, набор символов ...

СИСТЕМЫ И СПОСОБЫ ДЛЯ АНАЛИЗА И ИЗУЧЕНИЯ ОБЪЕКТОВ В СОЦИАЛЬНЫХ СЕТЯХ

Verfahren, um natursprachliche Abfragen von Textdatenbanken zu lösen

Hervorheben von Schlüsselabschnitten eines Texts innerhalb eines Dokuments

Generating a targeted summary of textual content tuned to a target audience vocabulary

A method for generating a targeted summary 116 of textual content 112 tuned to a target audience vocabulary 114 wherein a request to summarise textual content tuned to a target audience is received, an attention distribution 304 comprising words 306 from the textual content and audience vocabulary, and selection probability values 308 for each word is generated by a word generation model 120. The next word 312 in the targeted summary is selected based on the attention distribution and a linguistic preference model 122 indicating word preference probabilities 202 for the audience vocabulary and feedback 320 of the selected next word is provided to the word generation model causing it to modify the attention distribution for selection of subsequent words of the summary based on the feedback of the next generated word. Also disclosed is a method of training a linguistic preference model using target audience training data wherein the training data comprises a corpus of textual content and ...

System, method and interface for providing a search result using segment constraints

A method for providing a search result includes receiving a user query and determining, in response to receiving the user query, a set of segment candidates based on the user query and an indexing structure. The indexing structure is associated with at least one segment constraint. The method further includes ranking the set of segment candidates and providing a result associated with the set of segment candidates. Another method includes ranking each segment within the set of segment candidates based on a set of prioritized features. Another method has the at least one segment constraint including at least one of a critical keyword and an exclusionary keyword. Another method further includes excluding a segment based on the at least one segment constraint comprising the exclusionary keyword.

Generating a topic-based summary of textual content

A method for generating a summary of textual content tuned to a specific topic involves using a topic-aware encoding model to encode 804 the text using a topic label (e.g. a one-hot vector) to generate topic-aware encoded text. A word generation model selects a next word 808 for the summary from the encoded text. The word generation model is trained using machine learning and training data including documents with corresponding summaries, each having an associated topic. The selected next word is provided as feedback 810 to the word generation model. Also disclosed is a method for training the encoding word generation models by obtaining an intermediate dataset comprising documents, and a summary of each document with an associated topic. Training data is generated by merging the text of first and second documents to make a new document which is associated with the summary and topic of the first document, merging their text again and associating the resulting new document with the summary ...

Highlighting key portions of text within a document

CALL SYSTEM WITH AUTOMATIC SUMMARY OF TEXTS

Search and index hosting system

Selectively generating word vector and paragraph vector representations of fields for machine learning

Word vectors are multi-dimensional vectors that represent words in a corpus of text and that are embedded in a semantically-encoded vector space; paragraph vectors extend word vectors to represent, in the same semantically-encoded space, the overall semantic content and context of a phrase, sentence, paragraph, or other multi-word sample of text. Word and paragraph vectors can be used for sentiment analysis, comparison of the topic or content of samples of text, or other natural language processing tasks. However, the generation of word and paragraph vectors can be computationally expensive. Accordingly, word and paragraph vectors can be determined only for user-specified subsets of fields of incident reports in a database.

A SYSTEM FOR DEEP ABSTRACTIVE SUMMARIZATION OF LONG AND STRUCTURED DOCUMENTS

Techniques are disclosed for abstractive summarization process for summarizing documents, including long documents. A document is encoded using an encoder-decoder architecture with attentive decoding. In particular, an encoder for modeling documents generates both word-level and section-level representations of a document. A discourse-aware decoder then captures the information flow from all discourse sections of a document. In order to extend the robustness of the generated summarization, a neural attention mechanism considers both word-level as well as section-level representations of a document. The neural attention mechanism may utilize a set of weights that are applied to the word-level representations and section-level representations. x -~ E ) 0z 0o '0 0 UJ-A Z u0 a a) 0 UCD a) -< -oa 0 C0 o2 > a5a)a i6 T, ,m 0i c-) 00'a - t5~o a)- 0)' t5U 0) (3 a 0) 0 o0)U)0 a -5 Ma)0 U,06t CL )a)0E ...

METHOD TO GENERATE SUMMARIES TUNED TO A TARGET VOCABULARY

A targeted summary of textual content tuned to a target audience vocabulary is generated in a digital medium environment. A word generation model obtains textual content, and generates a targeted summary of the textual content. During the generation of the targeted summary, the words of the targeted summary generated by the word generation model are tuned to the target audience vocabulary using a linguistic preference model. The linguistic preference model is trained, using machine learning on target audience training data corresponding to a corpus of text of the target audience vocabulary, to learn word preferences of the target audience vocabulary between similar words (e.g., synonyms). After each word is generated using the word generation model and the linguistic preference model, feedback regarding the generated word is provided back to the word generation model. The feedback is utilized by the word generation model to generate subsequent words of the summary. Service Provider System ...

Phrase-based generation of document description

Systems and methods for generating issue networks

Systems and methods for generating issue networks are disclosed. In one embodiment, a computer-implemented method of generating an issue network from a document corpus includes searching, using a computer, the document corpus for a set of documents discussing a starting issue, wherein the starting issue is one of a plurality of normalized issues defined by the document corpus. The method further includes determining a set of normalized issues discussed by the set of documents discussing the starting issue, wherein the set of normalized issues also includes the starting issue, and determining instances of co-occurrences of individual normalized issues of the set of normalized issues within individual cases of the set of documents. The method also includes linking individual normalized issues of the set of normalized issues based on their co-occurrences within the set of documents, wherein the linked individual normalized issues at least in part define the issue network.

SYSTEM AND METHOD FOR MULTIMEDIA DOCUMENT SUMMARIZATION

Multimedia document summarization techniques are described. That is, given a document that includes text and a set of images, various implementations generate a summary by extracting relevant text segments in the document and relevant segments of images with constraints on the amount of text and number/size of images in the summary. Wolfe-SBMC Docket No.: P56 57-US Inventors: Modani et al. Title: Multimedia Document Summarization Multimedia Document Summarization Module 110 Objective Function Module ____ ___ ___ ____ ___ ___202 User Interface Coverage Module component Diversity component Cohesion component ...

Accumulated retrieval processing method, device, terminal, and storage medium

The present disclosure provides an accumulated retrieval processing method. The method includes steps as follows: obtaining a retrieval instruction, the retrieval instruction comprising a retrieval keyword; performing retrieving according to the retrieval instruction, and displaying a corresponding retrieval result, the retrieval result including retrieval data matching with the retrieval keyword; obtaining a selected instruction for the retrieval data; adding the retrieval data selected according to the selected instruction to a preset selected display area, the preset selected display area is configured to independently display the selected retrieval data. According to the aforementioned method, the display area is used to independently display the selected retrieval data. Therefore the retrieval data selected by multiple retrieval can be displayed in the display area, thereby facilitating to summarize and process the retrieval data of the multiple retrieval. In addition, an accumulated ...

Method, apparatus, and electronic device for executing transactions based on blockchain

A node device of a blockchain receives a target transaction including transaction content, where at least a part of the transaction content comprises a content summary of target content stored in a third-party storage system connected to the blockchain. The target content corresponding to the content summary is queried from the third-party storage system. The target content is verified based on the content summary of the target content in the target transaction. If the verification of the target content succeeds, the target transaction is executed based on the transaction content in the target transaction. After the target transaction is executed, the target transaction is stored in a distributed database of the blockchain.

Data summariser

Browse by prompted keyword phrases with an improved user interface

SYSTEM AND METHOD FOR VARYING VERBOSITY OF RESPONSE BASED ON CHANNEL PROPERTIES IN A GROUP COMMUNICATION USING ARTIFICIAL INTELLIGENCE

Efficient use of channel bandwidth response, response timing, along with the ability to acquire the most accurate and up to date response are provided for management of virtual assistant search queries within a communication system (100). Improved management is obtained using an artificial intelligence (AI) server (104) controlling response activity to a query communication device (102) by incorporating one or more of: adjusting verbosity of responses (158), redirecting queries from the AI server to alternate resources (412), and/ or prioritizing of a response (506) based on wait time.

SEGMENTATION DISCOVERY, EVALUATION AND IMPLEMENTATION PLATFORM

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, are described that enable clustering and evaluation of data. A data set is identified for which to evaluate cluster solutions, the data set including a plurality of records each including a plurality of attributes. Different attributes are identified, including target driver attributes, cluster candidate attributes, and profile attributes. One or more clustering algorithms are identified and applied to the data set to generate cluster solutions. Each cluster solution groups records in the data set into different clusters based on the cluster candidate attributes. A score is calculated for each cluster solution based at least on the target driver attributes, the cluster candidate attributes, and the profile attributes. A user interface is generated for presentation to a user showing the generated cluster solution organized according to the calculated score for each cluster solution.

NETWORK SERVER ARRANGEMENT FOR PROCESSING NON-PARAMETRIC, MULTI-DIMENSIONAL, SPATIAL AND TEMPORAL HUMAN BEHAVIOR OR TECHNICAL OBSERVATIONS MEASURED PERVASIVELY, AND RELATED METHODFOR THE SAME

This invention generally discusses wireless devices, servers and communications networks. In particular the invention pertains to performing observations in one or more mobile terminals and processing and distributing the related data in a server side system through layered data processing activities, and conversion of non- parametric data into parameterized form through the utilization of statistical filtering and semantic data structures. It is further explained how such multi-layer, parametrized data can be utilized for predictive purposes, and how feedback loops can be built with the physical world to improve future predictions. The invention is applicable in various applications, for example in systems where precise digital profiles of users need to be built on a continuous basis, and such profiles need to be dynamically linked to one or several actions triggered by emerging characteristics in the data. The multi-layer approaches makes it possible to structure output statistics into ...

DATA SUMMARISER

According to a first aspect of the present invention there is provided a system for summarising data sets comprising: a first data store for target data items; means for dividing said data set into sections and for comparing each said section against said target data items; means for calculating a ranking value for each said section dependent on the outcome of a said comparisons; and means for compiling a summary of the data set from sections having a ranking value past a pre- determined threshold value. According to a further aspect of the present invention a method of summarising a data set input to processing apparatus having a data store for target information is provided; the method comprising the steps of 1) dividing said data set into sections; 2) comparing said sections against said target information; 3) calculating a ranking value for each said section dependent on the outcome o f said comparison; 4) compiling a summary of the data see from sections having a ranking value past ...

Document processing system and method

METHODS AND SYSTEMS TO GENERATE INFORMATION ABOUT NEWS SOURCE ITEMS DESCRIBING NEWS EVENTS OR TOPICS OF INTEREST

This disclosure relates to methods and systems to generate information about news source items from a corpus of news sources, where identified news source items describe or are associated with a news event or topic of interest. The generated information can be presented as collections of news source items describing a news event or topic in, e.g., a newsfeed format, a report, a dashboard configuration, or for use in machine learning processes. News sources can be associated with a rating. The news source items, news sources, and collections can be analyzed to generate information including differences in coverage of generated or selected news events or topics according to various considerations, such as news source characteristics (e.g., bias/skew/viewpoint rating, age, location of news source or event, etc.), time, and presence, absence, or frequency of news sources ratings in a collection of news source items describing the news event or topic. 1. A method of generating information about a news event or topic of interest comprising: i. each of the plurality of individual news sources is configured to provide news source items describing news events or topics; and', 'ii. at least some of the plurality of individual news sources are each, independently, assigned a rating;, 'a. providing, by a computer, a corpus of news sources comprising a plurality of individual news sources whereinb. recognizing, by the computer, a news event or topic in the corpus of news sources that has not previously been recognized in a news source in the corpus of news sources, thereby generating an orphan news source item;c. determining, by the computer, if the orphan news source item is derived from an individual news source that has an assigned rating and, in response to having the assigned rating, creating, by the computer, a first news event or first topic of interest;d. determining, by the computer, a first time for the first news event or first topic of interest, wherein the first ...

Information collection system for a communication network with language translation capabilities

An information collection system comprises a user interface unit for executing input/output information with respect to a user, an external interface unit for exchanging various types of information with an external unit, a user model determination unit for preparing at least one of user information for discriminating information required by the user, user information for defining an information proposition method, and user information for defining an information modification method in accordance with information input from the user interface unit, an information drawing-out unit for drawing out and modifying information input from the external interface unit in accordance with the user information acquired from the user model determination unit, an information proposition processing unit for converting information acquired by the information drawing-out unit into a proposition form for the user in accordance with the information acquired from the user model determination unit, and a control ...

System and method for displaying and manipulating user-relevant data

A dynamic summary view is generated by defining an HTML page that links data binding HTML tables and other HTML controls to predetermined data within a storage of data. For each type of data, a parameter is determined which characterizes the predetermined data from the other data within the storage. A control module related to a specific type of data, searches the storage, determines the predetermined data using the parameter and displays the predetermined data via a data binding HTML table within a section of the dynamic summary view. Upon detecting a manipulation request, such as when a user clicks a button of the mouse, the appropriate control module accesses a subset of the program module that created the predetermined data. This is advantageously done without invoking the entire program module. A subset of the program module can be accessed by executing a script to call defined methods of objects within the program module. A subset of the program module also can be accessed by calling ...

Generating electronic summaries of online meetings

An improved technique of organizing content of online meetings involves generating an electronic summary based on a textual metadata derived from content presented in an online meeting. An online meeting server collects content such as audio, video, and slide files presented in a particular online meeting. From metadata associated with such content, the online meeting server generates an electronic summary of the particular online meeting which includes a textual description of the content. The online meeting server then stores the electronic summary and the content presented in the particular online meeting in a repository that is configured to store content from other online meetings.

DOCUMENT CLASSIFICATION BASED ON MULTIPLE META-ALGORITHMIC PATTERNS

One example is a system including a plurality of summarization engines, a plurality of meta-algorithmic patterns, an extractor, and an evaluator. Each of the plurality of summarization engines receives a text document to provide a meta-summary of the text document. The extractor extracts at least one summarization term from the meta-summary. The extractor generates at least one class term for each given class of a plurality of classes of documents, the at least one class term extracted from documents in the given class. The evaluator determines similarity measures of the text document over each given class of documents of the plurality of classes, each similarity measure indicative of a similarity between the at least one summarization term and the at least one class term for each given class. The selector selects a class of the plurality of classes, the selecting based on he determined similarity measures.

Context service system

The present system aggregates information from a plurality of different context sources. The present system also makes that aggregated information available to requesting components by abstracting it into a generalized form. Thus, the developer of a context-aware application need only know how to interact with the context service of the present invention, rather than knowing how to interact with each and every one of the context sources.

Converting Text Content to a Set of Graphical Icons

A method, system and program product for analyzing textual information and providing a visual representative of a summary of such textual information in the form of a ranked list of icons. A text to icon engine is used that takes as input a textual document. A plurality of icons are each associated to a specific rule such that when the text to icon engine processes textual input, it will apply the rules associated with the icons and return a value that represents how much the text belongs to a specific icon.

DATA INTEGRITY PROTECTION METHOD AND DEVICE

Provided are a data integrity protection method and device for protecting key data in control components of an industrial control system. The method includes establishing a correlation among a plurality of control components in the industrial control system; and determining a summary indicating the integrity of data to be protected in a first control component based on identity features and data features of other control components correlated to the first control component among the plurality of control components. The data features are used for identifying the data to be protected in the control components, and the first control component is any one of the plurality of control components. Since the security of the data in any control component is established over other correlated control components, the key data in the control components can be effectively protected.

METHODS AND SYSTEMS FOR IDENTIFYING CONTENT ELEMENTS

A method of identifying content of interest in a structured electronic document by an electronic device having a processor, an input device, and a display device, includes rendering a structured electronic document to the display device; receiving through the input device at least two separate indications of content elements within the rendered structured electronic document; and identifying with the processor a common characteristic of the indicated content elements, and identifying any further content element within the rendered structured electronic document sharing the common characteristic with the indicated content elements.

APPARATUS AND METHOD FOR AUTOMATED AND ASSISTED PATENT CLAIM MAPPING AND EXPENSE PLANNING

An apparatus and computer implemented method that include obtaining, into a computer, text of a patent, automatically finding and extracting, using the computer, a set of claim text from the patent text, identifying, using the computer, text of independent claims from the set of claim text, displaying in a first row on a computer monitor the text of the independent claims, automatically determining a plurality of preliminary scope-concept phrases from the text of the independent claims, displaying in a second row on the computer monitor the text of the plurality of preliminary scope-concept phrases, eliciting and receiving user input to specify a first one of the plurality of preliminary scope-concepts phrases, and highlighting each occurrence of the specified first one of the plurality of preliminary scope-concept phrases in a plurality of the independent claims displayed in the first row. A scope concept builder tool is also provided.

Meeting summary service

Technologies are disclosed for to utilizing a meeting summary service to generate meeting notes. The meeting notes generated by the meeting summary service can include a variety of information such as participant information, meeting information (e.g., time, place, location, . . . ) meeting agenda information, identified action items, a transcript of the meeting, a recording of the meeting, meeting content presented and/or distributed during the meeting, and the like. The meeting summary service generates meeting notes utilizing a transcript created from a recording of the meeting. In some configurations, machine learning mechanisms may be utilized to identify action items and generating summary information for the meeting. Action items may be assigned to users and tracked to determine state of the action items (e.g., completed). The meeting summary service may also provide a user interface that allows a user, such as a meeting participant, to review the meeting notes.

GENERATING A SUMMARY BASED ON READABILITY

In some examples, a set of sentences is extracted from a digital document, and each sentence is scored using a respective informativeness measure and readability measure. Sentences in the set of sentences are selected based on the readability measures and informativeness measures. A low readability, high informativeness sentence is identified from the set of sentences. A concatenated sentence is generated by concatenating at least one contextual sentence with the low readability, high informativeness sentence, where the concatenated sentence has a higher readability than the low readability, high informativeness sentence.

Method and system for improving performance of text summarization

The invention relates to a method and a system for improving performance of text summarization and has an object of improving performance of a technique for generating a summary from a given paragraph. According to the invention to achieve the object, a method for improving performance of text summarization includes: an a step of generating an embedding vector by vectorizing a natural language-based context; a b step of generating a graph by using the embedding vector; a c step of assigning a weight depending on whether or not a keyword corresponding to at least one node included in the graph is present in the context; and a d step of selecting a path having a highest likelihood in the graph and generating a summary based on the path.

Vector representation based on context

Embodiments relate to a system, program product, and method for use with an intelligent computer platform to create and apply textual data in vector format, and more specifically to apply context to the vector representation. Both context and document vectors are generated and assessed, with a calculated distance between the vectors corresponding to a weight. Word vectors are generated with associated word pairs and frequencies. A word vector generation model is trained. Utilization of the trained model generates one or more context sensitive word vector representations. A summarized sentence document is created and returned through application of the context sensitive word vectors.

METHOD AND SYSTEM FOR IMPROVING PERFORMANCE OF TEXT SUMMARIZATION

The invention relates to a method and a system for improving performance of text summarization and has an object of improving performance of a technique for generating a summary from a given paragraph. According to the invention to achieve the object, a method for improving performance of text summarization includes: an a step of generating an embedding vector by vectorizing a natural language-based context; a b step of generating a graph by using the embedding vector; a c step of assigning a weight depending on whether or not a keyword corresponding to at least one node included in the graph is present in the context; and a d step of selecting a path having a highest likelihood in the graph and generating a summary based on the path. 1. A method for improving performance of text summarization which is fulfilled by a summary generating device , the method comprising:an a step of generating an embedding vector by vectorizing a natural language-based context;a b step of generating a graph by using the embedding vector;a c step of assigning a weight depending on whether or not a keyword corresponding to at least one node included in the graph is present in the context; anda d step of selecting a path having a highest likelihood in the graph and generating a summary based on the path.2. The method for improving performance of text summarization according to claim 1 ,wherein the graph is generated based on a beam search algorithm.3. The method for improving performance of text summarization according to claim 1 ,wherein, in the b step, a first likelihood for each of the at least one node included in the graph is further calculated.4. The method for improving performance of text summarization according to claim 3 ,wherein, in the c step, when no keyword corresponding to the node is present in the context, a second likelihood is generated by assigning a weight to the first likelihood of the node.5. The method for improving performance of text summarization according to ...

СПОСОБ И УСТРОЙСТВО ДЛЯ ОТОБРАЖЕНИЯ ИНФОРМАЦИОННЫХ ПОТОКОВ В СОЦИАЛЬНОЙ СЕТИ И СЕРВЕР

Изобретение относится к способу и устройствам для отображения информационных потоков в социальной сети. Технический результат заключается в обеспечении объединения порций целевой информации. Способ содержит этапы, на которых в информационных потоках, размещенных пользователем социальной сети, оценивают, имеется ли порций целевой информации в количестве, большем чем или равном установленному числу, размещенных в течение установленного периода времени, причем число размещенных в течение установленного периода времени порций целевой информации устанавливается на основании числа отслеживаемых пользователей, если оценивают, что порции целевой информации существуют, в соответствии с предварительно установленным правилом, объединяют порции целевой информации в группу целевой информации и отображают группу целевой информации. 3 н. и 18 з.п. ф-лы, 13 ил.

ОПТИМИЗАЦИЯ ИЗВЛЕЧЕНИЯ ФАКТА С ИСПОЛЬЗОВАНИЕМ МНОГОЭТАПНОГО ПОДХОДА

... 1. Способ обнаружения фактов (610) в электронных ресурсах (116), содержащий ! сканирование (502) электронного ресурса (116) для обнаружения фактографических описаний (402) из предложений, которые содержат слова, соответствующие словам таблицы слов факта, ! исследование (506) обнаруженных фактографических описаний (402) для идентификации лингвистических элементов фактографических описаний, и ! определение (510), следует ли представить фактографическое описание (402) как факт (610), на основе идентифицированных лингвистических элементов. ! 2. Способ по п.1, в котором определение, следует ли представить фактографическое описание как факт, на основе идентифицированного лингвистического элемента, содержит ! применение правил исключения в отношении лингвистических элементов фактографических описаний для удаления определенных фактографических описаний из рассмотрения, ! оценивание фактографических описаний, ! сравнение оценок каждого фактографического описания, оставшегося в рассмотрении, с порогом ...

DOMÄNENWISSENSINJEKTION IN HALB-SCHWARMAUSGELAGERTE UNSTRUKTURIERTE DATENZUSAMMENFASSUNG FÜR DIAGNOSE UND REPARATUR

Ein Informationssynthesesystem zum Erzeugen einer Wissensbasis injiziert Domänenwissen in halb-schwarmausgelagerte Zusammenfassungspipelines zum Extrahieren von Informationen aus unstrukturierten Datenquellen. Die Zusammenfassungspipeline umfasst Ketten von Aufgaben, die durch Schwarmarbeiter und/oder Maschinen durchgeführt werden. Das Informationssynthesesystem verteilt die Aufgaben an Schwarmarbeiter und/oder Maschinen. Aufgabenantworten werden verarbeitet und gebündelt, um neue Informationen zu bestimmen, die verwendet werden, um die Wissensbasis zu aktualisieren.

Abstractive summarization of long documents using deep learning

Disclosed is an abstractive summarization method for summarizing documents, including long documents. The method for generating a summarization of a structured document having a plurality of sections comprises: processing each word in a plurality of words in a section using a respective first recurrent neural network to generate a word-level representation; processing each word-level representation by a second recurrent neural network to generate a section-level representation; generating a context vector by performing a neural attention process on one or more hidden states of said first recurrent neural network and one or more hidden stats of said second recurrent neural network; and then generating a next predicted word in said summarization based upon a previously predicted work and said context vector. The method is used for example to generate a document S from scratch by using words and phrases that are not exactly from the original document D. This robust abstractive summarization ...

Method for simulating a technical device

PROCEDURE, AROUND NATURE-LINGUISTIC INQUIRIES FROM TEXT DATA BANKS TO RELEASE

Methods and apparatus for summarizing document content for mobile communication devices

Section extraction tool for pdf documents

Graphical user interfaces for jury verdict information

The present inventors devised, among other things, an online legal research system that allows users to generate a report interface that not only summarizes key pieces of information, such as verdict information, but also enables access to related trending and statistical information as well as additional litigation, analytical, and expert materials. The exemplary system generates a dynamic verdict report based on parameters selected from a query-definition template having an embedded taxonomy.

A SYSTEM FOR DEEP ABSTRACTIVE SUMMARIZATION OF LONG AND STRUCTURED DOCUMENTS

Techniques are disclosed for abstractive summarization process for summarizing documents, including long documents. A document is encoded using an encoder-decoder architecture with attentive decoding. In particular, an encoder for modeling documents generates both word-level and section-level representations of a document. A discourse-aware decoder then captures the information flow from all discourse sections of a document. In order to extend the robustness of the generated summarization, a neural attention mechanism considers both word-level as well as section-level representations of a document. The neural attention mechanism may utilize a set of weights that are applied to the word-level representations and section-level representations. x -~ E ) 0z 0o '0 0 UJ-A Z u0 a a) 0 UCD a) -< -oa 0 C0 o2 > a5a)a i6 T, ,m 0i c-) 00'a - t5~o a)- 0)' t5U 0) (3 a 0) 0 o0)U)0 a -5 Ma)0 U,06t CL )a)0E ...

METHOD TO GENERATE SUMMARIES TUNED TO TOPICS OF INTEREST OF READERS

A word generation model obtains textual content and a requested topic of interest, and generates a targeted summary of the textual content tuned to the topic of interest. To do so, a topic-aware encoding model encodes the textual content with a topic label corresponding to the topic of interest to generate topic-aware encoded text. A word generation model selects a next word for the topic-based summary from the topic-aware encoded text. The word generation model is trained to generate topic-based summaries using machine learning on training data including a multitude of documents, a respective summary of each document, and a respective topic of each summary. Feedback of the selected next word is provided to the word generation model. The feedback causes the word generation model to select subsequent words for the topic based summary based on the feedback of the next selected word. Service Provider System 102 Request Topic-Based Summary Training Module Module 118 124 Cxtuat Word Generation ...

Method for presenting documents using a reading list panel

A reading list panel is displayed as a sidebar window with respect to a main window of a content viewing application. In response to a first input, a first article representation of a first article associated with a presentation page displayed in the main window is listed in the reading list panel, where the first article representation includes information identifying the first article. In response to a selection of a second article representation from the reading list panel, content of a second article represented by the second article representation is presented in a reader mode within the main window.

SYSTEM AND METHOD FOR ANALYZING AND MODELING CONTENT

Described herein are systems and methods for aggregating, parsing, and annotating regulatory context for use in resolving transactional inquiries. In one embodiment, a method comprises: aggregating documents from a plurality of data sources and storing the aggregated documents in a document database; selecting a first document from the document database; extracting regulatory content from the first document; parsing the regulatory content into a structured data object; identifying a substantively-relevant portion of the regulatory content in the structured data object; generating an annotation associated with the substantively-relevant portion; storing the generated annotation in an annotation database; and generating a domain-specific data structure for resolving transactional inquiries based on the annotation database.

SELECTIVELY GENERATING WORD VECTOR AND PARAGRAPH VECTOR REPRESENTATIONS OF FIELDS FOR MACHINE LEARNING

Word vectors are multi-dimensional vectors that represent words in a corpus of text and that are embedded in a semantically-encoded vector space; paragraph vectors extend word vectors to represent, in the same semantically-encoded space, the overall semantic content and context of a phrase, sentence, paragraph, or other multi-word sample of text. Word and paragraph vectors can be used for sentiment analysis, comparison of the topic or content of samples of text, or other natural language processing tasks. However, the generation of word and paragraph vectors can be computationally expensive. Accordingly, word and paragraph vectors can be determined only for user-specified subsets of fields of incident reports in a database.

METHOD AND SYSTEM TO PROVIDE VIDEO-BASED SEARCH RESULTS

METHOD, APPARATUS, AND ELECTRONIC DEVICE FOR EXECUTING TRANSACTIONS BASED ON BLOCKCHAIN

A node device of a blockchain receives a target transaction including transaction content, where at least a part of the transaction content comprises a content summary of target content stored in a third-party storage system connected to the blockchain. The target content corresponding to the content summary is queried from the third-party storage system. The target content is verified based on the content summary of the target content in the target transaction. If the verification of the target content succeeds, the target transaction is executed based on the transaction content in the target transaction. After the target transaction is executed, the target transaction is stored in a distributed database of the blockchain.

COMPUTING DEVICE AND CORRESPONDING METHOD FOR GENERATING DATA REPRESENTING TEXT

An example method involves (i) accessing first data defining multiple portions of a content item, wherein at least a plurality of the portions represent text; (ii) selecting, from the plurality of portions representing text, a subset of the portions representing text, wherein the selecting is based on each portion of the selected subset having a particular characteristic; (iii) based on the text represented by the portions of the selected subset, generating second data that represents a concatenation of the text represented by the portions of the selected subset; and (iv) providing output based on the generated second data.

SYSTEMS AND METHODS FOR ANALYZING DOCUMENTS

Systems and methods are provided for analyzing documents. In one implementation, a computer implemented method is provided for analyzing a patent application and providing a visual representation. According to the method, a selection is received from a user to view claims of the patent application in a claim tree hierarchy and a computer displays the claims in the claim tree hierarchy on a display. The claim tree hierarchy visually depicts relationships between the claims. The method identifies one or more words of at least one of the claims that constitutes an element and displays, in the claim tree hierarchy, the words constituting the element in association with the claim.

GRAPHICAL USER INTERFACES FOR JURY VERDICT INFORMATION

The present inventors devised, among other things, an online legal research system that allows users to generate a report interface that not only summarizes key pieces of information, such as verdict information, but also enables access to related trending and statistical information as well as additional litigation, analytical, and expert materials. The exemplary system generates a dynamic verdict report based on parameters selected from a query-definition template having an embedded taxonomy.

METHOD AND SYSTEM TO PROVIDE VIDEO-BASED SEARCH RESULTS

Method and system to provide video-based search results are described. A search results video may be present to a user details from listings that match certain search criteria. When a select request associated with the search results video is detected, a listing rendering module presents the selected listing on the display device.

REAL TIME STRUCTURED SUMMARY SEARCH ENGINE

A method of organizing electronic documents for storage and subsequent retrieval, involves storing a summary structure describing the structure of summary records associated with each document. Each structured summary record has at least one field representative of a characteristic of the document. A predetermined number of field values identify the value of the characteristic associated with the field. Predetermined keyword criteria associated with the field values are stored. Each document is analyzed to build a text index listing the occurrence of unique significant words in the document. The text index is compared with the keyword criteria to determine the appropriate field value for the document. For example, one characteristic field might be related to topic, which could have the field values of "financial" or "sports". The preponderance of certain keyword criteria, such as "money" or "shares" would identify the document with the financial topic.

AUTOMATED ASSISTANTS WITH CONFERENCE CAPABILITIES

TEXT ANALYZING DEVICE, PROBLEMATIC BEHAVIOR EXTRACTION METHOD, AND PROBLEMATIC BEHAVIOR EXTRACTION PROGRAM

The present invention provides a text analyzing device which can extract the great amount of problematic behavior at5 low cost. A punishment action text extraction means 81 extracts a text which describes a punishment action which is an action which indicates a punishment of a fraud or an illegal act, or an action for demanding the punishment, from an input text set which is a set of a plurality of texts to be inputted. A10 problematic behavior extraction means 82 extracts description related to a problematic behavior which is a cause of the punishment action taken before the punishment action described in the text extracted by the punishment action text extraction means 81.

System and method for traffic engineering information summary of a zone in network communications

A method for summarizing topology transparent zone (TTZ) traffic engineering (TE) information, comprising computing a TE link state for every TE link internal to a TTZ from a root node to one or more non-root edge nodes, wherein the TE link state comprises the maximum bandwidth of the link, summarizing the computed TE link state information and storing the summary in a memory, and distributing at least a portion of the information in the summary to at least one neighboring node external to the TTZ connected to the root node via an external link.

Query disambiguation

A search query is resolved prior to being submitted to one or more search engines. The query is resolved such that the query unambiguously corresponds to a category included in a query ontology that relates search queries to query categories. The query may be resolved by supplementing the query with additional information corresponding to the category. For example, the query may be formatted into a canonical form of the query for the category. Alternatively or additionally, the query may be supplemented with one or more keywords that are associated with the category and that represent words or phrases that appear in a high percentage of search results for queries from the category. Resolving the query yields search results that more closely reflect search results desired by a user submitting the query.

Method and system for generating a value enhanced derivative document from a patent document

The invention describes system and method for generation a derivative document from a patent document, which provide value, enhanced representation of the document and facilitate comprehension of information contained in the patent document. A segment of the patent document is selected and transformed into a value added form by extracting at least two portions of information from the selected segment and converting them into different forms. Conveniently, the converted forms include respective elements where the required correspondence is established between the elements. Depending on customer needs and requirements to the system, a customized selection of the elements can be provided with optional display, storage and/or delivery of the selected data over a network. Beneficially, generation of the derivative is performed by using distributed processing of the document in a network, where two or more computers are involved. Corresponding method of generation a database of the derivative ...

Generation of explanatory summaries

A method for generating summaries of text is described. The method includes the step of extracting features from text of text lists from summaries. The explanatoriness of the text is then evaluated, wherein evaluating the explanatoriness of text includes evaluating the features of the text, including at least the step of evaluating the discriminativeness of the features of the text by comparing the text to a first text data set, wherein the first text data set is derived from a topic label. The evaluated text is then ranked based on the explanatoriness evaluation.

Systems and methods for automatically generating content layout based on selected highest scored image and selected text snippet

A computerized method for automatically generating display content includes receiving a uniform resource locator, wherein the uniform resource locator specifies a landing resource and extracting visual information from the landing resource, wherein the visual information defines one or more images, texts, and colors displayed on the landing resource. The method further includes selecting one or more images, one or more text snippets, and one or more colors based on the visual information extracted from the landing resource, generating a layout for a content item based on one or more of the selected images or selected text snippets, and assembling the content item by applying the selected images, the selected text snippets, and the selected colors to the generated layout.

Graphical controls for selecting criteria based on fields present in event data

The disclosure relates to certain system and method embodiments for generating reports from unstructured data. In one embodiment, a method can include identifying events matching criteria of an initial search query (each of the events including a portion of raw machine data that is associated with a time), identifying a set of fields, each field defined for one or more of the identified events, causing display of an interactive graphical user interface (GUI) that includes one or more interactive elements enabling a user to define a report for providing information relating to the matching events (each interactive element enabling processing or presentation of information in the matching events using one or more fields in the identified set of fields), receiving, via the GUI, a report definition indicating how to report information relating to the matching events, and generating, based on the report definition, a report including information relating to the matching events.

CONTEXTUAL FEATURE SELECTION WITHIN AN ELECTRONIC DATA FILE

A system and method for feature selection within an electronic data file includes gathering a plurality of features from a first electronic data file. A relevancy of each of the plurality of features of the first electronic data file is determined, wherein the relevancy is expressed numerically. At least one of the plurality of features meeting a predetermined relevancy numeric is selected to create a summary file for one feature of the first electronic data file. The one feature of the first electronic data file is isolated with features of other electronic data files. A feature matrix is created for each electronic data file, the feature matrix having the plurality of features for each electronic data file. A connection between one of the plurality of features within the feature matrix is identified with a searched string based on a relevancy of the plurality of features to the electronic data file.

Text mining device, text mining method, and text mining program

Provided is a text mining device capable of showing a user whether the characteristics extracted by a text mining are either common to all texts independently of the citations, in case the text to be mined is configured with texts of a plurality of kinds of different citations, or deviated toward a text of a predetermined citation. The text mining device includes a citation information creating device for creating the citation information of texts containing characteristics extracted from a text set collected from a plurality of citations, and a mining result output device for outputting the characteristics and the citation information in a corresponding manner.

GENERATING CUSTOMIZED MEETING INSIGHTS BASED ON USER INTERACTIONS AND MEETING MEDIA

Methods, systems, and non-transitory computer readable storage media are disclosed for generating meeting insights based on media data and device input data. For example, in one or more embodiments, the disclosed system utilizes analyzes media data including audio data or video data and inputs to client devices associated with a meeting to determine a portion of the meeting (e.g., a portion of the media data) that is relevant for a user. In response to determining a relevant portion of the meeting, the system generates an electronic message including content related to the relevant portion of the meeting. The system then provides the electronic message to a client device of the user. For instance, in one or more embodiments, the system generates a meeting summary, meeting highlights, or action items related to the media data to provide to the client device of the user. In one or more embodiments, the system also uses the summary, highlights, or action items to train a machine-learning model ...

System and method for personalized snippet generation

Snippets of text provided are generated based in part on a user's profile. An item, such as a document, is examined to identify terms related to the user's profile. A term profile for an identified term is compared to a user's profile. The more closely related the identified term is to the user's profile, the higher a similarity score will be. Alternatively, terms found in a document may have a user profile score which may be obtained by looking the term up in the user's profile. Terms having high profile similarity scores or high user profile scores are used in identifying snippets which may be relevant to a user. The high scoring terms may be added to search terms and provided to a snippet generator.

Web-based system and method for archiving and searching participant-based internet text sources for customer lead data

A text mining system for collecting business intelligence about a client, as well as for identifying prospective customers of the client, for use in a lead generation system accessible by the client via the Internet. The text mining system has various components, including a data acquisition process that extracts textual data from various Internet sources, a database for storing the extracted data, a text mining server that executes query-based searches of the database, and an output repository. A web server provides client access to the repository, and to the mining server.

Phrase based snippet generation

Disclosed herein is a method, a system and a computer product for generating a snippet for an entity, wherein each snippet comprises a plurality of sentiments about the entity. One or more textual reviews associated with the entity is selected. A plurality of sentiment phrases are identified based on the one or more textual reviews, wherein each sentiment phrase comprises a sentiment about the entity. One or more sentiment phrases from the plurality of sentiment phrases are selected to generate a snippet.

Systems and methods for generating issue networks

Systems and methods for generating issue networks are disclosed. In one embodiment, a computer-implemented method of generating an issue network from a document corpus includes searching, using a computer, the document corpus for a set of documents discussing a starting issue, wherein the starting issue is one of a plurality of normalized issues defined by the document corpus. The method further includes determining a set of normalized issues discussed by the set of documents discussing the starting issue, wherein the set of normalized issues also includes the starting issue, and determining instances of co-occurrences of individual normalized issues of the set of normalized issues within individual cases of the set of documents. The method also includes linking individual normalized issues of the set of normalized issues based on their co-occurrences within the set of documents, wherein the linked individual normalized issues at least in part define the issue network.

Keyword outputting apparatus and method

A keyword analysis device obtains word vectors represented by the documents by analyzing keywords contained in each of documents input in a designated period. A topic cluster extraction device extracts topic clusters belonging to the same topic from a plurality of documents. A keyword extraction device extracts, as a characteristic keyword group, a predetermined number of keywords from the topic cluster in descending order of appearance frequency. A topic structurization determination device determines whether the topic can be structurized, by segmenting the topic cluster into subtopic clusters with reference to the number of documents, the variance of dates contained in the documents, or the C-value of keyword contained in the documents, as a determination criterion. And a keyword presentation device presents the characteristic keyword group in the subtopic cluster upon arranging the keyword group on the basis of the date information.

Systems and methods for generating summaries of documents

Systems and methods for summarizing online articles for consumption on a user device are disclosed herein. The system extracts the main body of an article's text from the HTML code of an online article. The system may then classify the extracted article into one of several different categories and removes duplicate articles. The system breaks down the article into its component sentences, and each sentence is classified into one of three categories: (1) potential candidate sentences that may be included in the generated summary; (2) weakly rejected sentences that will not be included in the summary but may be used to generate the summary; and (3) strongly rejected sentences that are not included in the summary. Finally, the system applies a document summarizer to generate quickly readable article summaries, for viewing on the user device, using relevant sentences from the article while maintaining the coherence of the article.

System and method for peer group detection, visualization and analysis in identity management artificial intelligence systems using cluster based analysis of network identity graphs

Systems and methods for graph based artificial intelligence systems for identity management systems are disclosed. Embodiments of the identity management systems disclosed herein may utilize a network graph approach to peer grouping of identities of distributed networked enterprise computing environment. Specifically, in certain embodiments, data on the identities and the respective entitlements assigned to each identity as utilized in an enterprise computer environment may be obtained by an identity management system. A network identity graph may be constructed using the identity and entitlement data. The identity graph can then be clustered into peer groups of identities. The peer groups of identities may be used by the identity management system and users thereof in risk assessment or other identity management tasks.

System And Method For Generating An Information Stream Summary Using A Display Metric

A system and method for generating an information stream summary using a display metric is provided. An information stream including a plurality of information stream items is received. A display metric is calculated for each of the plurality of information stream items. The information stream items are grouped into one or more summary objects. A size is assigned to each of the one or more summary objects and the one or more summary objects are displayed based on the assigned size.

INFORMATION PROCESSING APPARATUS AND NON-TRANSITORY COMPUTER READABLE MEDIUM STORING PROGRAM

An information processing apparatus includes a segment obtaining section that obtains a segment described in a document designated by a user, an extraction condition obtaining section that obtains an extraction condition for extracting information including a concept related to the segment as knowledge information from a concept structure information storage section storing concept structure information in which concepts representing events and relationships related to knowledge are related to each other in a hierarchical structure, a specifying section that specifies a storage location of the knowledge information in the concept structure information storage section and an extraction method for the concept included in the knowledge information from a designated content of the extraction condition, an extraction section that extracts the knowledge information in accordance with the specified extraction method from the storage location specified by the specifying section, and a presentation ...

System and method for facts extraction and domain knowledge repository creation from unstructured and semi-structured documents

Provided are methods and systems that extract facts of unstructured documents and build an oracle for various domains. The present invention addresses the problem of efficient finding and extraction of facts about a particular subject domain from semi-structured and unstructured documents, makes inferences of new facts from the extracted facts and the ways of verification of the facts, thus becoming a source of knowledge about the domain to be effectively queried. The methods and systems can also extract temporal information from unstructured and semi-structured documents, and can find and extract dynamically generated documents from Deep or Dynamic Web.

Ontological concept-based, user-centric text summarization

A method and system for constructing a text summarization. At least one domain ontology that includes a set of concepts is selected. A user profile indicative of a user's interests is defined in terms of the ontology concepts. A document's relevance to the user is determined based upon the user profile. If the document is relevant, at least a portion of the ontology is used to extract concepts from the document. The degree of match between the extracted concepts and the user profile concepts is determined and the document text summary is generated if the degree of match exceeds a predetermined threshold. Generating the summary may include selecting sentences based on the concepts in the user profile, ranking the selected sentences by relevance to the user profile, selecting sentences for inclusion in the document text summary based upon the ranking, and merging the selected sentences into the document text summary.

Data summarization method and apparatus

A method of generating caption abstract, including: generating a target text from a predetermined caption, analyzing a morpheme of a word included in the target text, and analyzing a grammatical structure of the target text by referring to the morpheme; extracting and removing low content words from the target text by using the morpheme or information on the grammatical structure and determining a main predicate; extracting a major sentence component with respect to the main predicate by referring to the information on the grammatical structure, as a candidate abstract word; substituting a relevant word for a complex noun phrase or a predicate phrase from the candidate abstract words by referring to a predetermined database; and generating an abstract by rearranging the candidate abstract words according to a predetermined rule.

Contextual content graph for automatic, unsupervised summarization of content

A method, system and computer-usable medium are disclosed for using a contextual graph to summarize a corpus of content. Natural Language Processing (NLP) preprocessing operations are performed on text within an input corpus to form a grammatical analysis. In turn, the grammatical analysis is used to generate semantic associations between phrases in the input corpus. The resulting semantic associations are then used to determine the thematic relevance of the individual sentences in the input corpus to form a context-based ranking. In turn, the context-based ranking is used to construct a context graph, the vertices of which are represented by phrases, and the edges are represented by an aggregate score resulting from performing calculations associated with semantic similarity of the phrases. The resulting context graph is then used to generate a content summarization for the input corpus.

INTELLIGENT IMAGE NOTE PROCESSING

Embodiments for intelligent image note processing by a processor. One or more images associated with a user equipment (UE) may be determined to have notation data. The notation data may be extracted from the one or more images to create one or more actions in relation to the notation data.

Signature generation using message summaries

Systems and methods for processing a message are provided. A message may be processed to generate a message summary by removing or replacing certain words, phrases, sentences, punctuation, and the like. Message signatures based upon the message summary may be generated and stored in a signature database, which may be used to identify and/or classify spam messages. Subsequently received messages may be classified by signature and processed based on classification.

DESIGN-TIME INFORMATION BASED ON RUN-TIME ARTIFACTS IN TRANSIENT CLOUD-BASED DISTRIBUTED COMPUTING CLUSTERS

Transient computing clusters can be temporarily provisioned in cloud-based infrastructure to run data processing tasks. Such tasks may be run by services operating in the clusters that consume and produce data including operational metadata. Techniques are introduced for tracking data lineage across multiple clusters, including transient computing clusters, based on the operational metadata. In some embodiments, operational metadata is extracted from the transient computing clusters and aggregated at a metadata system for analysis. Based on the analysis of the metadata, operations can be summarized at a cluster level even if the transient computing cluster no longer exists. Further relationships between workflows, such as dependencies or redundancies, can be identified and utilized to optimize the provisioning of computing clusters and tasks performed by the computing clusters.

System and method for generating social summaries

The described implementations relate to communication platforms that are provided over computer networks. One implementation provides a system that can include a storage component configured to store a plurality of communications having a common connector. The system can also include a score computation component that is configured to compute scores reflecting semantic relationships between individual communications from the plurality of communications. The system can also include a summary generation component that is configured to select one or more of the individual communications, based on the scores, and generate a summary of the common connector. The summary can represent the selected individual communications. The system can also include at least one processor configured to execute one or more of the components.

RANKING TEXT SUMMARIZATION OF TECHNICAL SOLUTIONS

An approach to ranking identified technical solutions summaries may be provided. The approach may include extracting data from technical tickets, subject matter expert reports, and online forum data. The approach may include receiving data relating to prior applications of one or more technical solutions. Steps associated with a technical solution may be included in the information from the prior application of the technical solutions and updated based on the information from prior applications of technical solutions. The approach may include generating a risk score and a cost score for the updated technical solution based on contextual factors associated with a user or machine. The approach may include enriching a static summary for the technical solution with the cost and risk score. The approach may include ranking the enriched summary against multiple potential technical solutions.

MACHINE LEARNING FOR MULTI-CHANNEL INTERACTION WORKFLOWS

Interactions between organizations occur through multiple channels such as textual communication (e.g., emails) and voice communication (e.g., telephone conversations). All such interaction data collated together constitutes a large amount of unstructured data. A framework is provided for collating the unstructured interaction data and creating a machine-legible structure from it using machine learning models. The machine learning models may generate a variety of generic as well as business-context-relevant insights, with the usage and application of custom-built machine learning model pipelines that generate an overall business insight record that can then be published back into a customer relationship management (CRM) system. Multiple data types are used for the interactions. For example, a voice call may be recorded and stored as an audio file, whereas an email may be stored as a text file. Multiple such formats may also be used to store interaction data.

Determining topic labels for communication transcripts based on a trained generative summarization model

The disclosure herein describes determining topics of communication transcripts using trained summarization models. A first communication transcript associated with a first communication is obtained and divided into a first set of communication segments. A first set of topic descriptions is generated based on the first set of communication segments by analyzing each communication segment of the first set of communication segments with a generative language model. A summarization model is trained using the first set of communication segments and associated first set of topic descriptions as training data. The trained summarization model is then applied to a second communication transcript and, based on applying the trained summarization model to the second communication transcript, a second set of topic descriptions of the second communication transcript is generated. By training the summarization model based on output of the generative language model, it enables efficient, accurate generation ...

Summarization Systems and Methods

A server-side summarization system includes a function for acquiring material to be summarized, along with source information about the material, a converter for converting the acquired material to machine-readable form, if not in that form when acquired, a summarizer for creating a summary from the acquired material, and a storage function for storing a copy of the acquired material and the summary created as separate files, associated and cross-referenced using the source information.

Techniques for style transformation

Techniques to stylistically transform source text are disclosed. A source text and information about an output channel may be received. The source text may be stylistically transformed based on the information about the output channel. The stylistically transformed source text may be output. Other embodiments are described and claimed.

Image-based popularity prediction

A machine may be configured to access an image of an item described by a description of the item. The machine may determine an image quality score of the image based on an analysis of the image. A request for search results that pertain to the description may be received by the machine, and the machine may present a search result that references the item's image, based on its image quality score. Also, the machine may access images of items and descriptions of items and generate a set of most frequent text tokens included in the item descriptions. The machine may identify an image feature exhibited by an item's image and determine that a text token from the corresponding item description matches one of the most frequent text tokens. A data structure may be generated by the machine to correlate the identified image feature with the text token.

Keyword Suggestion for Efficient Legal E-Discovery

Given a set of documents relevant to a litigation hold and a seed set of keywords, a second set of keywords can be generated and suggested to a user. Each document in a training set of documents is given an indication of relevance. Based on the indication of relevance, a set of further keywords relevant to the litigation is extracted from the documents and suggested to a user. The suggested set of keywords may or may not include keywords in the seed set. Additionally, the suggested set of keywords may be related to the seed set of keywords.

Systems and methods for generating and displaying user preference tag clouds

Systems and methods for generating and displaying user preferences in a tag cloud are provided in accordance with various embodiments of the present invention. A user preference tag cloud may be of any shape and size and may be generated using a stencil selected by a user. A user preference tag cloud may thus present a user's media preferences in an attractive and compelling visual arrangement that, in some embodiments, also functions as an intuitive interface which allows users to indicate and/or modify their preferences.

Character-based automated shot summarization

Methods, devices, systems and tools are presented that allow the summarization of text, audio, and audiovisual presentations, such as movies, into less lengthy forms. High-content media files are shortened in a manner that preserves important details, by splitting the files into segments, rating the segments, and reassembling preferred segments into a final abridged piece. Summarization of media can be customized by user selection of criteria, and opens new possibilities for delivering entertainment, news, and information in the form of dense, information-rich content that can be viewed by means of broadcast or cable distribution, “on-demand” distribution, internet and cell phone digital video streaming, or can be downloaded onto an iPod™ and other portable video playback devices.

Extracting terms from document data including text segment

A computer system, method, and article of manufacture for extracting a term from electronic document data that includes a text segment. The system includes: a first extraction unit that uses a first text processing information to extract a noun word from the document data; a second extraction unit that uses a second text processing information to extract a term candidate in relation to the noun word or a corpus that includes text data described in the same language used in the document data; a weight assignment unit that uses a third text processing information to select which type to assign a weight from the plurality of types and assigns the weight to the selected type for each noun word and term candidate; a determination unit that determines the type to which the noun word and term candidate belong; and an output unit to output the noun word and term candidate.

Systems and methods for extraction of policy information

In a system for extracting policy information from text, a processor analyzes if the text is relevant to a top-level category, and then determines if at least a portion of the text is relevant to categories and subcategories within a taxonomy of categories and subcategories related to the top-level category. If at least a portion of the text is determined to be relevant to the category/subcategory, a classifier extracts policy information associated with the category/subcategory. Using text that includes a known policy the classifiers can be trained to correctly recognize categories/subcategories, and the values associated therewith.

Systems and Methods For Predictive Analytics for Site Initiation and Patient Enrollment

Methods and systems for predictive analytics for site initiation and patient enrollment are disclosed. One method may include: receiving a user's selection of one or more parameters associated with a clinical trial; accessing a database of data associated with a plurality of previous clinical trials; comparing the one or more parameters to the previous clinical trials; determining one or more factors associated with the clinical trial based on the comparison; and displaying the parameters and the factors on a display.

Systems and Methods for Subject Identification (ID) Modeling

Systems and methods for subject identification (ID) modeling are disclosed. A subject identification may be associated with information contained in one or more core domains such as a patient domain, a country domain, and/or an investigator domain. The domains can be generically designed such that data sources that are unknown at the time the domains are created can be managed. In this way, using generic structures that support the domains, data sources can be added and/or updated as additional information and/or data sources become available. Using various graphical user interfaces, a user can dynamically associate patient criteria, country criteria, investigator criteria, and/or other information with subject identifications. A subject identification may be associated with a specified capture date. Information contained in the various domains may be filtered such that only information contained in the domain on or before the capture date is available for the subject identification.

Community authoring content generation and navigation

One or more techniques and/or systems are provided for creating socially authored, or community authored, summaries of documents and/or for navigating a forum comprising such summaries. In one embodiment, at least some of the summaries are generated automatically when a document is written and/or discovered (e.g., by a web crawler), for example. In another embodiment, the documents are created by users of the forum. A plurality of summaries of a document may be created (e.g., by different users), and users can provide feedback, such as comments or ratings, that may assist other users in identifying which summary or summaries better describe the document. Moreover, the users can navigate the forum and retrieve summaries by browsing categories (and subcategories) to identify a topic of interest and/or by performing a search based upon user inputted search term(s).

CROSS-CONTEXT NATURAL LANGUAGE MODEL GENERATION

Provided is a method including obtaining a corpus and an associated set of domain indicators. The method includes learning a set of vectors in an embedding space based on n-grams of the corpus. The method includes updating ontology graphs comprising a set of vertices and edges associating the set of vertices with each other. The method also includes determining a vector cluster using hierarchical clustering based on distances of the set of vectors with respect to each other in the embedding space and determining a hierarchy of the ontology graphs based on a set of domain indicators of a respective set of vertices corresponding to vectors of the vector cluster. The method also includes updating an index based on the ontology graphs. 1. A computer-implemented method of using domain-specific ontologies to of providing summaries of documents in a corpora of natural-language text documents , the method comprising:obtaining, with a computer system, a set of user-specific context parameters and a natural-language text document;determining, with the computer system, a first domain of knowledge based on the set of user-specific context parameters, wherein the first domain of knowledge maps to a first ontology amongst a plurality of ontologies, and wherein ontologies in the plurality of ontologies map n-grams onto a set of concepts to which the n-grams refer;scoring, with the computer system, a first set of n-grams of the natural-language text document using a scoring model based on relations between members of the first set of n-grams;selecting, with the computer system, text sections of the natural-language text based on n-gram scores provided by the scoring model;determining, with the computer system, an initial set of n-grams of the n-grams, wherein each respective n-gram of the initial set of n-grams maps to a respective concept of the set of concepts, and wherein each respective n-gram is identified by an ontology other than the first ontology;determining, with the ...

Computing device and corresponding method for generating data representing text

An example method involves (i) accessing first data defining multiple portions of a content item, wherein at least a plurality of the portions represent text; (ii) selecting, from the plurality of portions representing text, a subset of the portions representing text, wherein the selecting is based on each portion of the selected subset having a particular characteristic; (iii) based on the text represented by the portions of the selected subset, generating second data that represents a concatenation of the text represented by the portions of the selected subset; and (iv) providing output based on the generated second data.

STANCE DETECTION AND SUMMARIZATION FOR DATA SOURCES

Systems, methods, and software described herein provide improvements of identifying stances of data sources for events. In one implementation, an event summary service identifies data objects that correspond to an event and identifies a data source from a plurality of data sources for each of the data objects. The summary service further, for each data object of the data objects, processing the data object to identify pertinent data related to a stance for the data source for the data object in relation to the event, and identifies a stance for each of the plurality of data sources based on the pertinent data identified in the data objects. 1. A method of providing stance detection summaries for events , the method comprisingidentifying data objects that correspond to an event;identifying a data source from a plurality of data sources for each of the data objects;for each data object of the data objects, processing the data object to identify pertinent data related to a stance for the data source for the data object in relation to the event;identifying a stance for each of the plurality of data source based on the pertinent data identified in the data objects; andgenerating a summary based on the stances of the plurality of sources.2. The method of further comprising receiving a user request for the summary.3. The method of claim 1 , wherein processing the data object to identify the pertinent data related to the stance for the source in relation to the event comprises identifying terms or phrases of interest related to the stance of the source.4. The method of claim 1 , wherein generating the summary based on the stances of the plurality of sources comprises generating a visualization indicating differences in stance between at least a portion of the plurality of sources.5. The method of further comprising:processing one or more additional data objects that correspond to secondary events to identify additional pertinent data related to a stance for a first data ...

SYSTEM AND METHOD FOR EXECUTING ACCESS TRANSACTIONS OF DOCUMENTS RELATED TO DRUG DISCOVERY

Disclosed is a system for executing access transactions of documents, for example, pertaining to drug discovery. A document and its metainformation are obtained, and value features are extracted from the document based on identification of concepts associated with the document. An importance score of the document is determined based on the value features and the metainformation. A summarized view of the document is constructed based on the value features, the metainformation, the concepts and the importance score. A unique identifier is generated for the document and associated with the summarized view and the concepts of the document. A search query is processed, and the summarized view of the document is retrieved and displayed based on the query. A request for accessing the document is validated, and document access is allowed when the request is validated successfully. The document access transaction may, for example, be facilitated using a blockchain platform. 1. A system for access transaction of a document containing sensitive and confidential information , the system comprising a server arrangement including one or more processors , the server arrangement being communicably coupled via one or more data communication networks with a first client device and a second client device , wherein the server arrangement , when operated , provides a platform configured to: wherein the importance score, displayed along-with the summarized view, for each of the document in the list is determined on the platform without storing, on the platform, any document of said list of documents;', 'validate the access request for the document by the second user;, 'receive an access request for a document selected, by the second user, from a list of documents retrieved in response to a search query and displayed, on a user interface connected to the second client device, wherein each of the document in the list is associated with a summarized view and an importance score, and'} ...

MAINTAINING CONTEXT OF CLINICALLY RELEVANT INFORMATION WHEN DISPLAYED

Systems, methods, and GUIs are provided for visually communicating clinically relevant information in a manner that maintains context and trends across various sizes of user interfaces, such as smaller user interfaces on mobile devices. In an embodiment, a user interface may display a first timeline area with a first indication of a timespan that represents a portion of the timeline. The first indication of the timespan may be scrollable to change the portion of the timeline displayed. The first timeline area may further comprise a set of clinical diagnoses with corresponding duration indicators. The user interface may also display a second timeline area with a second indication of a timespan, which may mirror the first indication of the timespan. The second timeline area may further comprise a set of diagnostic parameters and associated measurements. The user interface may also present a medication area having lists of medications separated by classification. 1. A system for configuring clinically relevant data to maintain trend context when displayed on a user interface , the system comprising:at least one processor;the user interface in communication with the at least one processor; and a first indication of a timespan presented horizontally between a first boundary and a second boundary, wherein the first indication of the timespan represents at least a portion of a generated timeline,', 'a set of clinical diagnoses presented vertically, and', 'a duration indicator associated with a clinical diagnosis of the set of clinical diagnoses, the duration indicator having an onset date end associated with an onset date of the clinical diagnosis and a duration region beginning at the onset date end and extending horizontally therefrom, wherein the duration region is expanded and compressed based on the first indication of the timespan., 'a first timeline area, the first timeline area comprising, 'one or more computer-readable storage devices storing instructions that, ...

SYSTEM AND METHOD FOR AGGREGATING DATA FROM A PLURALITY OF DATA SOURCES

According to certain aspects, a computer system may be configured to aggregate and analyze data from a plurality of data sources. The system may obtain data from a plurality of data sources, each of which can include various types of data, including email data, system logon data, system logoff data, badge swipe data, employee data, job processing data, etc. associated with a plurality of individuals. The system may also transform data from each of the plurality of data sources into a format that is compatible for combining the data from the plurality of data sources. The system can resolve the data from each of the plurality of data sources to unique individuals of the plurality of individuals. The system can also determine an efficiency indicator based at least in part on a comparison of individuals of the unique individuals that have at least one common characteristic. 1. A computer system comprising:a hardware computer processor configured to execute code to cause the computer system to:access, from a first data source, first data items each associated with one of a plurality of individuals, the first data items indicating one or more of a badge-in time indicating entrance to a physical facility or a badge-out time indicating exit from the physical facility;generate, for each individual, a first summary of first data items associated with the individual;access, from a second data source, second data items each associated with one of the plurality of individuals, the second data items indicating one or more of system login time, system logout time, VPN login time, or VPN logout time;generate, for each individual, a second summary of second data items associated with the individual, wherein at least the first summary and the second summary are each accessible by the computer system;determine, a first group of unique individuals each sharing a first correlation between the first summary and the second summary;determine a second group of unique individuals each ...

CONTEXT-AWARE SENTENCE COMPRESSION

A method comprising receiving digital documents, a query statement, and a summary length constraint; identifying, for each of said digital documents, a sentence subset, based, at least in part, on said query statement, a modified version of said summary length constraint, and a first set of quality objectives, generating, for each of said sentence subsets, a random forest representation; iteratively (i) sampling, from each of said random forest representations, a plurality of tokens to create a corresponding candidate document summary, based, at least in part, on weights assigned to each of said tokens, (ii) assigning a quality ranking to said candidate document summary, based, at least in part, on said first set of quality objectives and a second set of quality objectives, and (iii) adjusting said weights, based, at least in part, on said quality rankings; and outputting a highest ranking said candidate document as a compressed summary. 1. A system comprising:at least one hardware processor; and receive, as input, one or more digital documents, a query statement, and a summary length constraint,', 'automatically identify, for each of said one or more digital documents, a sentence subset, based, at least in part, on said query statement, a modified version of said summary length constraint, and a first set of quality objectives,', 'automatically generate, for each of said sentence subsets, a random forest representation,', 'iteratively:', '(i) automatically sample, from each of said random forest representations, a plurality of tokens to create a corresponding candidate document summary, based, at least in part, on weights assigned to each of said tokens,', '(ii) automatically assign a quality ranking to said candidate document summary, based, at least in part, on said first set of quality objectives and a second set of quality objectives, and', '(iii) automatically adjust said weights, based, at least in part, on said quality rankings, and', 'automatically output ...

SYSTEMS AND METHODS FOR PROVIDING A VISUALIZABLE RESULTS LIST

Systems and methods for displaying a visualizable results list in response to an electronic search request are disclosed. A method includes accessing metadata for each of a plurality of search results that result from a search query, annotating one or more locations in each search result with first and second indicators for each of one or more grouped search terms in first and second units based on the metadata, and displaying a visualizable results list that includes the plurality of search results and a corresponding hit pattern for each search result. The hit pattern includes the first indicator and the second indicator. 124.-. (canceled)25. A method of displaying a visualizable results list , the method comprising:receiving, by a processing device, a search query, wherein the search query comprises a plurality of search terms;grouping, by the processing device, the plurality of search terms into a plurality of units, wherein each of the plurality of units comprises a related one or more of the plurality of search terms;accessing, by the processing device, metadata for each document in a plurality of search results that corresponds to the search query;annotating, by the processing device, one or more highest ranked locations in each document with a first indicator for each of the one or more highest ranked search terms in a first unit of the plurality of units and a second indicator for each of the one or more search terms in a second unit of the plurality of units based on the metadata, wherein the highest ranked search terms in the first unit are terms that have been determined by the processing device to be more likely to be relevant to the search query relative to other terms; and the plurality of search results,', 'a corresponding hit pattern for each document in the plurality of search results,, 'displaying, by the processing device, a visualizable results list comprising 'a bar graph comprising a plurality of bars, wherein each bar of the plurality of bars ...

Real-time dynamic visual aid implementation based on context obtained from heterogeneous sources

In one embodiment, a computer-implemented method includes extracting one or more keywords from summarized content according to one or more classified topics. The method also includes searching for visual aid elements that relate to the one or more keywords in a visual aid element repository that stores a plurality of visual aid elements. In addition, the method includes selecting one or more visual aid elements from the visual aid element repository based on a type of the one or more classified topics. Also, the method includes generating at least one visual aid object using the one or more visual aid elements based on at least one predefined visual aid template. Moreover, the method includes delivering the at least one visual aid object to one or more registered devices of at least one user.

DISTRIBUTED TRANSACTION MANAGEMENT WITH TOKENS

A system, method and computer product for managing distributed transactions of a database. A transaction manager is provided for each of a plurality of transactions of the database. Each transaction manager is configured to perform functions that include generating a transaction token that specifies data to be visible for a transaction on the database. The database contains both row and column storage engines, and the transaction token includes a transaction identifier (TID) for identifying committed transactions and uncommitted transactions. A last computed transaction is designated with a computed identifier (CID), record-level locking of records of the database is performed using the TID and CID to execute the transaction, and the plurality of transactions of the database are executed with each transaction manager. 121-. (canceled)22. A method comprising:generating a transaction token specifying that changes to a database by a first transaction are visible to a second transaction and that changes to the database by a third transaction are not visible to the second transaction;locking a first record of the database; and generating an index including a column of first identifiers, the transaction token including a first identifier for identifying committed transactions in the column of first identifiers,', 'generating a delta index including a second identifier in a column of the delta index, and', 'replacing the second identifier in the column of the delta index with a third identifier for an uncommitted transaction that becomes committed, the delta index characterizing changes to the index., 'executing the second transaction using the transaction token by at least23. The method in accordance with claim 22 , wherein locking the first record further comprises storing the second identifier associated with one or more records in the database in every row and in the column of the delta index.24. The method in accordance with claim 22 , wherein transactions of the ...

DOCUMENT PROCESSING PROGRAM AND INFORMATION PROCESSING APPARATUS

A document processing program and an information processing apparatus that present a contract status of an organization based on the contents of contract documents. The document processing program including instructions that causes the information processing apparatus to: accept a condition for analyzing a contract document by an acceptance unit; extract a contract document by an analysis target extraction unit, wherein the contract document containing extraction information matching the condition accepted by the acceptance unit from a contract document database which includes a plurality of contract documents and in which information indicating a contract status of the plurality of contract documents is extracted as extraction information; analyze the contract document extracted by the analysis target extraction unit based on the condition accepted by the acceptance unit, by an analysis unit; and display and output an analysis result of the analysis unit by the output unit. 1. A non-transitory computer-readable medium storing a program including instructions that , when executed by a processor , causes an information processing apparatus connected to a document processing apparatus through a communication interface , to:accept a condition for analyzing a contract document by an acceptance unit;extract a contract document by an analysis target extraction unit, wherein the contract document containing information that matches to the condition accepted by the acceptance unit is extracted from a contract document database which contains a plurality of contract documents and information indicating a contract status of the plurality of contract documents;analyze the contract document extracted by the analysis target extraction unit based on the condition accepted by the acceptance unit, by an analysis unit; anddisplay and output an analysis result of the analysis unit by the output unit.2. A non-transitory computer-readable medium storing a program including instructions ...

SYSTEM AND METHOD FOR PEER GROUP DETECTION, VISUALIZATION AND ANALYSIS IN IDENTITY MANAGEMENT ARTIFICIAL INTELLIGENCE SYSTEMS USING CLUSTER BASED ANALYSIS OF NETWORK IDENTITY GRAPHS

Systems and methods for graph based artificial intelligence systems for identity management systems are disclosed. Embodiments of the identity management systems disclosed herein may utilize a network graph approach to peer grouping of identities of distributed networked enterprise computing environment. Specifically, in certain embodiments, data on the identities and the respective entitlements assigned to each identity as utilized in an enterprise computer environment may be obtained by an identity management system. A network identity graph may be constructed using the identity and entitlement data. The identity graph can then be clustered into peer groups of identities. The peer groups of identities may be used by the identity management system and users thereof in risk assessment or other identity management tasks. 1. An identity management system , comprising:a memory;a processor;a non-transitory, computer-readable storage medium including computer instructions for:presenting a peer group interface; a node for each of the first set of identities, and', 'an edge between a first node and a second node for each first identity and second identity that share at least one entitlement of the first set of entitlements, wherein the first node and the second node respectively represent the first identity and the second identity and where the edge has a weight based on the at least one shared entitlement between the first identity and the second identity; and, 'presenting a peer group determined from an identity graph through the peer group interface, wherein the identity graph was created from identity management data, the identity management data utilized in identity management in a distributed enterprise computing environment and comprising data on a first set of identities and a first set of entitlements associated with the first set of identities, wherein the identity graph includeswherein the peer group was determined by:pruning a first set of edges of the identity ...

SYSTEM AND METHOD OF EMBEDDING AND LAUNCHING A FORM FROM THIRD-PARTY KNOWLEDGE CONTENT

In the field of government engagement management, for users of an employee desktop web client, it is now possible, within the web client application, to search and read articles and/or knowledge content that has been authored to external locations. Due to this integration to external, third-party applications, content and/or articles can be displayed to an agent on the employee desktop web client graphical user interface. Agents can enter free text into a specific search field and review the results in summary form, and then select an article in HTML format to progress the current interaction with the client. An additional feature extending from this capability is to add an amount of coding to external knowledge content websites that are owned and/or operated by the owner of the system such that when the website is viewed through the third-party integration module, a button or icon appears within the website that when selected takes the agent to an appropriate form. This button or icon does not appear when the website is viewed outside of the system. This functionality adds value to the agent experience and enables the agent to provide an improved service to the end client. Results may be filtered by the search engine as well. Moreover, this system and method improves the operation of the computer in that the computer running such a system in the past was not able to integrate in such a fashion in a web client format. This system and method also enables an agent to handle calls with the web client more efficiently, and allows agents on the web client to automatically classify. 112.-. (canceled)13. A method of embedding and launching a form with an external application for an agent in a web client application , the method comprising:searching for relevant knowledge content for an interaction through a third-party integration module using a graphical user interface;launching a knowledge content form from a knowledge content website with an embedded knowledge content ...

Systems and methods for content processing

Embodiments of the present disclosure may be used to gather, rank, categorize, and perform other processing of various types of content. In some embodiments, content items such as text, images, video, and other content are received from a variety of different sources and are processed to generate an article containing selected content items. While there may be hundreds or thousands of separate articles and stories regarding a particular topic, embodiments of the present disclosure help provide users with a single concise article that contains high-quality content items selected from among a potentially vast number of disparate sources.

Question answering system using multilingual information sources

A method of question answering from multilingual information sources is disclosed. The present invention discloses a method, a computer system and a program product for selecting an information source language of an information source, the method includes: receiving a question; analyzing the question to obtain a category information of a word included in the question; obtaining a word included in the category information as estimated topic or region related to the question; determining a candidate for an information source language using the estimated topic or region; and selecting the information source language and corresponding information sources for retrieving documents to generate an answer of the question.

CAPTURING MESSAGES FROM A PHONE MESSAGE EXCHANGE

A method for text capture is provided. The method monitors a text session among a set of mobile text-enabled devices capable of having mixed operating system types. The method captures messages and message metadata from the text session by a machine-attended message-capture-dedicated phone configured for reception-or-pass-through-only with respect to the mobile text-enabled devices. The method receives the messages and the message metadata from the message-capture-dedicated phone by a remote message capture device that is constrained to have a compatible operating system type as the machine-attended message-capture-dedicated phone but unconstrained with respect to the operating system type of the set of mobile text-enabled devices. The method stores the metadata and the message metadata for remote access in a searchable remote message repository, unconstrained with respect to the operating system type of the set of mobile text-enabled devices, the machine-attended message-capture-dedicated phone, and the remote message capture device. 1. A method for text capture , comprising:monitoring a text session among a set of mobile text-enabled devices capable of having mixed operating system types;capturing during the text session messages and message metadata from the text session by a machine-attended message-capture-dedicated phone configured for reception-or-pass-through-only with respect to the one or more mobile text-enabled devices and unassociated with any of the message participants;receiving the messages and the message metadata from the machine-attended message-capture-dedicated phone by a remote message capture device that is constrained with respect to operating system type to have a compatible operating system type as the machine-attended message-capture-dedicated phone but unconstrained with respect to the operating system type of the set of mobile text-enabled devices; andstoring the metadata and the message metadata for remote access in a searchable remote ...

ACTIVE LISTENING TO MANAGE ADAPTIVE CONTENT ITEMS

Systems, methods, and software described herein provide improvements for dynamically modifying the presentation of content items to end users. In one example, a summary service determines first content items associated with an end user and determines a first sequence for the first content items. The summary service further monitors user interactions with one or more secondary services and determines content of interest for the end user based on the user interactions. As the content of interest is identified, the summary service determines second content items to be presented to the end user and determines a second sequence for the second content items based on the content of interest. 1. A method of managing content items for end users , the method comprisingdetermining first content items to be presented to an end user;determining a first sequence for the first content items;monitoring user interactions with one or more secondary services;determining content of interest for the end user based on the user interactions;determining second content items to be presented to the end user based on the content of interest; anddetermining a second sequence for the second content items based on the content of interest.2. The method of claim 1 , wherein the user interactions comprise voice and text communications using the one or more secondary services.3. The method of claim 1 , wherein the first content items comprise first summaries of a first plurality of events claim 1 , and wherein the second content items comprise second summaries of a second plurality of events.4. The method of claim 3 , wherein determining the first content items to be presented to the end user comprises:obtaining data objects from a plurality of data sources;generating the first summaries of the first plurality of events based at least on content of the data objects.5. The method of claim 4 , wherein generating the first summaries of the first plurality of events based at least on content of the data ...

Systems and Methods for Multi-Source Reference Class Identification, Base Rate Calculation, and Prediction

Systems and methods for multi-source reference class identification, base rate calculation, and prediction are disclosed. The systems and method can guide on, then elicit, information about reference class identification on a case-by-case basis, connects to a database in order to calculate historical base rates according to user reference class selections, and collect additional quantitative and qualitative information from users. The systems and methods can then generate predictive estimates based on the combination of the inputs by one or more users.

SYSTEM AND METHOD OF RUNNING AN AGENT GUIDE SCRIPT-FLOW IN AN EMPLOYEE DESKTOP WEB CLIENT

In the field of government engagement management, an agent guide or script-flow in an employee desktop web client is implemented. In such a system and method, when agents create interactions with clients they can follow a script-flow which will guide the agent through the interaction through a series of menu selections and automated sets of instructions. This feature of the government engagement management system allows existing customer investment from the rich desktop client or non-web client in developing specific scripts, that can also now function in the web client atmosphere. This system and method also enables an agent to handle calls with the web client more efficiently, and allows agents on the web client to automatically classify. 116.-. (canceled)17. A method of running an agent guide script-flow for an agent in a web client application , the method comprising:providing an engagement management system, wherein the system is configured to run agent guide script-flows for the agent in the web client application;using a graphical user interface, starting an interaction with a client through the web client application;determining, by a processor, the agent guide script-flow associated with an interaction type for the interaction;displaying the determined agent guide script-flow to an agent through the graphical user interface; andcompleting the interaction with the client after the determined script-flow is completed.18. The method of claim 17 , the method further comprising initializing the graphical user interface in the web client application.19. The method of claim 17 , wherein the agent guide script flow is text the agent will speak to the client.20. The method of claim 17 , wherein the interaction with the client is any one of a live telephone call claim 17 , face-to-face claim 17 , or a web chat session with the client.21. The method of claim 17 , further comprising completing the interaction with the client without the agent guide script-flow if no ...

UNSUPERVISED TEXT SIMPLIFICATION USING AUTOENCODERS WITH A CONSTRAINED DECODER

A method of producing an unsupervised constrained text simplification autoencoder including an encoder and a constrained decoder, including: encoding, by the encoder, input text to produce a code; combining a complexity parameter with the code; decoding, by constrained decoder, the combined code to produce a plurality of outputs, wherein the constrained decoder uses a dropout function to randomize the parameters of the constrained decoder; evaluating a loss function for each of the plurality of outputs, wherein the loss function is based upon the complexity parameter, indicates an achieved text simplification level, and produces an output indicating the difference between the achieved text simplification level and a desired text simplification level; and optimizing the constrained text simplification autoencoder by repeatedly evaluating the loss function for each input text in an input text training data set while varying parameters of the encoder, the parameters of the constrained decoder, and the complexity parameter until the output of the loss function is minimized. 1. A method of producing an unsupervised constrained text simplification autoencoder including an encoder and a constrained decoder , comprising:encoding, by the encoder, input text to produce a code;combining a complexity parameter with the code;decoding, by constrained decoder, the combined code to produce a plurality of outputs, wherein the constrained decoder uses a dropout function to randomize the parameters of the constrained decoder;evaluating a loss function for each of the plurality of outputs, wherein the loss function is based upon the complexity parameter, indicates an achieved text simplification level, and produces an output indicating the difference between the achieved text simplification level and a desired text simplification level; andoptimizing the constrained text simplification autoencoder by repeatedly evaluating the loss function for each input text in an input text training ...

Extraction of concept-based summaries from documents

Embodiments of the present invention enable users to generate a summary for a document with respect to a concept, making use of inherent hierarchies present in a text document based on subject-object relationships of the sentences in the text document. In one embodiment, a text document is parsed into sentences, and a tuple is created for each sentence, the tuple comprising a subject and an object found in the sentence. The tuples may then be searched for a specified topic to identify matching tuples, as well as tuples that are related to the matching tuples based on relationships between their respective subjects and objects. A summary focused on the specified topic may then be generated using the sentences corresponding to the matching tuples and the tuples related to the matching tuples.

GENERATING STRUCTURED DATA FOR RICH EXPERIENCES FROM UNSTRUCTURED DATA STREAMS

Aspects of the present disclosure are directed to providing a rich content experience based on information received from unstructured content. A plurality of information items may be obtained from a plurality of data source, where each information item includes unstructured content. The plurality of information items may be provided to a trained machine learning model, where the model is trained with training data that includes information items and corresponding labeled entities for a plurality of historical events. In examples, a formatted request may be received, where the formatted request is associated with one or more labeled entities associated with the trained machine learning model. The trained machine learning model may identify multiple entities from the unstructured content based on the formatted request associated with the one or more labeled entities. In examples, each identified entity of the multiple identified entities is stored as structured content responsive to the formatted request.

Signature generation using message summaries

Systems and methods for processing a message are provided. A message may be processed to generate a message summary by removing or replacing certain words, phrases, sentences, punctuation, and the like. Message signatures based upon the message summary may be generated and stored in a signature database, which may be used to identify and/or classify spam messages. Subsequently received messages may be classified by signature and processed based on classification.

Determining sentiments of social posts based on user feedback

User feedback regarding sentiments of social posts is used to improve sentiment assignment for social analysis. The user feedback is used to generate sentiment tuning data, which may include assignments between reference sentiments and reference social posts. Sentiments of new social posts may be determined by applying the sentiment tuning data to an analysis of the new social posts. Sentiments of new social posts may also be determined by applying entries from one or more lexical dictionaries to the new social posts using natural language processing. At least some of the entries can be automatically generated from the user feedback or can be supplied by a user separate from the user feedback.

SNIPPET GENERATION AND ITEM DESCRIPTION SUMMARIZER

In various example embodiments, a system and method for a Target Language Engine are presented. The Target Language Engine augments a synonym list in a base dictionary of a target language with one or more historical search queries previously submitted to search one or more listings in listing data. The Target Language Engine identifies a compound word and a plurality of words present in the listing data that have a common meaning in the target language. Each word from the plurality of words is present in the compound word. The Target Language Engine causes a database to create an associative link between the portion of text and a word selected from at least one of the synonym list or the plurality of words. 1. A system comprising:a processor; and receiving a search query from a mobile device that is mapped to a listing webpage for an item;', 'selecting one or more text portions from a plurality of text portions within the listing webpage based at least in part on a relevancy determination for the one or more text portions;', 'generating a listing snippet based at least in part on the one or more text portions; and', 'transmitting the listing snippet to the mobile device based at least in part on the search query., 'a memory coupled to the processor and storing instructions that, when executed by the processor, cause the system to perform operations comprising2. The system of claim 1 , wherein the instructions to select the one or more text portions claim 1 , when executed by the processor claim 1 , further cause the system to perform operations comprising:selecting a first text portion of the one or more text portions based at least in part on a relevancy score of the first text portion satisfying a threshold relevancy score.3. The system of claim 1 , the operations further comprising:comparing the plurality of text portions to a list of keywords;identifying a subset of the plurality of text portions that includes one or more words from the list of keywords; ...

Creation of a summary for a plurality of texts

Creating a summary of a plurality of texts includes tokenizing each of a plurality of texts to obtain tokens; generating a vector space using a first set of vectors having one or more obtained feature scores equal to or larger than a predefined value; executing non-hierarchical clustering using the vector space to generate a first plurality of clusters; choosing a first representative text in each of the plurality of clusters; generating a second set of vectors from each of the arrays generated based on a number of characters included in tokens of the representative texts; executing hierarchical clustering using the second set of vectors to generate a second plurality of clusters; and in response to a determining a number of clusters included in the second plurality of clusters, determining a second representative text for each of the clusters included in the second plurality of clusters.

INGESTION PLANNING FOR COMPLEX TABLES

Embodiments of the present invention disclose a method, computer program product, and system for generating a plan for document processing. A plurality of electronic documents are received, by a computer, using a network. The plurality of electronic documents are analyzed, using the computer, to identify a plurality of tabular data, based on the analyzed plurality of electronic documents. Textual data is identified within the identified tabular data, of the analyzed plurality of electronic documents. Textual hints are generated, based on the identified textual data within the identified tabular data. References are identified, wherein references are based on matching textual hints with textual data in the received plurality of electronic documents. A count of references is calculated, associated with one or more sets of tabular data. A priority score is calculated based on the count of references, and an ingestion plan is generated, based on the calculated priority score. 1. A computer-implemented method for generating a plan for document processing , the method comprising:receiving a plurality of electronic documents, by a computer using a network;analyzing one of the received plurality of electronic documents, using the computer, to identify a table containing tabular data;identifying textual data within the identified tabular data, by performing a first natural language search of the identified tabular data;generating textual hints, based on the identified textual data within the identified tabular data;identifying references, wherein the references are based on matching textual hints with textual data in non-tabular data of the one analyzed electronic document of the received plurality of electronic documents;calculating a priority score based on a calculated count of references;generating an ordered list of identified references and the associated tabular data, wherein the ordering of the ordered lists is based on generated list of identified references; ...

Interactive information retrieval using knowledge graphs

A method includes receiving a natural language query at an information system, the natural language query indicating an intent and at least a first factor and a second factor. The method also includes retrieving a set of candidate information from the information system based on the natural language query, the set of candidate information having a type determined by the intent. The method additionally includes selecting a knowledge display template from a set of knowledge display templates using the intent, the first factor and the second factor. The method further includes rendering, using the knowledge display template, a first knowledge graph comprising the set of candidate information, the first knowledge graph indicating a relationship between the set of candidate information based the first factor and the second factor.

IMPLICIT NARRATION FOR AURAL USER INTERFACE

A computing device and a method for controlling narration. The computing device comprises a display device displaying a visual user interface including textual information and an electronic processor configured to map the textual information to an implicit audio narration, wherein mapping textual information to the implicit audio narration has a scalable level of precision to the textual information depending on the visual user interface, and the electronic processor further configured to output the implicit audio narration. 1. A computing device comprising:a visual user interface including textual information and graphical information; and map each field of the textual information of the visual user interface to an implicit audio narration, wherein mapping a field of the textual information to the implicit audio narration has a scalable level of precision based on a context of content in the visual user interface,', 'map the graphical information to the implicit audio narration, wherein mapping the graphical information to the implicit audio narration includes mapping a graphical icon to an application name, and', 'output the implicit audio narration, 'an electronic processor configured to2. The computing device of claim 1 , wherein the electronic processor is further configured toanalyze the visual user interface, anddetermine, for each field of the textual information, the scalable level of precision for mapping the field of the textual information to the implicit audio narration.3. The computing device of claim 1 , wherein the electronic processor is further configured tomap a first field of the textual information including a time-stamp to a first segment of the implicit audio narration, the first segment of the implicit audio narration including a relative indication of a duration associated with the time-stamp with respect to a reference time.4. The computing device of claim 1 , wherein the textual information is selected from a group consisting of an email ...

Systems and methods providing a cognitive augmented memory network

A system to electronically generate original content may include a Cognitive Memory Augmented Network (“CAMN”) that ingests data from structured and unstructured sources and organizes it in a neural network. Generic and/or custom decomposition may ensure that the data sources are broken down inside the CAMN to individual elements of reusable data. A Cognitive Gateway Interface (“CGI”) may make data available inside the CAMN accessible to processes such as cognitive search, content extraction, and/or summarization. A feedback mechanism may ingest human thought and convert the feedback to introduce original content into an output. With an enriched CAMN built upon substantial digital content, the system may learn deep semantic meaning and understanding based on content. The system may create and curate new articles, and an assistant system may work as interpreter of content. The system may help with complex research on advanced topics and provide personalized and/or customized reports.

METHODS FOR INDEXING AND RETRIEVING TEXT

A method for indexing and retrieving text that includes affixing a first text identifier adjacent to a first body of text, the first body of text is included in a physical collection of text, the first text identifier that includes a first iconography; affixing a first page identifier adjacent to a page included in the physical collection of text, the page includes the particular body of text, the first page identifier includes the first iconography; and modifying a list to include a first summary of the first body of text, the list include a table of cells arranged into rows and columns, each of the rows is associated with one of a plurality of iconographies, the plurality of iconographies includes the first iconography, each iconography is associated with one indexing item. 1. A method for indexing and retrieving text , comprising:affixing a first text identifier adjacent to a first body of text, the first body of text is included in a physical collection of text, the first text identifier comprises a first iconography;affixing a first page identifier adjacent to a page included in the physical collection of text, the page includes the particular body of text, the first page identifier comprises the first iconography; andmodifying a list to comprise a first summary of the first body of text, the list comprises a table of cells arranged into rows and columns, each of the rows is associated with one of a plurality of iconographies, the plurality of iconographies comprise the first iconography, each iconography is associated with one indexing item.2. The method of claim 1 , further comprising:affixing a second text identifier adjacent to a second body of text, the second body of text included in the physical collection of text, the second text identifier comprises a second iconography;affixing a second page identifier adjacent to a second page included in the physical collection of text, the second page includes the second body of text, the second page identifier ...

Method and System for Refactoring Document Content and Deriving Relationships Therefrom

A method and system for refactoring document content and deriving relationships therefrom are described. For each page of a document to be processed, a processing engine processes a page of the document to create a summary and metadata relating to the page, determines a keyphrase relating to the summary, generates links to other content based on the keyphrase, and stores the summary, the keyphrase, the links, and the metadata. A search engine processes a search term, retrieves a page of a document containing the search term, and returns only the page that contains the search term and not the entire document that contains the search term.

Legal timeline analytics

Various of the disclosed embodiments concern systems and methods for applying legal analytics. In some embodiments, a legal analytics platform retrieves legal data from an electronic database, analyzes some or all of the legal data, and identifies interesting patterns and results of statistical analyses. In order to permit searching of the legal data, metadata elements or tags can be generated for legal entities and legal events. In some embodiments, the legal analytics platform identifies timestamps in the legal data and performs time-based statistical analysis. Results of the statistical analyses can be presented to a user via a graphical user interface (GUI), which may also allow the user to interact with the legal analytics platform and search one or more databases of legal data.

Method and system for performing summarization of text

In an embodiment, a method of performing summarization of text is disclosed. The method may include receiving an input text including a plurality of paragraphs and a user-query including one or more tokens. The method may further include segregating the input text into the plurality of paragraphs, creating a plurality of paragraph-vectors representative of the plurality of paragraphs, and clustering the plurality of paragraph-vectors to generate one or more clusters of paragraph-vectors. The method may further include determining a relevant cluster of paragraph-vectors from the one or more clusters of paragraph-vectors, based on a degree of similarity of each cluster of paragraph-vectors with the user-query. The relevant cluster of paragraph-vectors is representative of a set of relevant paragraphs from the input text. The set of relevant paragraphs corresponding to the relevant cluster of paragraph-vectors may be outputted.

Optimized summarizing method and system utilizing fact checking

An optimized fact checking system analyzes and determines the factual accuracy of information and/or characterizes the information by comparing the information with source information. The optimized fact checking system automatically monitors information, processes the information, fact checks the information in an optimized manner and/or provides a status of the information. In some embodiments, the optimized fact checking system generates, aggregates, and/or summarizes content.

Optimized summarizing and fact checking method and system

An optimized fact checking system analyzes and determines the factual accuracy of information and/or characterizes the information by comparing the information with source information. The optimized fact checking system automatically monitors information, processes the information, fact checks the information in an optimized manner and/or provides a status of the information. In some embodiments, the optimized fact checking system generates, aggregates, and/or summarizes content.

System and method to minimally reduce characters in character limiting scenarios

Approaches presented herein enable reduction of characters in a character-limited scenario by minimally editing a text to remain within a character limit while maintaining a tone of a user's writing. More specifically, as a user enters text into a character-limited field, character reduction opportunities for shortening words or phrases are identified in the text. These identified opportunities for shortening words or phrases are compared with a historical writing tone profile of the user in order to preserve a tone and style of the user. Words or phrases that are presented and implemented to shorten the text entered by the user are only sufficient to bring a character count of the entered text within the character limit of the character-limited field. Once the text is within the character limit, no further character reduction is applied.

Readability awareness in natural language processing systems

Electronic natural language processing in a natural language processing (NLP) system, such as a Question-Answering (QA) system. A receives electronic text input, in question form, and determines a readability level indicator in the question. The readability level indicator includes at least a grammatical error, a slang term, and a misspelling type. The computer determines a readability level for the electronic text input based on the readability level indicator, and retrieves candidate answers based on the readability level.

EXTRACTIVE QUERY-FOCUSED MULTI-DOCUMENT SUMMARIZATION

A method, computer system, and computer program product for generating a multi-document summary is provided. The embodiment may include receiving a query statement, one or more documents, one or more summary constraints, and quality goals. The embodiment may include identifying one or more keywords within the query statement. The embodiment may include performing a sentence selection from the one or more documents based on the one or more identified keywords. The embodiment may include generating a plurality of candidate summaries of the one or more documents based on the performed sentence selection, the goals, and a cross entropy method. The embodiment may include calculating a quality score for each of the plurality of generated candidate summaries using a plurality of quality features. The embodiment may include selecting a candidate summary from the plurality of generated candidate summaries with the highest calculated quality score that also satisfies a quality score threshold. 1. A processor-implemented method for generating a multi-document summary , the method comprising:performing a sentence selection from one or more documents based on one or more keywords within a query statement;generating a plurality of candidate summaries of the one or more documents based on the performed sentence selection, one or more goals, and a fully-polynomial randomized approximation scheme (FPRAS) cross entropy method;calculating a quality score for each of the plurality of generated candidate summaries using a plurality of quality features; andselecting a candidate summary from the plurality of generated candidate summaries with the highest calculated quality score that also satisfies a quality score threshold.2. The method of claim 1 , further comprising:generating an expanded query statement using a plurality of query expansion techniques, wherein the expanded query statement comprises the one or more identified keywords and one or more other keywords related to the ...

Method and system for generating a summary of the digital content

There is provided a method and a system for generating a summary of digital content. The method comprises: executing a syntax analysis of a textual representation of the digital content; segmenting the digital content into an ordered set of fragments (i.e. a first fragment and a second fragment); executing a semantic analysis of each fragment of the textual representation; determining a utility parameter for each fragment of the set of fragments; determining a linkage between each pair of fragments of the set of fragments; in response to the utility parameter of the second fragment exceeding a pre-determined threshold value, including the second fragment in a subset of fragments for inclusion in the summary of the digital content; in response to the linkage having been determined between the second fragment and the first fragment, including the first fragment in the subset of fragments; and generating the summary of the digital content.

RELATION EXTRACTION ACROSS SENTENCE BOUNDARIES

Systems, methods, and computer-readable media for providing entity relation extraction across sentences in a document using distant supervision. In some examples, a computing device can receive an input, such as a document comprising a plurality of sentences. The computing device can identify syntactic and/or semantic links between words in a sentence and/or between words in different sentences, and extract relationships between entities throughout the document. Techniques and technologies described herein populate a knowledge base (e.g., a table, chart, database etc.) of entity relations based on the extracted relationships. An output of the populated knowledge base can be used by a classifier to identify additional relationships between entities in various documents. Example techniques described herein can apply machine learning to train the classifier to predict relations between entities. The classifier can be trained using known entity relations, syntactic links and/or semantic links. 1. A system comprising:one or more processors; processing at least two sentences;', 'determining a plurality of inter-sentential paths between a first entity in a first sentence of the at least two sentences and a second entity in a second sentence of the at least two sentences;', 'applying a classifier to each inter-sentential path;', 'identifying, for each inter-sentential path, a relation between the first entity and the second entity based on the inter-sentential path; and', 'identifying, from the plurality of inter-sentential paths, a shortest distance path between the first entity and the second entity, 'a computer storage media including instructions for a relation extraction framework, that, when executed by the one or more processors, cause the relation extraction framework to perform operations comprising2. The system as recites claim 1 , the operations further comprising:receiving a training document comprising at least two related entities; andtraining one or more ...

Search Engine UI systems and processes

The present disclosure relates to UI systems and processes including methods for displaying on a computer display information about electronic documents matching selection criteria. Summary information may appear in representative bubbles that can be smoothly panned and zoomed, with amounts of detail changing in proportion to the size of the bubbles. In a small size, an image extracted from the document, if any, may be displayed. In one size, keywords identified by NLP and NER algorithms can be added. In another size, a document summary can be shown. In another size, a full-text view a scrollable widow or iframe displays the document within the bubble. Bubbles may be clumped by various criteria including topic, age, popularity, and so on. Bubbles may use colors to indicate topic, age, language, or document source. User-viewed bubbles may be deemphasized after the user has view them. 1. A method for displaying on a computer display information about electronic documents matching selection criteria and supporting user interaction therewith , the method comprising steps executed on one or more computer processors of:running each electronic document through a Natural Language Processing module to tokenize text of the electronic document and assign part-of-speech tags and named entity tags to said tokenized text;running each electronic document's tokenized text, part-of-speech tags, and named entity tags through a summarization algorithm to create a summarization of the electronic document;computing a current bubble size for each electronic document based on, at least in part, a relevancy score for the electronic document; andrendering on the computer display, for each electronic document, a summary of the electronic document in a contiguous bubble region sized proportionately to the electronic document's current bubble size, said summary comprising an image extracted from the electronic document, if any, and, according to threshold criteria: keywords selected from the ...

Organizing and aggregating meetings into threaded representations

One embodiment of the present invention sets forth a technique for organizing meeting content. The technique includes generating, from a set of available meetings, a thread comprising a collection of related meetings that share one or more attributes. The technique also includes aggregating data for the related meetings, where the data comprises metadata for the related meetings and terms included in recordings of the related meetings. The technique further includes outputting at least a portion of the aggregated data within a summary of the thread.

Method and apparatus for 3d display and analysis of disparate data

The system provides a method and apparatus for sorting and displaying collections of communications. These communications can be a single type or multiple types of data and may come from email systems, bulletin boards, text messages, Facebook and Twitter postings and comments, financial transactions, travel itineraries or any other type of communications. The communications represented by the system can be electronic or physical as desired. The system can also present forwarded, copied, replied, or other types of communications. In one embodiment, the system provides a Universe View of a set of communications. The Universe View, in one embodiment, is a three dimensional representation of a plurality of cubes. Each cube represents a subset of a collection of communications. Each cube can be color coded or shaded to represent a dominant theme of the contents of the communications represented by the cube.

CREATION OF A SUMMARY FOR A PLURALITY OF TEXTS

Creating a summary of a plurality of texts includes tokenizing each of a plurality of texts to obtain tokens; generating a vector space using a first set of vectors having one or more obtained feature scores equal to or larger than a predefined value; executing non-hierarchical clustering using the vector space to generate a first plurality of clusters; choosing a first representative text in each of the plurality of clusters; generating a second set of vectors from each of the arrays generated based on a number of characters included in tokens of the representative texts; executing hierarchical clustering using the second set of vectors to generate a second plurality of clusters; and in response to a determining a number of clusters included in the second plurality of clusters, determining a second representative text for each of the clusters included in the second plurality of clusters. 1. A computer-implemented method for summarizing a plurality of texts , the method comprising:generating a vector space based on a first set of vectors, wherein each vector includes one or more feature scores determined from tokens of a plurality of texts;determining a number of clusters that will be included in a first plurality of clusters when non-hierarchical clustering generates the first plurality of clusters, wherein the number of clusters that will be generated in the non-hierarchical clustering is determined according to a number of texts included in the plurality of texts;executing the non-hierarchical clustering using the vector space to generate the first plurality of clusters;generating a second set of vectors based on quantities of characters in tokens of first representative texts, wherein each first representative text is selected from a corresponding cluster of the first plurality of clusters, and wherein arrays are generated based on the quantities of characters in the tokens of the first representative texts to generate the second set of vectors when the number ...

Multi-Document Summary Generation Method and Apparatus, and Terminal

A multi-document summary generation method includes obtaining a candidate sentence set, training each candidate sentence in the candidate sentence set using a cascaded attention mechanism and an unsupervised learning model in a preset network model, to obtain importance of each candidate sentence, selecting, based on the importance of each candidate sentence, a phrase that meets a preset condition from the candidate sentence set as a summary phrase set, and obtaining a summary of a plurality of candidate documents based on the summary phrase set. 1. A multi-document summary generation method , comprising:obtaining a plurality of candidate documents about an event, wherein the candidate documents comprise candidate sentences;obtaining a candidate sentence set from the candidate documents, wherein the candidate sentence set comprises a plurality of candidate sentences;processing each of the candidate sentences using a cascaded attention mechanism and an unsupervised learning model in a preset network model to obtain an importance of each of the candidate sentences, wherein an importance of a candidate sentence corresponds to a modulus of a row vector in a cascaded attention mechanism matrix, wherein the preset network model optimizes a reconstruction error function from the unsupervised learning model to output the cascaded attention mechanism matrix, and wherein the importance of the candidate sentence indicates an importance degree of a meaning from the candidate sentence in the candidate documents;selecting, from the candidate sentence set based on the importance of each of the candidate sentences, a phrase that meets a preset condition as a summary phrase set; andobtaining a summary of the candidate documents based on the summary phrase set.2. The multi-document summary generation method of claim 1 , wherein the processing comprises:obtaining, based on the preset network model, m vectors used to describe the event; and executing the unsupervised learning model; ...

METHOD AND APPARATUS FOR BROWSING INFORMATION

Disclosed is a method of generating a multi-level summary of an article. The method may comprise generating, by a computing device, a low-level summary from article-matter in an article. The method may also comprise generating, by the computing device, a mid-level summary based on the low-level summary and the article-matter. The method may also comprise generating, by the computing device, an upper-level summary based on the mid-level summary, the low-level summary, and the article-matter. 1. A method of generating a multi-level summary of an article , the method comprising:generating, by a computing device, a low-level summary from article-matter in an article;generating, by the computing device, a mid-level summary based on the low-level summary and the article-matter; andgenerating, by the computing device, an upper-level summary based on the mid-level summary, the low-level summary, and the article-matter.24.-. (canceled) This application claims the benefit of and priority to U.S. Provisional Patent Application No. 61/829,757, filed May 31, 2013, which is incorporated herein by reference. This application also claims the benefit of and priority to U.S. Provisional Patent Application No. 61/892,701, filed Oct. 18, 2013, which is incorporated herein by reference.Disclosed is a method of browsing in text, graphics, tables, pictures, mathematical expressions, graphs, slide-shows, videos etc. using apparatus such as computer systems, tablets, smartphones etc. The current art browsing methods have adopted from the print medium, but there has been no significant innovation to capitalize on the groundbreaking advantages offered by computer systems for many decades.In the current interactive computer medium, the typical means of browsing in an article consist of: a table of contents in the beginning of an article or a book; and/or hyperlinks on phrases in the body of the article.A very common example is the table of contents at the start of an article in Wikipedia. Such ...

Method of Summarizing Text with Sentence Extraction

A method for summarizing text with sentence extraction including steps as follows. Sentences are extracted from a document including text by a natural language processing (NLP) based feature extractor. A word vector set with respect to each of the sentences is generated by a processor. The word vector set with respect to each of the sentences is used to generate a n-grams vector set and a phrase-n vector set with respect to each of the sentences. A word score representing similarity between the word vector sets, a n-grams score representing similarity between the n-grams vector sets, and a phrase-n score representing similarity between the phrase-n vector sets are computed. The word, n-grams, and phrase-n scores are combined to compute an edge score. Text features are selected from the sentences using the edge scores of the sentences, so as to output a summary of the document. 1. A method for summarizing text with sentence extraction comprising:extracting a plurality of sentences from a textual document by a natural language processing (NLP) based feature extractor;generating a word vector set with respect to each of the sentences by a processor;using the word vector set with respect to each of the sentences to generate a n-grams vector set and a phrase-n vector set with respect to each of the sentences by the processor, wherein n is a positive integer greater than 1;computing a word score representing similarity between the word vector sets, a n-grams score representing similarity between the n-grams vector sets, and a phrase-n score representing similarity between the phrase-n vector sets by the processor;combining the word score, the n-grams score, and the phrase-n score to compute an edge score representing similarity between the two sentences by the processor;computing a ranking of importance on the sentences using the edge scores of the sentences; andgenerating a summary of the document using a pre-defined number of top importance-ranking sentences.2. The ...

APPARATUS, SYSTEM, AND METHOD OF ASSISTING INFORMATION SHARING, AND RECORDING MEDIUM

A system for assisting sharing of information includes circuitry to: input a plurality of sentences each representing a statement made by one of a plurality of users, the sentence being generated by speaking or writing during a meeting or by extracting from at least one of meeting data, email data, electronic file data, and chat data at any time; determine a statement type of the statement represented by each one of the plurality of sentences, the statement type being one of a plurality of statement types previously determined; select, from among the plurality of sentences being input, one or more sentences each representing a statement of a specific statement type of the plurality of types; and output a list of the selected one or more sentences as key statements of the plurality of sentences. 1 receive communication data of a plurality of users;', 'calculate, using the received communication data, a relationship strength between at least a first user and a second user of the plurality of users; and, 'circuitry configured to'}cause a display to display a communication diagram, the communication diagram illustrating the calculated relationship strength between the first user and the second user, the calculated relationship strength between the first user and the second user being expressed as a thickness of a line displayed between a displayed representation of the first user and a displayed representation of the second user.. A system, comprising: This application is a continuation Application of U.S. application Ser. No. 16/796,313, filed Feb. 20, 2020, which is a continuation application Ser. No. 15/606,691, filed May 26, 2017 (now U.S. Pat. No. 10,614,162), which is based on and claims priority pursuant to 35 U.S.C. § 119(a) to Japanese Patent Application No. 2016-106604, filed on May 27, 2016 and 2017-074344, filed on Apr. 4, 2017, in the Japan Patent Office. The entire contents of the above-identified applications are incorporated herein by reference.The ...

Smart Communications Assistant With Audio Interface

Methods, systems, and computer programs are presented for a smart communications assistant with an audio interface. One method includes an operation for getting messages addressed to a user. The messages are from one or more message sources and each message comprising message data that includes text. The method further includes operations for analyzing the message data to determine a meaning of each message, for generating a score for each message based on the respective message data and the meaning of the message, and for generating a textual summary for the messages based on the message scores and the meaning of the messages. A speech summary is created based on the textual summary and the speech summary is then sent to a speaker associated with the user. The audio interface further allows the user to verbally request actions for the messages. 1. A computer implemented method comprising:obtaining by one or more processors, one or more messages from one or more message sources, the one or more messages being addressed to a user, each message comprising message data that includes message text;creating a textual summary for each message in a subset of the one or more messages;creating a speech summary summarizing all messages in the subset based on the textual summary;sending, by the one or more processors, the speech summary to a speaker associated with the user;in response to sending the speech summary, receiving a command from the user to delegate communications for at least one message of the one or more messages to a device having a screen; andinitiating the delegation on behalf of the user.2. The method as recited in claim 1 , wherein the delegation comprises sending the textual summary of the at least one message to the device.3. The method as recited in claim 1 , wherein the delegation comprises sending the at least one message of the one or more messages to the device.4. The method as recited in claim 1 , wherein the speaker belongs to a device without a ...

SUPPLY KNOWLEDGE PORTAL SYSTEMS AND METHODS

Systems and methods are provided for a supply knowledge portal. The supply knowledge portal provides a new metric dashboard that delivers real-time information on the status and health of the hospital supply chain. The new dashboard is driven by the transactional data generated from system point of use devices and allows end users to view data at various levels starting at the facility level and moving down to filter for specific areas, devices and, at the lowest level, items. 1. A system , comprisinga database server;one or more point-of-use devices in a hospital supply chain, each configured to provide controlled access to medical items and to provide information associated with the medical items to the database server via a network,wherein the database server comprises a memory that stores at least one metric value for a plurality of metrics for the hospital supply chain, wherein the at least one metric value for each metric is generated, based on at least a portion of the information associated with the medical items, at a corresponding partition of an analysis database of the database server; anda web server configured to facilitate user access to the stored metric values via a metric dashboard of a user interface.2. The system of claim 1 , wherein the metric dashboard includes a displayed metric value for each of a plurality of categories claim 1 , and provides clickable access to additional metric values in each category.3. The system of claim 2 , wherein the plurality of categories comprise an inventory category claim 2 , a compliance category claim 2 , a discrepancy category claim 2 , and an opportunity category.4. The system of claim 3 , wherein the displayed metric value for the inventory category comprises at least one of a month-to-date daily average value claim 3 , an area filter value claim 3 , a monthly trend value claim 3 , a daily trend value claim 3 , a station detail value claim 3 , or an item detail value.5. The system of claim 4 , wherein the ...

PERSONALIZED MEETING SUMMARIES

A method, a computer program product, and a computer system generate personalized meeting summaries. The method includes identifying a participant attending a meeting associated with a purpose. The method includes determining role information of the participant. The role information indicates a role type that the participant provides toward the purpose. The method includes monitoring discussions of the meeting. The method includes generating a personalized meeting summary for the participant. The personalized meeting summary includes a summary section describing portions of the discussions that are directed to the role type of the participant. 1. A computer-implemented method for generating personalized meeting summaries , the method comprising:identifying a participant attending a meeting associated with a purpose;determining role information of the participant, the role information indicating a role type that the participant provides toward the purpose;monitoring discussions of the meeting;generating a personalized meeting summary for the participant, the personalized meeting summary including a summary section describing portions of the discussions that are directed to the role type of the participant; andtransmitting the personalized meeting summary for viewing by the participant.2. The computer-implemented method of claim 1 , wherein the role information further indicates role interests claim 1 , the role interests being linked toward tasks to be completed by the participant as the role type.3. The computer-implemented method of claim 2 , wherein the summary section includes further portions of the discussions that are directed to the role interests.4. The computer-implemented method of claim 1 , wherein the personalized meeting summary further includes a missed section describing portions of the discussions taking place at durations that the participant was absent.5. The computer-implemented method of claim 1 , further comprising:determining tasks arising from ...

User-Focused, Ontological, Automatic Text Summarization

The present disclosure is directed to systems and methods of providing systems and methods of autonomously generating summary documents based, at least in part, on a plurality of queries provided by a system user. The systems and methods disclosed herein include processor circuitry to identify a plurality of information sources for a specific topic guided by an ontology with specific concepts and relations. The systems and methods disclosed herein also include processor circuitry to generate user-focused extractive text summarization from each of at least some of the plurality of identified information sources using a plurality of queries supplied by the user/researcher.

CONTENT MANAGEMENT SYSTEMS PROVIDING AUTOMATED GENERATION OF CONTENT SUMMARIES

Systems for generating content summaries in a web content management service, wherein in one embodiment a digital page editor and a component browser are launched to enable selection of a first content item. A summary of the first content item is automatically generated according to parameters that may have default values or values set by a user. The parameters may specify a size for the summary as a percentage of the first content item's size, as a particular number of lines, characters or words, as a size for a particular type of device, etc. The automatically generated summary is provided to the digital page editor, which can edit it and add it to the digital page. The summary is stored in a content repository as an independent summary content item with its own metadata.

Generating question and answer pairs to assess understanding of key concepts in social learning playlist

A method, system and computer program product for determining whether the social learning playlist is effective in educating participants. The text of the collection of online materials of a social learning playlist is scanned to identify key concepts (i.e., the most important points) using natural language processing. The user selects a concept from a list of key concepts, which includes these identified key concepts, and a type of question (e.g., true/false) to be used in assessing the understanding of the selected key concept. The selected type of question and answer to the question are generated using analytic analysis and artificial intelligence on the online materials of the playlist. In this manner, by generating appropriate question and answer pairs, where the questions are inserted at selected locations within the playlist, the creator of the playlist is able to assess whether the participants are understanding the key concepts in the playlist.

ARRANGEMENTS OF DOCUMENTS IN A DOCUMENT FEED

Some embodiments provide a GUI for a document reader application that displays a selectable representation of content that, when selected, cause the content to be displayed in the GUI. GUI controls may be exposed in response to a user input slide operation on the selectable representation of content. 1. A tangible , non-transitory , computer-readable medium , comprising computer-readable instructions that , when executed by one or more processors of a computer , cause the computer to:render a graphical user interface (GUI) comprising a first selectable representation of first content, that upon selection, causes the first content, which is associated with the first selectable representation, to be presented in the GUI;receive a user input, the user input comprising a slide operation associated with the first selectable representation;in response to the user input, render, in the GUI, one or more GUI controls in an exposed area of the GUI.2. The computer-readable medium of claim 1 , comprising computer-readable instructions that claim 1 , when executed by the one or more processors claim 1 , cause the computer to:in response to the user input, expose the exposed area, by generating, in the GUI, a slide animation that slides the first selectable representation to a new location.3. The computer-readable medium of claim 2 , wherein the slide animation comprises at least a portion of: the first selectable representation claim 2 , a second selectable representation neighboring the first selectable representation claim 2 , or both sliding out of visibility within the GUI.4. The computer-readable medium of claim 2 , wherein the slide animation comprises sliding the first selectable representation and a neighboring second selectable representation such that one of the first selectable representation or the neighboring second selectable representation appears beneath the other.5. The computer-readable medium of claim 1 , comprising computer-readable instructions that claim 1 ...

SYSTEMS AND METHODS FOR GENERATING SOCIAL ASSETS FROM ELECTRONIC PUBLICATIONS

Systems and techniques are provided for generating a social asset from an electronic publication. The system includes providing a template having a set of reserve spaces for elements. The system receives an electronic publication containing elements including images and text passages. The system assigns images from the publication to each of the reserve spaces for images including assigning a first image from the publication to a first one of the reserve spaces for an image. The system chooses a first one of the text passages for associating with the first image. The system selects a portion of less than all of the first text passage. The system generates a social asset by processing the set of reserve spaces to automatically move forward in an animated manner wherein the selected portion of the first text passage superimposes a portion of the first image. 1. A method of generating a social asset from an electronic publication including images and text passages , the method including:assigning images from the electronic publication to each of a set of reserve spaces for images in a page, including assigning a first image from the publication to a first one of the reserve spaces for an image; calculating distances of each of a plurality of text passages in the electronic publication to the first image;', 'filtering out the text passages in captions of images; and', 'selecting a text passage in the plurality of text passages, excluding filtered out text passages, with a shortest distance to the first image and inferring the association between the selected text passage and the first image;, 'choosing a first one of the text passages for associating with the first image by inferring association in the electronic publication between the first one of the text passages and the first image, includingselecting a portion of the first text passage which is less than all of the first text passage; andgenerating a social asset by processing the set of reserve spaces to ...

Method and system for automatically converting input text into animated video

The present invention provides a system and a method for automatically converting input text into animated video, optionally with a voiceover. Specifically, the present invention programmatically converts the input text, which is in the form of XML, HTML, RTF, or simple word document into an animated video. The animated video is generated via a series of steps, which involve summarizing and processing the text into an intermediate markup, which is then drawn, in the form of an animated whiteboard video including vector images and both spatial (perspective camera movements, zooms and pans) and semantic accentuation (highlighting, variation in speed of animation). Further, the voiceover is included automatically and the voiceover can be modified manually as a summary of the given input text. Furthermore, the generated video can be post processed by varying the time duration, background music, voiceover, splicing of video at specific points and the video can be uploaded or stored in cloud storage or to hard disk.

Virtual sticky generation

Digital programmed logic implemented on a computing device programmed to cause the display of an electronic document on a graphical user interface within the computing device. The electronic document displayed includes a plurality of data items of information. The programmed logic is programmed to automatically generate summary data that summarizes at least two data items from the plurality of data items included in the electronic document. The programmed logic is further programmed to generate a virtual sticky and display the virtual sticky on the electronic document. The virtual sticky displays the automatically generated summary data and the display of the virtual sticky is overlaid onto at least a portion of the display of the electronic document.

Segmentation Discovery, Evaluation and Implementation Platform

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, are described that enable clustering and evaluation of data. A data set is identified for which to evaluate cluster solutions, the data set including a plurality of records each including a plurality of attributes. Different attributes are identified, including target driver attributes, cluster candidate attributes, and profile attributes. One or more clustering algorithms are identified and applied to the data set to generate cluster solutions. Each cluster solution groups records in the data set into different clusters based on the cluster candidate attributes. A score is calculated for each cluster solution based at least on the target driver attributes, the cluster candidate attributes, and the profile attributes. A user interface is generated for presentation to a user showing the generated cluster solution organized according to the calculated score for each cluster solution.

Content summarization and/or recommendation apparatus and method

Embodiments are provided for summarization and recommendation of content. In disclosed embodiments, a summarization engine scores constituent parts of content, and generates a plurality of summaries from a plurality of points of view for the content based at least in part on the scores of constituent parts. The summaries may be formed with constituent parts extracted from the contents. A recommendation engine provides recommendations to a user based on rankings of the summaries generated by the summarization engine. Other embodiments may be described and/or claimed.

Evaluating the Factual Consistency of Abstractive Text Summarization

A weakly-supervised, model-based approach is provided for verifying or checking factual consistency and identifying conflicts between source documents and a generated summary. In some embodiments, an artificially generated training dataset is created by applying rule-based transformations to sentences sampled from one or more unannotated source documents of a dataset. Each of the resulting transformed sentences can be either semantically variant or invariant from the respective original sampled sentence, and labeled accordingly. In some embodiments, the generated training dataset is used to train a factual consistency checking model. The factual consistency checking model can classify whether a corresponding text summary is factually consistent with a source text document, and if so, may identify a span in the source text document that supports the corresponding text summary. 1. A computer-implemented method for verifying factual consistency as between a source text document and a corresponding text summary , the method comprising: receiving a dataset with one or more unannotated source documents, each source document comprising a plurality of sentences;', 'sampling one or more sentences from the one or more unannotated source documents;', performing a transformation to generate a respective novel claim sentence; and', 'labeling the respective novel claim sentence according to whether it is semantically variant or semantically invariant from the sampled sentence;, 'for each sampled sentence], 'providing a factual consistency checking model trained with a training data set, wherein the training data set is generated byreceiving the source text document and the corresponding text summary as input to the trained factual consistency checking model, wherein the corresponding text summary is generated by a text summarization model;classifying by the trained factual consistency checking model whether the corresponding text summary is factually consistent with the source ...

Distributed Transaction Management With Tokens

A system, method and computer product for managing distributed transactions of a database. A transaction manager is provided for each of a plurality of transactions of the database. Each transaction manager is configured to perform functions that include generating a transaction token that specifies data to be visible for a transaction on the database. The database contains both row and column storage engines, and the transaction token includes a transaction identifier (TID) for identifying committed transactions and uncommitted transactions. A last computed transaction is designated with a computed identifier (CID), record-level locking of records of the database is performed using the TID and CID to execute the transaction, and the plurality of transactions of the database are executed with each transaction manager. 1. A computer-implemented method comprising:generating, by a transaction manager, a transaction token specifying that changes to a database by one or more of a plurality of transactions are visible to a transaction of the plurality of transactions associated with the transaction manager and that changes to the database by others of the plurality of transactions are not visible to the transaction associated with the transaction manager; andperforming record-level locking of a first record in a plurality of records of the database using the transaction token to execute the transaction by generating a main/history index of the plurality of records in the database as a persistent data structure, the main/history index having a computed identifier column.2. The computer-implemented method in accordance with claim 1 , wherein the transaction token includes a maximum visible computed identifier for identifying a plurality of committed transactions and a plurality of uncommitted transactions.3. The computer-implemented method in accordance with claim 2 , wherein performing record-level locking of the first record further comprises generating a delta index ...

SYSTEM AND METHOD FOR PROVIDING TECHNOLOGY ASSISTED DATA REVIEW WITH OPTIMIZING FEATURES

Embodiments may provide a document system that receives a responsiveness call from a user through the task/queue framework regarding a machine call document. Theses responsiveness calls may be used to refining the scoring algorithm used by the document system of to generate a desired confidence score for the document system. 1. An electronic document system , comprising:a processor; selecting a control set of documents from a plurality of documents in a data store;', 'presenting the control set of documents to a user;', 'receiving an indicator of responsiveness for each of the documents of the control set of documents;', a) determining a responsiveness score for each of the plurality of documents according to a scoring algorithm including determining a document responsiveness probability for the document, determining a weighted topic score for the document for each of a set of topics in a topic-related generative model based on the document responsiveness probability and a topic-document weight between the topic and the document, generating an initial responsiveness score based on the topic-document weights of the document for each topic and the weighted topic score, and normalizing the document responsiveness probability based on the initial responsiveness score to determine the responsiveness score for the document;', 'b) determining a set of responsive documents of the plurality of documents based on the responsiveness score determined for each of the plurality of documents and the decision boundary score;', 'c) determining a confidence score for the document system using the responsiveness score for each of the documents of the control set and the indicator of responsiveness for each of the control set documents received from the user;', 'd) selecting one or more of the plurality of documents based on the responsiveness scores of the plurality of documents;', 'e) presenting the one or more selected documents to the user;', 'f) receiving the indicator of ...

SUMMARIZATION AND PROCESSING OF EMAIL ON A CLIENT COMPUTING DEVICE BASED ON CONTENT CONTRIBUTION TO AN EMAIL THREAD USING WEIGHTING TECHNIQUES

Systems, methods, and computer-readable media are disclosed for enhancing an email application to automatically analyze an email thread and generate a compact content summary. The content summary is based on relative content contributions provided by the constituent email messages in the email thread. The content summary may be presented in a special window without disturbing or modifying the email thread or its constituent email messages. The distinctive content summary disclosed herein comprises certain sentences that are automatically gleaned from the email thread, analyzed relative to other sentences, and presented in a chronological sequence so that the user can quickly determine what the email thread is about and/or the current status of the conversation. The content summary is based on email weights, word weights, and intersecting sentence pairs. 1. A system for generating a content summary of an email-thread , the system comprising:a computing device comprising one or more processors and computer memory, wherein the computing device executes an email application and is configured to:identify email messages that form the email-thread; (i) an email-weight assigned to each email message in the email-thread,', '(ii) a word-weight assigned to certain words in each email message in the email-thread, and', 'wherein a first sentence and a second sentence in a respective intersecting sentence pair have a set of words in common; and', '(iii) an intersection-score assigned to intersecting sentence pairs found in the email messages in the email-thread,'}], 'generate the content summary of the email-thread, based at least in part on (a) word-weights of the set of words in common belonging to the first sentence, weighted by the email-weight of the email message comprising the first sentence, and', '(b) word-weights of the set of words in common belonging to the second sentence, weighted by the email-weight of the email message comprising the second sentence., 'wherein the ...

System and method of embedding and launching a form from third-party knowledge content

In the field of government engagement management, for users of an employee desktop web client, it is now possible, within the web client application, to search and read articles and/or knowledge content that has been authored to external locations. Due to this integration to external, third-party applications, content and/or articles can be displayed to an agent on the employee desktop web client graphical user interface. Agents can enter free text into a specific search field and review the results in summary form, and then select an article in HTML format to progress the current interaction with the client. An additional feature extending from this capability is to add an amount of coding to external knowledge content websites that are owned and/or operated by the owner of the system such that when the website is viewed through the third-party integration module, a button or icon appears within the website that when selected takes the agent to an appropriate form. This button or icon does not appear when the website is viewed outside of the system. This functionality adds value to the agent experience and enables the agent to provide an improved service to the end client. Results may be filtered by the search engine as well. Moreover, this system and method improves the operation of the computer in that the computer running such a system in the past was not able to integrate in such a fashion in a web client format. This system and method also enables an agent to handle calls with the web client more efficiently, and allows agents on the web client to automatically classify.

System and method for automatically detecting and interactively displaying information about entities, activities, and events from multiple-modality natural language sources

A method for automatically extracting and organizing information by a processing device from a plurality of data sources is provided. A natural language processing information extraction pipeline that includes an automatic detection of entities is applied to the data sources. Information about detected entities is identified by analyzing products of the natural language processing pipeline. Identified information is grouped into equivalence classes containing equivalent information. At least one displayable representation of the equivalence classes is created. An order in which the at least one displayable representation is displayed is computed. A combined representation of the equivalence classes that respects the order in which the displayable representation is displayed is produced.

Text processing apparatus, text processing method, and computer program product

According to an embodiment, a text processing apparatus includes a generator and a list display unit. The generator is configured to generate topic structure information by analyzing input text. The topic structure information includes information that represents a subordinate relation between a plurality of topics included in the text and information that represents a relative positional relation between the topics included in the text. The list display unit is configured to display, on a display, a topic structure list in which a plurality of nodes each corresponding to a topic included in the text and each including a label that represents a subordinate relation between a topic corresponding to each node and another topic are arranged based on the topic structure information in accordance with a relative positional relation between topics corresponding to the respective nodes.

Transformation of Database Entries for Improved Association with Related Content Items

A content analysis system includes processor and memory hardware storing data analyzed content items and instructions for execution by the processor hardware. The instructions include, in response to a first intermediate content item being analyzed to generate a first text description, receiving the first intermediate content item and analyzing the first text description to generate a first reduced text description. The instructions include identifying a first set of tags by applying a tag model to the first text description and generating a first analyzed content item. The instructions include adding the first analyzed content item to the analyzed content database and, in response to a displayed content item being associated with at least one tag of the first set of tags, displaying a first user-selectable link corresponding to the first analyzed content item on a portion of a user interface of a user device displaying the displayed content item.

Natural language processor for providing natural language signals in a natural language output

Embodiments are directed to a natural language processing (NLP) system configured to receive a natural language (NL) input and perform an analysis operation to generate a NL output. The NLP system is configured to generate at least one confidence level based at least in part on at least one portion of the analysis operation. The NLP system is further configured to integrate at least one disfluency into the NL output based at least in part on the at least one confidence level.

Mapping of software code via user interface summarization

Techniques for identifying similar software code are provided. In one example, a computer-implemented method comprises: based on detection of an input, determining, by a device operatively coupled to a processor, a user interface functionality associated with a website; and based on a likelihood that the user interface functionality and a result of a query have a defined level of correlation, matching, by the device, the result of the query to the user interface functionality. The computer-implemented method can further comprise mapping, by the device, a vector associated with the website, to an integer value, employing a hash function.

Techniques for user-centric document summarization

Disclosed techniques can generate content object summaries. Content of a content object can be parsed into a set of word groups. For each word group, at least one topic to which the word group pertains can be identified and it can be determined, via a user model, at least one weight of the plurality of weights corresponding to the topic(s). For each word group, a score can be determined for the word group based on the weight(s). A subset of the set of word groups can be selected based on the scores for the word group. A summary of the content object can be generated that includes the subset but that does not include one or more other word groups in the set of word groups that are not in the subset. At least part of the summary of the content object can be output.

READABILITY AWARENESS IN NATURAL LANGUAGE PROCESSING SYSTEMS

Electronic natural language processing in a natural language processing (NLP) system, such as a Question-Answering (QA) system. A receives electronic text input, in question form, and determines a readability level indicator in the question. The readability level indicator includes at least a grammatical error, a slang term, and a misspelling type. The computer determines a readability level for the electronic text input based on the readability level indicator, and retrieves candidate answers based on the readability level. 1. A method for electronic natural language processing in an electronic natural language processing (NLP) system , comprising:receiving an electronic text input;determining a readability level indicator of the electronic text input, wherein the readability level indicator comprises at least one of a grammatical error, a slang term, and a misspelling type in the electronic text input; anddetermining a readability level of the electronic text input based on the readability level indicator.2. The method of claim 1 , further comprising:receiving the electronic text input from an electronic input source in response to an input from a user.3. The method of claim 1 , further comprising:identifying the electronic text input as a question.4. The method of claim 3 , further comprising:generating a plurality of candidate answers for the question; andselecting a set of candidate answers from among the plurality of candidate answers based on matching readability levels of the set of candidate answers to the readability level of the question.5. The method of claim 1 , further comprising:parsing the electronic text input using a full parsing process.6. The method of claim 1 , further comprising:comparing the readability indicators of the electronic text input with readability indicators of one or more questions in a corpus of questions,wherein determining the readability level for the electronic text input is based on readability levels of the one or more ...

Message providing methods and apparatuses, display control methods and apparatuses, and computer-readable mediums storing computer programs for executing methods

A message providing method includes: extracting a keyword from a message; searching a list of messages to extract a related message associated with the keyword, the messages communicated between a user and a conversational partner or between the user and a third party; and linking the related message to the keyword by a hyperlink.

METHOD, SYSTEM AND APPARATUS FOR PROVIDING A CONTEXTUAL KEYWORD COLLECTIVE FOR COMMUNICATION EVENTS IN A MULTICOMMUNICATION PLATFORM ENVIRONMENT

The invention provides a system, a method and an apparatus for creating and presenting intelligent contextual summary highlighting the essence of previous communication events happening between a user of a wireless communication device and his/her contact. The system captures messages in the communication events; arranges them in chronological order of occurrence; summarizes them into a contextual summary, removing unwanted words; provides weightage to each word in the contextual summary based on number of times each word occurs in the communication events, chronological order of its communication events, and dictionary importance of each word; determining who all other contacts are talking related to topic of contextual summary; and consequently creating the intelligent keyword collective for each contact representing context of the recent conversations with the contact. The system further presents the keyword collective to the user at the communication device, on occurrence of one or more triggering events. 2. The system as claimed in claim 1 , wherein the communication information is created by capturing conversations between the user and the one or more contacts of the contact list and gathering information claim 1 , related to the user claim 1 , from the one or more web-based servers and gathering information from one or more events stored in a calendar at the user device.3. The system as claimed in claim 1 , wherein the summarization module further clears redundant unimportant non-contextual words referred to as ‘stop words’ from the summarized gist claim 1 , the stop words include ‘is’ claim 1 , ‘a’ claim 1 , ‘an’ claim 1 , ‘the’ and other non-contextual words.4. The system as claimed in claim 1 , wherein the context generation module determines the contextual meaning of each word in the summarized gist based on an NER method (Name claim 1 , Entity claim 1 , Recognition) in which the contextual meaning recognizes and tells whether the word is a person claim 1 ...

METHOD AND SYSTEM FOR ANALYZING ENTITIES

A recurrent neural network (RNN) method implemented on a computer system is used to produce summaries of unstructured text generated by multiple networks of individuals interacting over time by encoding the unstructured text into intermediate representations and decoding the intermediate representations into summaries of each network. Parameter data for the RNN is obtained by using multiple different versions of the same source texts to train the computer system. The method and computer system can be used to identify which of the networks match a query by determining which network generates the query with low or lowest cost. 119-. (canceled)20. An improved computational method of identifying which corpus of interaction data best matches a query , comprising:providing two or more corpuses of interaction data, wherein a corpus of interaction data comprises a corpus of event data generated by interactions over time; one or more processors coupled to non-transitory data storage media, wherein the data storage media comprises trained parameter data, and', 'wherein the data storage media further comprises object translator computer instructions which, when executed by the one or more processors, cause the object translator computer system to perform a recurrent neural network method using the trained parameter data to create a summary of a corpus of interaction data, and', encoder computer instructions to encode a corpus of interaction data into an intermediate representation of interaction data and to store the intermediate representation of interaction data in the data storage media, wherein said intermediate representation of interaction data comprises a numeric representation in a high-dimensional space, and', 'decoder computer instructions to decode the intermediate representation of interaction data into a summary;, 'wherein the object translator computer instructions further comprise], 'providing an object translator computer system comprisingfor each of the two or ...

AUTOMATIC GENERATION OF PRESENTATION SLIDES FROM DOCUMENTS

Systems and methods for creating presentation slides. A slide title is received and portions of source documents relevant to the title are identified based on a dense vector information retrieval machine learning process. An abstractive summary of the portions is generated based on a long form question answering machine learning process. A first presentation slide is created with the abstractive summary and the title. The first presentation slide is presented to an operator and an input indicating one of accepting or rejection the abstractive summary is received. Based on the input that indicating rejecting the abstractive summary, the abstractive summary is removed from the presentation slide and negative training feedback for the abstractive summary is provided to at least one of the dense vector information retrieval machine learning process or the long form question answering machine learning process. 1. A method for creating presentation slides , the method comprising:receiving a title for a presentation slide;identifying portions of at least one source document that are relevant to a meaning of the title based on a dense vector information retrieval machine learning process operating on the at least one source document;generating an abstractive summary of the portions of the at least one source document based on a long form question answering machine learning process;creating a first presentation slide comprising the abstractive summary and the title;presenting the first presentation slide to an operator;receiving, based on presenting the abstractive summary, an input indicating rejection of the abstractive summary; and removing the abstractive summary from the presentation slide, and', 'providing negative training feedback for the abstractive summary to at least one of the dense vector information retrieval machine learning process or the long form question answering machine learning process., 'based on receiving the input that indicates rejection of the ...

HANDWRITING TEXT SUMMARIZATION

The present disclosure relates to a computer-implemented method for handwriting-to-text-summarization, comprising obtaining, via a user interface of a system, a handwriting input representing a handwriting of a user of the system for handwriting-to-text-summarization, recognizing a text in the handwriting input, extracting at least one dynamic feature of the handwriting from the handwriting input, generating a text summary of the text, wherein generating the text summary is based on the text and on the at least one dynamic feature of the handwriting. The present disclosure also relates to a system for handwriting-to-text-summarization, comprising a user interface comprising a capturing subsystem configured to capture a handwriting of a user of the system, and wherein the system is configured to run the method for handwriting-to-text-summarization. 1. A computer-implemented method for handwriting-to-text-summarization , comprising:obtaining, via a user interface of a system, a handwriting input representing a handwriting of a user of the system for the handwriting-to-text-summarization;recognizing a text in the handwriting input;extracting at least one dynamic feature of the handwriting from the handwriting input; andgenerating a text summary of the text,wherein generating the text summary is based on the text and on the at least one dynamic feature of the handwriting.2. The computer-implemented method of claim 1 , wherein the at least one dynamic feature comprises an average writing pressure claim 1 , an average stroke length claim 1 , an average stroke duration claim 1 , or a combination thereof claim 1 , and wherein averaging is over the text or portions thereof.3. The computer-implemented method of claim 1 , wherein the handwriting input comprises a first set of data representing the text.4. The computer-implemented method of claim 1 , wherein the handwriting input comprises a second set of data representing properties of the handwriting that indicate information ...

SNIPPET GENERATION AND ITEM DESCRIPTION SUMMARIZER

In various example embodiments, a system and method for a Target Language Engine are presented. The Target Language Engine augments a synonym list in a base dictionary of a target language with one or more historical search queries previously submitted to search one or more listings in listing data. The Target Language Engine identifies a compound word and a plurality of words present in the listing data that have a common meaning in the target language. Each word from the plurality of words is present in the compound word. The Target Language Engine causes a database to create an associative link between the portion of text and a word selected from at least one of the synonym list or the plurality of words. 1a processor;a memory device holding an instruction set executable on the processor to cause the computer system to perform operations comprising:augmenting a synonym list in a base dictionary of a target language with a historical search query previously submitted to search one or more listings in listing data;identifying a compound word and a plurality of words present in the listing data that have a common meaning in the target language, each word from the plurality of words being present in the compound word; andcausing a database to create an associative link between the portion of text and a word selected from at least one of the synonym list or the plurality of words.. A computer system comprising: This Application is a continuation of U.S. application Ser. No. 15/237,091, filed Aug. 15, 2016, which is hereby incorporated by reference in its entirety.The subject matter disclosed herein generally relates to the technical field of special-purpose machines that facilitate augmenting a base dictionary and identifying a plurality of words that share a meaning with a compound word, including software-configured computerized variants of such special-purpose machines and improvements to such variants, and to the technologies by which such special-purpose machines ...

UNSUPERVISED ATTENTION BASED SCIENTIFIC DOCUMENT SUMMARIZATION

Embodiments may provide automated summarization of documents, such as scientific documents by using a prior distribution on logical sections learnt from a corpus of human authored summaries. For example, a method of document summarization may comprise receiving, at the computer system, a document and segmenting the document into a plurality of sentences, identifying, at the computer system, sections in the document and aligning each sentence in the document to a section logical role, and summarizing, at the computer system, the document using a probability distribution. 1. A method of document summarization , implemented in a computer comprising a processor , memory accessible by the processor , and computer program instructions stored in the memory and executable by the processor , the method comprising:receiving, at the computer system, a document and segmenting the document into a plurality of sentences;identifying, at the computer system, sections in the document and aligning each sentence in the document to a section logical role; andsummarizing, at the computer system, the document using a probability distribution;wherein the probability distribution is generated by:receiving, at the computer system, a plurality of documents and segmenting the plurality of documents into a plurality of sentences;identifying, at the computer system, sections in the plurality of documents and aligning document sentences to similar sentences in a plurality of summaries, wherein each summary sentence is aligned to one document sentence; andgenerating, at the computer system, a probability distribution of summary sentences over section logical roles; andwherein the probability distribution of summary sentences over section logical roles comprises a prior probability distribution representing an average length of text in human authored summaries that is devoted to each role.24-. (canceled)5. The method of claim 1 , wherein summarizing the document using the probability distribution ...

Method and system for mobile device transition to summary mode of operation

A method for providing a summary mode on an electronic personal display is provided. The method includes receiving a request to enter a summary mode from a user, accessing a reading history related to the user and directing the electronic personal display to open a summary of the reading history related to the user when initiating the summary mode.

Dynamically managing figments in social media

Systems and methods for dynamically managing figments are disclosed. A computer-implemented method includes: receiving, by a computing device, a question from a user; answering, by the computing device, the question using a first degree figment; classifying, by the computing device, the question based on topics; forwarding, by the computing device, the question to a set of second degree figments; receiving, by the computing device, answers to the question from the set of second degree figments; ranking, by the computing device, the answers received from the set of second degree figments; and providing, by the computing device, the ranked answers to the user.

METHODS AND SYSTEMS FOR TEXT SUMMARIZATION USING GRAPH CENTRALITY

A method for summarizing text is disclosed. The method can include a step of generating a connected network graph based on multiple portions of the text, wherein each portion of the text is a node of the network graph. The method can include a step of determining a similarity score of the multiple nodes of the network graph, wherein the similarity score of each node is based on its similarity with other nodes of the network graph. The method can include a step of measuring a centrality of each node of the network graph using graph centrality that is based on the similarity score and ranking the nodes based on the measured centrality. The method can include a step of generating a summary of the text by using one or more top ranked nodes. 1. A computer-implemented method for summarizing text using graph centrality , the method comprising:generating a connected network graph based on multiple portions of the text, wherein each portion of the text is a node of the network graph;determining a similarity score of the multiple nodes of the network graph, wherein the similarity score of each node is based on its similarity with other nodes of the network graph;measuring a centrality of each node of the network graph using graph centrality that is based on the similarity score and ranking the nodes based on the centrality; andgenerating a summary of the text by using one or more top ranked nodes.2. The method of claim 1 , wherein the portion of the text is a sentence.3. The method of claim 1 , comprising:pruning the network graph by removing one or more connections between the nodes that have a similarity score less than a predetermined threshold before ranking the nodes.4. The method of claim 1 , wherein the determining of the similarity score is based on a machine learning model.5. The method of claim 4 , wherein the machine learning model is a bag of words model claim 4 , a Bidirectional Encoder Representations from Transformers (BERT) model claim 4 , or a WordNet model.6 ...

Systems and methods for query-focused summarization

Embodiments described herein provide a query-focused summarization model that employs a single or dual encoder model. A two-step approach may be adopted that first extracts parts of the source document and then synthesizes the extracted segments into a final summary. In another embodiment, an end-to-end approach may be adopted that splits the source document into overlapping segments, and then concatenates encodings into a single embedding sequence for the decoder to output a summary.

Methods and systems for automatically generating reports from search results

A method for generating a document summary includes identifying, in a document, a plurality of candidate summary sentences satisfying predefined criteria; determining at least one content feature of the document; generating a graph of relationships among the plurality of sentences; ordering the plurality of sentences based on at least one relationship involving a respective sentence; and generating a document summary from the ordered sentences, the document summary including the sentences most related to other sentences. A method for generating a search report summary includes generating a meta-document from a plurality of document summaries; determining at least one content feature of the meta-document; generating a graph of relationships among the meta-document sentences; ordering the meta-document sentences based on at least one relationship involving a respective meta-document sentence; and generating a meta-document summary from the ordered meta-document sentences, the meta-document summary including the meta-document sentences most related to other meta-document sentences.

Display apparatus and method for summarizing of document

A display apparatus including a communicator configured to perform data communication with a content server and to receive at least one of a main document and a sub document related to the main document; a document analyzer configured to extract a keyword having a high frequency of occurrence from the main document and to determine a head keyword for generating a summarized document from the extracted keyword with reference to the received sub document; and a processor configured to determine a reliability of each sentence of the main document based on the head keyword, extract a sentence that matches a predetermined condition with reference to the determined reliability, and analyze a structural format of the extracted sentence so as to re-configure a word that forms the sentence and generate a summarized sentence, thereby generating a summarized document where information and logical cohesion have been obtained.