Natural Language Patents (Class 704/9)
  • Patent number: 10289676
    Abstract: The present invention relates to the field of computer-based semantic understanding. Specifically, it relates to a method for semantic analysis of a natural-language text by data-processing means with a view to the classification thereof.
    Type: Grant
    Filed: January 28, 2015
    Date of Patent: May 14, 2019
    Assignee: DEADIA
    Inventor: Jean-Pierre Malle
  • Patent number: 10291774
    Abstract: A method for determining a spam caller phone number is disclosed. The method may include obtaining N suspicious numbers in a call record set, wherein the N suspicious numbers are first N unknown numbers in a predetermined number of target call records that have the highest frequencies of appearance, determining whether a spam caller feature word recorded in a preset dictionary exists in keywords contained in a target call record of each suspicious number, and if a spam caller feature word recorded in the preset dictionary exists in keywords contained in the target call record of a suspicious number, determining the suspicious number to be a spam caller phone number.
    Type: Grant
    Filed: June 16, 2016
    Date of Patent: May 14, 2019
    Assignee: Xiaomi Inc.
    Inventors: Qiuping Qin, Zhijun Chen, Fei Long
  • Patent number: 10289731
    Abstract: A mechanism is provided in a data processing system for aggregating sentiment about an entity from a corpus of documents. The mechanism identifies a plurality of sentiment passages in the corpus of documents. Each of the plurality of sentiment passages includes a statement of sentiment about the entity. The mechanism determines a plurality of passage sentiment scores for the plurality of sentiment passages and an actual aggregate sentiment score from the plurality of passage sentiment scores based on a k-valued model. The mechanism determines a sentiment confidence score for the actual aggregate sentiment score based on the raw aggregate sentiment score and the actual aggregate sentiment score and presents the actual aggregate sentiment score and the sentiment confidence score.
    Type: Grant
    Filed: August 17, 2015
    Date of Patent: May 14, 2019
    Assignee: International Business Machines Corporation
    Inventors: John M. Boyer, Scott N. Gerard, Srikanth G. Tamilselvam
  • Patent number: 10289717
    Abstract: Disclosed are an apparatus and a method of searching for information by a mobile device. The present invention provides simplified ontology to be applicable to a mobile environment having a limited resource, and provides ontology capable of providing a combined search environment by combining DBs used by various applications within a mobile device, respectively. Further, the present invention provides a semantic search engine providing a function of searching a local database within a mobile device, and expanding a search to a web as necessary and performing the search.
    Type: Grant
    Filed: February 4, 2016
    Date of Patent: May 14, 2019
    Assignee: INDUSTRY-ACADEMIC COOPERATION FOUNDATION, YONSEI UNIVERSITY
    Inventors: Kyong Ho Lee, Min Jae Song, Sang Jin Shin, Sung Kwang Eom
  • Patent number: 10289952
    Abstract: A computer-implemented technique can include receiving, at a server, labeled training data including a plurality of groups of words, each group of words having a predicate word, each word having generic word embeddings. The technique can include extracting, at the server, the plurality of groups of words in a syntactic context of their predicate words. The technique can include concatenating, at the server, the generic word embeddings to create a high dimensional vector space representing features for each word. The technique can include obtaining, at the server, a model having a learned mapping from the high dimensional vector space to a low dimensional vector space and learned embeddings for each possible semantic frame in the low dimensional vector space. The technique can also include outputting, by the server, the model for storage, the model being configured to identify a specific semantic frame for an input.
    Type: Grant
    Filed: January 28, 2016
    Date of Patent: May 14, 2019
    Assignee: Google LLC
    Inventors: Dipanjan Das, Kuzman Ganchev, Jason Weston, Karl Moritz Hermann
  • Patent number: 10292045
    Abstract: An information obtaining method, executable by a processor of an over the top (OTT) for interacting with a mobile terminal and displaying notification information on a display interface. The method includes: receiving a first ID recognizing frequency from mobile terminal, sending first confirming information to the mobile terminal according to the first ID recognizing frequency, receiving an information category frequency sent by the mobile terminal according to the first ID recognizing frequency, and displaying the notification information corresponding to the information category frequency on the display interface.
    Type: Grant
    Filed: August 24, 2017
    Date of Patent: May 14, 2019
    Assignee: NANNING FUGUI PRECISION INDUSTRIAL CO., LTD.
    Inventor: Yuan-Tao Liang
  • Patent number: 10282356
    Abstract: A method for evaluating annotation quality is provided. The method may include obtaining annotation information associated with a plurality of annotators and a plurality of data elements including a plurality of annotation entries corresponding to at least one data element and entered based on an annotation guideline, determining a quality rating for the annotation guideline based on a comparison between a first value associated with the plurality of annotators and the plurality of data elements and a second value associated with any disparity among the plurality of annotation entries, determining a proficiency rating for an annotator from the plurality of annotators based on a comparison between a third value associated with annotation entries by the annotator and the second value, and generating a report based on the quality rating and the proficiency rating.
    Type: Grant
    Filed: March 7, 2016
    Date of Patent: May 7, 2019
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Masaki Komedani, Ken Kumagai, Takuma Murakami, Akihiro Nakayama
  • Patent number: 10282771
    Abstract: Systems and methods for programmatically classifying text are discussed herein. Some embodiments may provide for a system including circuitry configured to programmatically classify a block of text. For example, the circuitry may be configured to identify topics associated with the block of text and identify one or more categories for each of the topics. The circuitry may be further configured to determine unique categories across the one or more categories for each of the topics. For each unique category, an actual category frequency may be determined based on a number of times each of the topics in the block of text is associated with the unique category. The circuitry may be further configured to associate a unique category with the block of text based on the actual category frequency for each the unique category and one or more other actual category frequencies for one or more other unique categories.
    Type: Grant
    Filed: June 5, 2017
    Date of Patent: May 7, 2019
    Assignee: Nook Digital, LLC
    Inventors: Michael Jason Welch, Aditya Vailaya, Ralph Rizkallah Rabbat, Jiang Wu
  • Patent number: 10282416
    Abstract: The present disclosure generally relates to integrated text conversion and prediction. In an example process, a current character input of a first writing system is received. A first current character context in the first writing system is determined based on the current character input and a first previous character context in the first writing system. A second current character context in a second writing system is determined based on the first current character context, a second previous character context in the second writing system, and a character representation in the second writing system. A current word context in the second writing system is determined based on the second current character context, a previous word context in the second writing system, and a word representation in the second writing system. Based on the current word context, a probability distribution over a word inventory in the second writing system is determined.
    Type: Grant
    Filed: August 10, 2017
    Date of Patent: May 7, 2019
    Assignee: Apple Inc.
    Inventors: Jerome R. Bellegarda, Jannes G. Dolfing, Xin Wang
  • Patent number: 10282419
    Abstract: An arrangement and corresponding method are described for multi-domain natural language processing. Multiple parallel domain pipelines are used for processing a natural language input. Each domain pipeline represents a different specific subject domain of related concepts. Each domain pipeline includes a mention module that processes the natural language input using natural language understanding (NLU) to determine a corresponding list of mentions, and an interpretation generator that receives the list of mentions and produces a rank-ordered domain output set of sentence-level interpretation candidates. A global evidence ranker receives the domain output sets from the domain pipelines and produces an overall rank-ordered final output set of sentence-level interpretations.
    Type: Grant
    Filed: December 12, 2012
    Date of Patent: May 7, 2019
    Assignee: Nuance Communications, Inc.
    Inventors: Matthieu Hebert, Jean-Philippe Robichaud, Christopher M. Parisien, Nicolae Duta, Jerome Tremblay, Amjad Almahairi, Lakshmish Kaushik, Maryse Boisvert
  • Patent number: 10282413
    Abstract: Disclosed is a device for generating an aligned corpus based on unsupervised-learning alignment, and a method thereof, a device for analyzing a destructive expression morpheme using an aligned corpus, and a method for analyzing a morpheme thereof. The morpheme analyzing device includes a knowledge database and an analyzer. The knowledge database includes an aligned corpus for storing a plurality of knowledge information sets used for a per-language morpheme analysis, and stores a morpheme dictionary for storing morpheme information corresponding to a normal expression and normal expression information corresponding to a destructive expression (here, the destructive expression represents an expression that is erroneous in orthography or is not normalized and standardized).
    Type: Grant
    Filed: August 27, 2014
    Date of Patent: May 7, 2019
    Assignee: SYSTRAN INTERNATIONAL CO., LTD.
    Inventor: Chang Jin Ji
  • Patent number: 10275708
    Abstract: An energy management system includes a neural network, a predictive model, and a dictionary reducer. The network iteratively calculates weights, resulting in a final set, for each of single-word terms and trigram terms of training data business names, each of the weights indicative of a likelihood of correlating a business category. The predictive employs sets of the weights to predict a first corresponding one of the plurality of business categories for each of the training data business names until employment of the final set accurately predicts a correct business category for the each of the training data business names, and subsequently employs the final set of the weights to predict a second corresponding one of the plurality of business categories for each of a plurality of operational business names. The dictionary reducer eliminates unessential terms taken to determine the plurality of single-word terms and trigram terms.
    Type: Grant
    Filed: October 27, 2015
    Date of Patent: April 30, 2019
    Assignee: Yardi Systems, Inc.
    Inventor: Amelia Hardjasa
  • Patent number: 10274983
    Abstract: An energy management system includes a neural network, a predictive model, and a dictionary reducer. The network iteratively calculates weights, resulting in a final set, for each of single-word terms and bigram terms of training data business names, each of the weights indicative of a likelihood of correlating a business category. The predictive employs sets of the weights to predict a first corresponding one of the plurality of business categories for each of the training data business names until employment of the final set accurately predicts a correct business category for the each of the training data business names, and subsequently employs the final set of the weights to predict a second corresponding one of the plurality of business categories for each of a plurality of operational business names. The dictionary reducer eliminates unessential terms taken to determine the plurality of single-word terms and bigram terms.
    Type: Grant
    Filed: October 27, 2015
    Date of Patent: April 30, 2019
    Assignee: Yardi Systems, Inc.
    Inventor: Amelia Hardjasa
  • Patent number: 10275442
    Abstract: Techniques for creating a template to be used in connection with automatically generating text. Techniques include creating a template to include human language text and at least a first tag that serves as a placeholder for a text portion referring to at least one referent; and allowing a user to specify multiple options to be used in place of the first tag when generating output text using the created template, the options comprising at least a first referential expression for the at least one referent and at least a first anaphoric expression for the at least one referent.
    Type: Grant
    Filed: June 19, 2018
    Date of Patent: April 30, 2019
    Assignee: YSEOP SA
    Inventors: Alain Kaeser, Emmanuel Vignon, Ludan Stoeckle
  • Patent number: 10275424
    Abstract: Improved systems and methods for extracting information from medical and natural-language text data.
    Type: Grant
    Filed: January 28, 2014
    Date of Patent: April 30, 2019
    Assignee: The Trustees of Columbia University in the City of New York
    Inventor: Carol Friedman
  • Patent number: 10275447
    Abstract: Embodiments relate to a type of expression based on a particular theme. An aspect includes acquiring, by an electronic apparatus, from text data for learning, a subset of the text data associated with the particular theme and with particular time period information. Another aspect includes extracting text data containing negative information from the acquired subset of the text data. Another aspect includes extracting a word or phrase having a high correlation with the extracted text data or a word or phrase having a high appearance frequency in the extracted text data from the extracted text data. Yet another aspect includes determining that the extracted word or phrase is the type of expression based on the particular theme.
    Type: Grant
    Filed: December 12, 2016
    Date of Patent: April 30, 2019
    Assignee: International Business Machines Corporation
    Inventors: Emiko Takeuchi, Daisuke Takuma, Hirobumi Toyoshima
  • Patent number: 10276160
    Abstract: An interaction assistant conducts multiple turn interaction dialogs with a user in which context is maintained between turns, and the system manages the dialog to achieve an inferred goal for the user. The system includes a linguistic interface to a user and a parser for processing linguistic events from the user. A dialog manager of the system is configured to receive alternative outputs from the parser, and selecting an action and causing the action to be performed based on the received alternative outputs. The system further includes a dialog state for an interaction with the user, and the alternative outputs represent alternative transitions from a current dialog state to a next dialog state. The system further includes a storage for a plurality of templates, and wherein each dialog state is defined in terms of an interrelationship of one or more instances of the templates.
    Type: Grant
    Filed: November 10, 2016
    Date of Patent: April 30, 2019
    Assignee: Semantic Machines, Inc.
    Inventors: Jacob Daniel Andreas, Taylor Darwin Berg-Kirkpatrick, Pengyu Chen, Jordan Rian Cohen, Laurence Steven Gillick, David Leo Wright Hall, Daniel Klein, Michael Newman, Adam David Pauls, Daniel Lawrence Roth, Jesse Daniel Eskes Rusak, Andrew Robert Volpe, Steven Andrew Wegmann
  • Patent number: 10268965
    Abstract: An energy management system includes a neural network, a predictive model, and a dictionary reducer. The network iteratively calculates weights, resulting in a final set, for each of single-word terms and part of speech terms of training data business names, each of the weights indicative of a likelihood of correlating a business category. The predictive employs sets of the weights to predict a first corresponding one of the plurality of business categories for each of the training data business names until employment of the final set accurately predicts a correct business category for the each of the training data business names, and subsequently employs the final set of the weights to predict a second corresponding one of the plurality of business categories for each of a plurality of operational business names. The dictionary reducer eliminates unessential terms taken to determine the plurality of single-word terms and part of speech terms.
    Type: Grant
    Filed: October 27, 2015
    Date of Patent: April 23, 2019
    Assignee: Yardi Systems, Inc.
    Inventor: Amelia Hardjasa
  • Patent number: 10268649
    Abstract: In one embodiment, a method includes receiving a query input from a client system comprising one or more n-grams, sending instructions for presenting one or more suggested modifications for the query input, each suggested modification comprising references to one or more objects associated with the online social network, receiving an indication of a selection of one of the suggested modifications, parsing the query input and the selected suggested modification using a context-free grammar model to generate an executable query command, and sending instructions to the client system for presenting one or more search results corresponding to the query command.
    Type: Grant
    Filed: May 16, 2017
    Date of Patent: April 23, 2019
    Assignee: Facebook, Inc.
    Inventors: Thomas S. Whitnah, Olivier Chatot, Erik N. Vee, William R. Maschmeyer, Keith L. Peiris, Alexander Langenfeld
  • Patent number: 10268954
    Abstract: A method, system and computer-usable medium for performing cognitive computing operations comprising receiving streams of data from a plurality of data sources; processing the streams of data from the plurality of data sources, the processing the streams of data from the plurality of data sources performing data enriching for incorporation into a cognitive graph; defining a cognitive persona within the cognitive graph, the cognitive persona corresponding to an archetype user model, the cognitive persona comprising a set of nodes in the cognitive graph; associating a user with the cognitive persona; and, performing a cognitive computing operation based upon the cognitive persona associated with the user.
    Type: Grant
    Filed: June 5, 2015
    Date of Patent: April 23, 2019
    Assignee: Cognitive Scale, Inc.
    Inventors: John N. Faith, Kyle W. Kothe, Matthew Sanchez, Neeraj Chawla
  • Patent number: 10268686
    Abstract: Exemplary embodiments relate to detecting, removing, and/or replacing objectionable words and phrases in a machine-generated translation. A classifier identifies translations containing target words or phrases. The classifier may be applied to the output translation to remove target words and phrases from the translation, or to prevent target words and phrases from being automatically presented. Further, the classifier may be applied to a translation model to prevent the target words and phrases from appearing in the output translation. Still further, the classifier may be applied to training data so that the translation model is not trained using the target words of phrases. The classifier may remove target words or phrases only when the target words or phrases appear in the output translation but not the source language input data. The classifier may be provided as a standalone service, or may be employed in the context of a machine translation system.
    Type: Grant
    Filed: June 24, 2016
    Date of Patent: April 23, 2019
    Assignee: FACEBOOK, INC.
    Inventors: Matthias Gerhard Eck, Priya Goyal
  • Patent number: 10262654
    Abstract: A computer-implemented technique is described herein for detecting actionable items in speech. In one manner of operation, the technique can include receiving utterance information that expresses at least one utterance made by one participant of a conversation to at least one other participant of the conversation. The technique can also include converting the utterance information into recognized speech information and using a machine-trained model to recognize at least one actionable item associated with the recognized speech information. The technique can also include performing at least one computer-implemented action associated the actionable item(s). The machine-trained model may correspond to a deep-structured convolutional neural network. The technique can produce the machine-trained model using a source environment corpus that is not optimally suited for a target environment in which the model is intended to be applied.
    Type: Grant
    Filed: September 24, 2015
    Date of Patent: April 16, 2019
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Dilek Zeynep Hakkani-Tur, Xiaodong He, Yun-Nung Chen
  • Patent number: 10262555
    Abstract: Speech generating devices, communication systems, and methods for communicating using the devices and systems are disclosed herein. In certain examples, a communication system is configured to receive a generated communication, establish a connection between a speech generating device and a computing device subsequent to receipt of the generated communication, and transmit the generated communication to the computing device. In other examples, a computing device is configured to establish a connection with a speech generating device, and receive a transmission generated by the speech generating device following the connection, the transmission including previously generated communications or real-time communication segments or proxies.
    Type: Grant
    Filed: October 9, 2015
    Date of Patent: April 16, 2019
    Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC
    Inventors: Jon Campbell, Ann Paradiso, Jay Beavers, Mira E. Shah, Meredith Morris, Alexander Fiannaca, Harish Kulkarni
  • Patent number: 10262043
    Abstract: A method for evaluating annotation quality is provided. The method may include obtaining annotation information associated with a plurality of annotators and a plurality of data elements including a plurality of annotation entries corresponding to at least one data element and entered based on an annotation guideline, determining a quality rating for the annotation guideline based on a comparison between a first value associated with the plurality of annotators and the plurality of data elements and a second value associated with any disparity among the plurality of annotation entries, determining a proficiency rating for an annotator from the plurality of annotators based on a comparison between a third value associated with annotation entries by the annotator and the second value, and generating a report based on the quality rating and the proficiency rating.
    Type: Grant
    Filed: July 27, 2017
    Date of Patent: April 16, 2019
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Masaki Komedani, Ken Kumagai, Takuma Murakami, Akihiro Nakayama
  • Patent number: 10264095
    Abstract: Enabling an authenticated user to access content associated with an authenticated user as though the authenticated user had a selected user relationship with the authenticated user. The user relationship may comprise a relationship degree, a relationship category, a relationship rating, and/or the like. An invitation to join an electronic service, such as an online social network, is sent to the unauthenticated user at an address known to the authenticated user. The invitation includes a time-limited token, such as a URL, that includes an invitation identifier, which relates the invitation to the authenticated user content. The token may be encrypted in the invitation. The unauthenticated user returns the token as a request to preview the authenticated user content without first becoming an authenticated user of the electronic service. If the token is still valid, access is granted. The unauthenticated user may also request to establish a connection with the authenticated user.
    Type: Grant
    Filed: November 11, 2013
    Date of Patent: April 16, 2019
    Assignee: EXCALIBUR IP, LLC
    Inventors: Michael La Rotonda, Neal Sample, F. Randall Farmer, Paul Brody, Ellen Sue Perelman
  • Patent number: 10261991
    Abstract: One variation of a system for imposing a dynamic sentiment vector to an electronic message includes: a processor; an electronic computing device communicatively coupled to the processor and associated with a particular user; and a sentiment vector generator comprising: a parsing module; a dynamic sentiment value spectrum associated with the particular user; and a program executable by the processor and configured to: receive a text input comprising message content from the electronic computing device; parse, at the parsing module, the message content comprised in the text input for emotionally charged language; based on the emotionally charged language, generate a sentiment value from the dynamic sentiment value spectrum for the text input and, based on the sentiment value, impose a sentiment vector, corresponding to the assigned sentiment value, to the text input, the imposed sentiment vector rendering a sensory effect on the message content designed to convey a corresponding sentiment.
    Type: Grant
    Filed: September 12, 2017
    Date of Patent: April 16, 2019
    Assignee: Aebeze labs
    Inventors: Michael Phillips Moskowitz, Matthew Jordan, Martin Kay, Ray Sidney, Barbara McGillivray, Scott Tong, Bradley Artziniega
  • Patent number: 10261993
    Abstract: A text analytics platform includes instructions embodied in one or more non-transitory machine accessible storage media configured to cause a computing device to retrieve text from at least one text source and implement one or more algorithms to determine a quantitative linguistics assessment for the retrieved text and provide as output a numeric value corresponding to the quantitative linguistics assessment. The quantitative linguistics assessment is based at least in part on a trained model.
    Type: Grant
    Filed: September 22, 2016
    Date of Patent: April 16, 2019
    Assignee: SRI International
    Inventors: John J. Niekrasz, Edmond D Chow
  • Patent number: 10262759
    Abstract: A method for facilitating a personal health operating system (PHOS) is provided in one example embodiment and includes extracting data into a mobile device that includes a portable health virtual machine executing the PHOS using a processor couples to a memory element, generating an N-gram dataset comprising data indicative and predictive of fitness of an individual, generating, in the PHOS, an N-gram from the N-gram dataset from the data according to a data structure indicative and predictive of fitness of an individual, the fitness including a numerical index representing a composite effect of various health conditions of the individual including interdependencies of the health conditions, generating an N-gram based on the N-gram dataset and calculating the individual's fitness using the N-gram.
    Type: Grant
    Filed: March 13, 2015
    Date of Patent: April 16, 2019
    Assignee: NANTHEALTH, INC.
    Inventors: Patrick Soon-Shiong, Vasu Rangadass, Ravi Seshadri
  • Patent number: 10255546
    Abstract: A computer program product and method provides a question and answer service that accepts an initial first question from a user and analyzes the question by a first generation subsystem to generate a first answer. A second generation subsystem of the question and answer service is configured to generate a second question based at least in-part on keywords from the first question and the first answer.
    Type: Grant
    Filed: December 22, 2017
    Date of Patent: April 9, 2019
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Mariana Alupului, Andrea L. Ames, Beth Anne M. Collopy, Joseph F. Pesot, Robert Pierce, David C. Steinmetz
  • Patent number: 10255273
    Abstract: Examples of the present disclosure describe systems and methods relating to generating a relevance score on a given natural language answer to a natural language query for ranking the answer among other answers for the query, while generating a summary passage and a likely query to the given passage. For instance, multi-layered, recurrent neural networks may be used to encode the query and the passage, along with a multi-layered neural network for information retrieval features, to generate a relevant score for the passage. A multi-layered, recurrent neural network with soft attention and sequence-to-sequence learning task may be used as a decoder to generate a summary passage. A common encoding neural network may be employed to encode the passage for the ranking and the summarizing, in order to present concise and accurate natural language answers to the query.
    Type: Grant
    Filed: June 15, 2017
    Date of Patent: April 9, 2019
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Doran Chakraborty, Manish Malik, Qifa Ke, Jonathan R. Tiao
  • Patent number: 10248648
    Abstract: An online system receives comments provided by users and analyzes them. The users may be associated with an organization, for example, employees of an enterprise may provide comments related to the enterprise. The online system classifies the comments to determine whether the comments are prescriptive or non-prescriptive. The online system may generate reports based on the classification of the comments. The online system may use a machine learning model for classifying the comments. The features used for the machine learning model include an indication of whether the input comment is associated with a question, n-grams from the comment, location of verbs in sentences, and so on.
    Type: Grant
    Filed: March 30, 2017
    Date of Patent: April 2, 2019
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Christopher Johannes Thomas, Chih Po Wen, Goutham Kurra
  • Patent number: 10248651
    Abstract: Machine learning models can determine whether post-edits to machine translated content are corrective post-edits, which are edits made to correct translation errors caused during machine translation, or content improvement post-edits, which are post-edits that have been made to improve source language content. The corrective post-edits can be utilized to generate or modify labels for strings utilized to train a translation quality estimation system. The content improvement post-edits can be utilized to improve the quality of source content prior to providing the source content to the machine translation system for translation.
    Type: Grant
    Filed: November 23, 2016
    Date of Patent: April 2, 2019
    Assignee: Amazon Technologies, Inc.
    Inventors: Hagen Fuerstenau, Felix Hieber
  • Patent number: 10248718
    Abstract: A device may receive a text, from a text source, in association with a request to generate an ontology for the text. The device may generate a set of word vectors from a list of terms determined from the text. The device may determine a quantity of term clusters to be generated to form the ontology based on the set of word vectors. The device may generate term clusters based on the quantity of term clusters, attributes, and/or non-hierarchical relationships. The term clusters may be associated with concepts of the ontology. The device may provide the term clusters for display via a user interface associated with a device.
    Type: Grant
    Filed: June 22, 2016
    Date of Patent: April 2, 2019
    Assignee: Accenture Global Solutions Limited
    Inventors: Sanjay Podder, Niharika Gupta, Annervaz Karukapadath Mohamedrasheed, Shubhashis Sengupta
  • Patent number: 10241995
    Abstract: Topics are determined for short text messages using an unsupervised topic model. In a training corpus created from a number of short text messages, a vocabulary of words is identified, and for each word a distributed vector representation is obtained by processing windows of the corpus having a fixed length. The corpus is modeled as a Gaussian mixture model in which Gaussian components represent topics. To determine a topic of a sample short text message, a posterior distribution over the corpus topics is obtained using the Gaussian mixture model.
    Type: Grant
    Filed: February 5, 2018
    Date of Patent: March 26, 2019
    Assignee: AT&T INTELLECTUAL PROPERTY I, L.P.
    Inventor: Vivek Kumar Rangarajan Sridhar
  • Patent number: 10241998
    Abstract: A method for tokenizing documents. The method includes obtaining a document comprising text to be tokenized, isolating a first string of consecutive characters in the document, searching, in a token tree, for an expression that matches the first string, making a determination that a matching expression exists in the token tree and, based on the determination, storing the matching expression as an extracted token.
    Type: Grant
    Filed: June 29, 2016
    Date of Patent: March 26, 2019
    Assignee: EMC IP Holding Company LLC
    Inventors: Lei Zhang, Chao Chen, Jingjing Liu, Kunwu Huang, Hongtao Dai, Ying Teng
  • Patent number: 10242089
    Abstract: A method of presenting digital assets in response to a search query by a user to locate at least one digital asset from a database of digital assets is described. Each digital asset has at least one keyword associated with it, and each associated keyword is part of a hierarchical organization of keywords. A first set of digital assets that have associated keywords equivalent to the search query is identified as well as suggested keywords that have e.g., an ancestor, descendant or sibling relation to the search query. The digital assets and the suggested keywords are presented to the user. The user selects a suggested keyword, and a second set of digital assets that have associated keywords equivalent to the suggested keyword is identified. The second set of digital assets is presented to the user.
    Type: Grant
    Filed: February 1, 2016
    Date of Patent: March 26, 2019
    Assignee: Getty Images (US), Inc.
    Inventors: Nate Gandert, Chris Ziobro, Evan Cariss, Mary Forster, Mary Pat Gotschall, Joy Moffatt, Jeff Oberlander, Jenny Blackburn, Debbie Cargile, Aaron Kraemer
  • Patent number: 10242310
    Abstract: A system and method for automatically mapping LATs and candidate answers to multiple taxonomies without a need to merge these taxonomies. The method includes using a syntactic analysis of a corpus to extract all type instances of the LAT. The extracted instances are then mapped to a given taxonomy and clustered in a set of supertypes. Each supertype receives a score based on the coverage of LAT instances in the corpus. The method includes mapping the candidate answer to the same taxonomy to determine if the candidate answer is an instance of a significant supertype. Then the score of a candidate answer is obtained by aggregating or taking a maximum of the score of the matched significant supertypes. This score evaluates the type match between the LAT and candidate answer for a taxonomy. Multiple taxonomies can be used to increase the chance of LAT and candidate answer mapping.
    Type: Grant
    Filed: January 11, 2017
    Date of Patent: March 26, 2019
    Assignee: International Business Machines Corporation
    Inventors: Sugato Bagchi, Mihaela A. Bornea, James J. Fan, Aditya A. Kalyanpur, Christopher Welty
  • Patent number: 10242049
    Abstract: Embodiments of the present invention provide a method, system and storage medium for implementing intelligent question answering. The method includes: receiving a query question; performing a semantic analysis of the question; performing corresponding search processing for the question based on a result of the semantic analysis, wherein the search processing includes search processing performed for the question by at least one of a semantic relationship mining system, a text library search system, a knowledge base search system, and a question and answer library search system; and returning an answer based on a result of the search processing. In this way, the accuracy of answers to the questions is effectively improved.
    Type: Grant
    Filed: August 5, 2015
    Date of Patent: March 26, 2019
    Assignee: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) CO., LTD.
    Inventors: Yanjun Ma, Guohua Li, Xingwu Sun, Xingjian Li, Weimeng Zhang, Haojie Wei, Meng Liao, Ming Zong, Xijuan Zhang, Hua Wu, Haifeng Wang
  • Patent number: 10241987
    Abstract: A method, computer program and system for performing a find and replace editing operation of a text starting from a couple of initial find and replace expressions provided by the user, applying each rule defining admissible inflected forms of the initial find and replace expressions, to the initial find and replace expressions to identify all the derived couples of find and replace expressions. The find expression and the replace expression of the derived couples correspond to inflected forms of the initial find and replace expressions. Then, for each match in the text of the find expression of the derived couples, proposing to the user the derived couples for replacement in the text.
    Type: Grant
    Filed: October 27, 2006
    Date of Patent: March 26, 2019
    Assignee: International Business Machines Corporation
    Inventor: Daniel Maxime
  • Patent number: 10237148
    Abstract: Systems and methods are disclosed for aggregating data capable of diagnosing unique datacenter issues. Traffic statistic collection may be moved from intermediate, datacenter nodes to end hosts providing reports for aggregation and correlation with events at an analytic controller, uncovering implications for such events. To track metrics and/or diagnose datacenter issues not addressed in traffic statistics, information locally available to the end hosts may be combined and/or correlated with traffic statistics. Examples may involve information about: virtual and physical computing resources; a sub-cluster; an application and/or process utilized by a datacenter task; a task/job type; an implementation phase; an initiating user; a task priority; link utilization and/or other traffic statistics relative to the foregoing.
    Type: Grant
    Filed: October 19, 2015
    Date of Patent: March 19, 2019
    Assignee: ROBIN SYSTEMS, INC.
    Inventors: Rafit Izhak-Ratzin, Shravan Kumar Vallala, Alon Pelled, Krishna Satyasai Yeddanapudi
  • Patent number: 10235446
    Abstract: According to one embodiment, a computer-implemented method for cleaning up a data set having a possible incorrect label includes: selecting a plurality of training documents; estimating a quality of an organization of a plurality of categories; and determining whether the quality of the organization is greater than a predetermined quality threshold. Corresponding system and computer program product embodiments are also presented. Other aspects and advantages of the present invention will become apparent from the following detailed description, which, when taken in conjunction with the drawings, illustrate by way of example the principles of the invention.
    Type: Grant
    Filed: August 1, 2017
    Date of Patent: March 19, 2019
    Assignee: KOFAX, INC.
    Inventors: Mauritius A. R. Schmidtler, Jan W. Amtrup, Stephen Michael Thompson, Anthony Sarah
  • Patent number: 10229106
    Abstract: Designing a natural language understanding (NLU) model for an application from scratch can be difficult for non-experts. A system can simplify the design process by providing an interface allowing a designer to input example usage sentences and build an NLU model based on presented matches to those example sentences. In one embodiment, a method for initializing a workspace for building an NLU system includes parsing a sample sentence to select at least one candidate stub grammar from among multiple candidate stub grammars. The method can include presenting, to a user, respective representations of the candidate stub grammars selected by the parsing of the sample sentence. The method can include enabling the user to choose one of the respective representations of the candidate stub grammars. The method can include adding to the workspace a stub grammar corresponding to the representation of the candidate stub grammar chosen by the user.
    Type: Grant
    Filed: July 26, 2013
    Date of Patent: March 12, 2019
    Assignee: Nuance Communications, Inc.
    Inventor: Jeffrey N. Marcus
  • Patent number: 10229673
    Abstract: In certain implementations, follow-up responses may be provided for prior natural language inputs of a user. As an example, a natural language input associated with a user may be received at a computer system. A determination of whether information sufficient for providing an adequate response to the natural language input is currently accessible to the computer system may be effectuated. A first response to the natural language input (that indicates that a follow-up response will be provided) may be provided based on a determination that information sufficient for providing an adequate response to the natural language input is not currently accessible. Information sufficient for providing an adequate response to the natural language input may be received. A second response to the natural language input may then be provided based on the received sufficient information.
    Type: Grant
    Filed: August 18, 2017
    Date of Patent: March 12, 2019
    Assignee: VOICEBOX TECHNOLOGIES CORPORATION
    Inventors: Michael R. Kennewick, Jr., Michael R. Kennewick, Sr.
  • Patent number: 10229156
    Abstract: An approach is provided in which a knowledge manager matches a question to multiple natural language contexts that each correspond to relations associated with entities in a structured resource. The knowledge manager identifies database queries corresponding to the multiple natural language contexts and assigns priority scores to the database queries based upon their relative specificity. In turn, the knowledge manager invokes one of the database queries based upon the assigned priority scores.
    Type: Grant
    Filed: November 3, 2014
    Date of Patent: March 12, 2019
    Assignee: International Business Machines Corporation
    Inventors: Timothy A. Bishop, Stephen A. Boxwell, Benjamin L. Brumfield, Nirav P. Desai, Stanley J. Vernier
  • Patent number: 10229107
    Abstract: A system and method for analyzing narrative data based on a functional ontology using semiotic square functions to produce analyzed data outputs. A computer implemented method accesses narrative data and reads a semiotic square function data table for each verb in the sequence of words, each semiotic square function data table classifies at least one verb in each sentence pattern as a functional type and includes one or more words in a semiotic square relationship to the verb classified, the functional type applying at least one symmetrical relationship between a first actor and a second actor in the narrative data. The method parses each sentence which includes a verb matching a functional type to match sentence subjects and objects to an event template and outputs an analysis of the narrative data relative to a common story theme based on a sequence of event records.
    Type: Grant
    Filed: October 24, 2017
    Date of Patent: March 12, 2019
    Assignee: RAFTR, INC.
    Inventors: Claude Vogel, Susan Decker
  • Patent number: 10229186
    Abstract: An apparatus in one embodiment comprises a processing platform implementing a data set discovery engine. The data set discovery engine comprises a data set indexer configured to generate similarity indexes for a plurality of data sets, and a relativistic retriever coupled to the data set indexer and configured to obtain a suitability template for a query and to execute the query against one or more of the similarity indexes based at least in part on the suitability template. A given one of the similarity indexes comprises at least first and second auxiliary information generated from respective ones of at least first and second different similarity measures of a plurality of different similarity measures. The first and second similarity measures comprise selected ones of the plurality of different similarity measures that are supported by the data set discovery engine with the supported similarity measures comprising both frequency-based and non-frequency-based similarity measures.
    Type: Grant
    Filed: March 18, 2016
    Date of Patent: March 12, 2019
    Assignee: EMC IP Holding Company LLC
    Inventors: David Stephen Reiner, Nihar Nanda, Leonid Levkovich-Maslyuk, Andrey Abramov
  • Patent number: 10230818
    Abstract: Systems and methods for selecting content based on an event associated with a device identifier are provided. One or more processors can receive a request to serve content. The processors can identify a device identifier associated with the request. The processors can determine, from the device identifier, an event for which to serve content. The processors can determine, from the request, a length of time between a time the request to serve content is received and a time at which the event is scheduled to occur. The processors can select, based on the determined length of time and event parameters associated with the event, content for display and provide the selected content for display at a computing device associated with the device identifier.
    Type: Grant
    Filed: December 6, 2017
    Date of Patent: March 12, 2019
    Assignee: Google LLC
    Inventors: Courtney Hampson, Jason Robert Richard Sanio
  • Patent number: 10229111
    Abstract: Methods, systems, apparatus, including computer programs encoded on computer storage medium, for generating a sentence summary. In one aspect, the method includes actions of tokenizing the sentence into a plurality of tokens, processing data representative of each token in a first order using an LSTM neural network to initialize an internal state of a second LSTM neural network, processing data representative of each token in a second order using the second LSTM neural network, comprising, for each token in the sentence: processing the data representative of the token using the second LSTM neural network in accordance with a current internal state of the second LSTM neural network to (i) generate an LSTM output for the token, and (ii) to update the current internal state of the second LSTM neural network, and generating the summarized version of the sentence using the outputs of the second LSTM neural network for the tokens.
    Type: Grant
    Filed: February 3, 2017
    Date of Patent: March 12, 2019
    Assignee: Google LLC
    Inventors: Ekaterina Filippova, Enrique Alfonseca, Carlos Alberto Colmenares Rojas, Lukasz Mieczyslaw Kaiser, Oriol Vinyals
  • Patent number: 10223661
    Abstract: A method, system and computer program product for improving management and performance of an employee. An indication of a goal sponsored by an owner, such as a manager, is received. After receiving an indication of a user subscribing to the goal sponsored by the owner, communications (e.g., posts) on the social network involving the subscribed user that include a tag designating the goal may be monitored. Upon detecting a completion of the goal by the subscribed user in the monitored communications, a pattern of steps (e.g., “prepare,” “review” and “finish”) to accomplish the goal is determined based on the monitored communications. The pattern may then be used to recommend actions to other users subscribed to the goal concerning accomplishing the goal based on the pattern. Furthermore, the owner may receive indications as to the progress of the user in accomplishing the goal based on the pattern.
    Type: Grant
    Filed: May 19, 2016
    Date of Patent: March 5, 2019
    Assignee: International Business Machines Corporation
    Inventors: Paul R. Bastide, Matthew E. Broomhall, Sean Callanan, Sandra L. Kogan
  • Patent number: 10223709
    Abstract: Methods, apparatus, and computer program products are disclosed for providing an impression to a consumer based on consumer preferences for future promotions. The methods include accessing consumer preferences for future promotions that specify at least one promotion request relating to a provider or a promotion category, and one or more promotion qualities, analyzing a plurality of promotions to identify those that satisfy the consumer preferences, and providing an impression to the consumer indicating the availability of the identified promotions. In embodiments, the methods can be used to identify promotions that are combinable with additional promotions offered by the same provider. Corresponding apparatus and computer program products are also provided.
    Type: Grant
    Filed: March 14, 2014
    Date of Patent: March 5, 2019
    Assignee: GROUPON, INC.
    Inventor: Injae Lee