Patents by Inventor NECIP FAZIL AYAN

NECIP FAZIL AYAN has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 10366171
    Abstract: Exemplary embodiments relate to techniques for improving a machine translation system. The machine translation system may include one or more models for generating a translation. The system may generate multiple candidate translations, and may present the candidate translations to different groups of users, such as users of a social network. User engagement with the different candidate translations may be measured, and the system may determine which of the candidate translations was most favored by the users. For example, in the context of a social network, the number of times that the translation is liked or shared, or the number of comments associated with the translation, may be used to determine user engagement with the translation. The models of the machine translation system may be modified to favor the most-favored candidate translation. The translation system may repeat this process to continue to tune the models in a feedback loop.
    Type: Grant
    Filed: September 27, 2018
    Date of Patent: July 30, 2019
    Assignee: FACEBOOK, INC.
    Inventors: Ying Zhang, Fei Hung, Kay Rottmann, Necip Fazil Ayan
  • Publication number: 20190141004
    Abstract: The present disclosure is directed toward systems and methods for providing translations of electronic messages via a social networking system. For example, systems and methods described herein involve determining whether to provide an electronic message or a translation of the electronic message to a recipient based on social networking activities of the recipient. Furthermore, systems and methods described herein can provide a translation of an electronic message based on an analysis of social networking activities of one or more recipients of the electronic message.
    Type: Application
    Filed: November 5, 2018
    Publication date: May 9, 2019
    Inventors: Matthias Eck, Necip Fazil Ayan, Ying Zhang, Kay Rottman, Lukasz Langa
  • Publication number: 20190130912
    Abstract: A method for assisting a user with one or more desired tasks is disclosed. For example, an executable, generic language understanding module and an executable, generic task reasoning module are provided for execution in the computer processing system. A set of run-time specifications is provided to the generic language understanding module and the generic task reasoning module, comprising one or more models specific to a domain. A language input is then received from a user, an intention of the user is determined with respect to one or more desired tasks, and the user is assisted with the one or more desired tasks, in accordance with the intention of the user.
    Type: Application
    Filed: December 21, 2018
    Publication date: May 2, 2019
    Inventors: Osher Yadgar, Neil Yorke-Smith, Bart Peintner, Gokhan Tur, Necip Fazil Ayan, Michael J. Wolverton, Girish Acharya, Venkatarama Satyanarayana Parimi, William S. Mark, Wen Wang, Andreas Kathol, Regis Vincent, Horacio E. Franco
  • Patent number: 10163440
    Abstract: A method for assisting a user with one or more desired tasks is disclosed. For example, an executable, generic language understanding module and an executable, generic task reasoning module are provided for execution in the computer processing system. A set of run-time specifications is provided to the generic language understanding module and the generic task reasoning module, comprising one or more models specific to a domain. A language input is then received from a user, an intention of the user is determined with respect to one or more desired tasks, and the user is assisted with the one or more desired tasks, in accordance with the intention of the user.
    Type: Grant
    Filed: January 5, 2017
    Date of Patent: December 25, 2018
    Assignee: SRI International
    Inventors: Osher Yadgar, Neil Yorke-Smith, Bart Peintner, Gokhan Tur, Necip Fazil Ayan, Michael J. Wolverton, Girish Acharya, Venkatarama Satyanarayana Parimi, William S. Mark, Wen Wang, Andreas Kathol, Regis Vincent, Horacio E. Franco
  • Patent number: 10122670
    Abstract: The present disclosure is directed toward systems and methods for providing translations of electronic messages via a social networking system. For example, systems and methods described herein involve determining whether to provide an electronic message or a translation of the electronic message to a recipient based on social networking activities of the recipient. Furthermore, systems and methods described herein can provide a translation of an electronic message based on an analysis of social networking activities of one or more recipients of the electronic message.
    Type: Grant
    Filed: December 31, 2014
    Date of Patent: November 6, 2018
    Assignee: FACEBOOK, INC.
    Inventors: Matthias Eck, Necip Fazil Ayan, Ying Zhang, Kay Rottman, Lukasz Langa
  • Patent number: 10114819
    Abstract: Exemplary embodiments relate to techniques for improving a machine translation system. The machine translation system may include one or more models for generating a translation. The system may generate multiple candidate translations, and may present the candidate translations to different groups of users, such as users of a social network. User engagement with the different candidate translations may be measured, and the system may determine which of the candidate translations was most favored by the users. For example, in the context of a social network, the number of times that the translation is liked or shared, or the number of comments associated with the translation, may be used to determine user engagement with the translation. The models of the machine translation system may be modified to favor the most-favored candidate translation. The translation system may repeat this process to continue to tune the models in a feedback loop.
    Type: Grant
    Filed: June 24, 2016
    Date of Patent: October 30, 2018
    Assignee: FACEBOOK, INC.
    Inventors: Ying Zhang, Fei Huang, Kay Rottmann, Necip Fazil Ayan
  • Patent number: 9916305
    Abstract: This disclosure covers systems and methods that create references for locating a translation of a term expressed within a digital communication. In particular, in certain embodiments, the disclosed systems and methods create a hashkey to identify a translation (or multiple translations) of an initial term from a source language to a target language. By referring to this hashkey corresponding to the initial term, the disclosed systems and methods can identify a translation (or multiple translations) of the same or similar term within a digital communication to translate a digital communication from a source language to a target language.
    Type: Grant
    Filed: December 28, 2016
    Date of Patent: March 13, 2018
    Assignee: FACEBOOK, INC.
    Inventors: Necip Fazil Ayan, Donald Vincent Husa, Shawn C. P. Mei
  • Patent number: 9875494
    Abstract: A virtual personal assistant (VPA) application analyzes intents to, among other things, enhance or personalize a user's dialog experience with the VPA application. A set of intents, or multiple sets of intents, are maintained over the course of one or more user-specific dialog sessions with the VPA. Inferences may be derived from the set or sets of intents and incorporated into a current or future dialog session between the VPA and a user of the VPA application. In some embodiments, the inferences are only made available through the systemic understanding of natural language discourse by the VPA.
    Type: Grant
    Filed: July 30, 2013
    Date of Patent: January 23, 2018
    Assignee: SRI INTERNATIONAL
    Inventors: Edgar T. Kalns, William S. Mark, Necip Fazil Ayan
  • Publication number: 20170371868
    Abstract: Exemplary embodiments relate to techniques for improving a machine translation system. The machine translation system may include one or more models for generating a translation. The system may generate multiple candidate translations, and may present the candidate translations to different groups of users, such as users of a social network. User engagement with the different candidate translations may be measured, and the system may determine which of the candidate translations was most favored by the users. For example, in the context of a social network, the number of times that the translation is liked or shared, or the number of comments associated with the translation, may be used to determine user engagement with the translation. The models of the machine translation system may be modified to favor the most-favored candidate translation. The translation system may repeat this process to continue to tune the models in a feedback loop.
    Type: Application
    Filed: June 24, 2016
    Publication date: December 28, 2017
    Applicant: Facebook, Inc.
    Inventors: Ying Zhang, Fei Huang, Kay Rottmann, Necip Fazil Ayan
  • Publication number: 20170316105
    Abstract: In one embodiment, a method includes receiving a search query from a user and identifying one or more objects that match the search query. The method includes determining one or more search intents of the search query based on one or more topics associated with the identified objects and a ratio of object-types of the identified objects. The method includes generating search-result modules corresponding to the search query based on the determined search intents. Each search-result module is associated with a particular object-type and includes search results of that object-type. The method includes sending instructions for presenting a search-results interface to the client system of the user for display. The search-results interface may include one or more of the search result modules displayed in a blended order based on the determined search intents.
    Type: Application
    Filed: July 19, 2017
    Publication date: November 2, 2017
    Inventors: Necip Fazil Ayan, Maxime Boucher, Xiao Li, Alexander Perelygin
  • Patent number: 9805718
    Abstract: A dialog assistant embodied in a computing system can present a clarification question based on a machine-readable version of human-generated conversational natural language input. Some versions of the dialog assistant identify a clarification target in the machine-readable version, determine a clarification type relating to the clarification target, present the clarification question in a conversational natural language manner, and process a human-generated conversational natural language response to the clarification question.
    Type: Grant
    Filed: April 19, 2013
    Date of Patent: October 31, 2017
    Assignee: SRI INTERNAITONAL
    Inventors: Necip Fazil Ayan, Arindam Mandal, Jing Zheng
  • Publication number: 20170270126
    Abstract: In one embodiment, a method includes receiving, from a client system of a first user, a text query including one or more n-grams, including an ambiguous n-gram. The method includes searching multiple keyword generators to identify one or more keyword suggestions matching the ambiguous n-gram, each keyword generator having a particular type. The method includes calculating, by a particular scoring algorithm for each keyword generator, a keyword score for each identified keyword suggestion. The scoring algorithm includes multiple weighting factors chosen based on the type of the keyword generator. The method includes generating a set of suggested queries including at least a portion of the text query and one or more identified keyword suggestions and filtering suggested queries from the set based on privacy settings associated with the identified keyword suggestions. The method includes sending, to the client system, instructions for presenting one or more of the suggested queries.
    Type: Application
    Filed: May 31, 2017
    Publication date: September 21, 2017
    Inventors: Maxime Boucher, Xiao Li, Alexander Perelygin, Veselin S. Stoyanov, Russell Lee-Goldman, Necip Fazil Ayan
  • Patent number: 9754037
    Abstract: In one embodiment, a method includes receiving a search query from a first user and identifying one or more second nodes that match the search query. The method includes determining one or more search intents of the search query. Search intent may be based on one or more topics associated with the identified nodes and one or more node-types of the identified nodes. The method includes generating one or more search results corresponding to the search query, the search-results being generated based on the determined search intents. The method includes sending a search-results page to the client system of the first user for display. The search-results page may include one or more of the generated search results.
    Type: Grant
    Filed: August 27, 2014
    Date of Patent: September 5, 2017
    Assignee: Facebook, Inc.
    Inventors: Necip Fazil Ayan, Maxime Boucher, Xiao Li, Alexander Perelygin
  • Patent number: 9703859
    Abstract: In one embodiment, a method includes receiving from a client system of a first user an unstructured text query. The method includes parsing the text query to identify one or more n-grams. At least one of the n-grams is an ambiguous n-gram. The method includes searching a plurality of keyword generators to identify one or more keyword suggestions matching the ambiguous n-gram. The method further includes calculating a keyword score for each identified keyword suggestions and generating one or more suggested queries including one or more n-grams identified from the text query. The one or more identified keyword suggestions having a keyword score greater than a threshold keyword score. The method includes sending one or more of the suggested queries to the client system of the first user for display.
    Type: Grant
    Filed: August 27, 2014
    Date of Patent: July 11, 2017
    Assignee: Facebook, Inc.
    Inventors: Maxime Boucher, Xiao Li, Alexander Perelygin, Veselin S. Stoyanov, Russell Lee-Goldman, Necip Fazil Ayan
  • Publication number: 20170116989
    Abstract: A method for assisting a user with one or more desired tasks is disclosed. For example, an executable, generic language understanding module and an executable, generic task reasoning module are provided for execution in the computer processing system. A set of run-time specifications is provided to the generic language understanding module and the generic task reasoning module, comprising one or more models specific to a domain. A language input is then received from a user, an intention of the user is determined with respect to one or more desired tasks, and the user is assisted with the one or more desired tasks, in accordance with the intention of the user.
    Type: Application
    Filed: January 5, 2017
    Publication date: April 27, 2017
    Applicant: SRI International
    Inventors: Osher Yadgar, Neil Yorke-Smith, Bart Peintner, Gokhan Tur, Necip Fazil Ayan, Michael J. Wolverton, Girish Acharya, Venkatarama Satyanarayana Parimi, William S. Mark, Wen Wang, Andreas Kathol, Regis Vincent, Horacio E. Franco
  • Patent number: 9575964
    Abstract: A method for assisting a user with one or more desired tasks is disclosed. For example, an executable, generic language understanding module and an executable, generic task reasoning module are provided for execution in the computer processing system. A set of run-time specifications is provided to the generic language understanding module and the generic task reasoning module, comprising one or more models specific to a domain. A language input is then received from a user, an intention of the user is determined with respect to one or more desired tasks, and the user is assisted with the one or more desired tasks, in accordance with the intention of the user.
    Type: Grant
    Filed: June 30, 2015
    Date of Patent: February 21, 2017
    Assignee: SRI INTERNATIONAL
    Inventors: Osher Yadgar, Neil Yorke-Smith, Bart Peintner, Gokhan Tur, Necip Fazil Ayan, Michael J. Wolverton, Girish Acharya, Venkatarama Satyanarayana Parimi, William S. Mark, Wen Wang, Andreas Kathol, Regis Vincent, Horacio E. Franco
  • Patent number: 9489625
    Abstract: A platform for developing a virtual personal assistant (“VPA”) application includes an ontology that defines a computerized structure for representing knowledge relating to one or more domains. A domain may refer to a category of information and/or activities in relation to which the VPA application may engage in a conversational natural language dialog with a computing device user. Re-usable VPA components may be linked to or included in the ontology. An ontology populating agent may at least partially automate the process of populating the ontology with domain-specific information. The re-usable VPA components may be linked with the domain-specific information through the ontology. A VPA application created with the platform may include domain-adapted re-usable VPA components that may be called upon by an executable VPA engine to determine a likely intended meaning of conversational natural language input of the user and/or initiate an appropriate system response to the input.
    Type: Grant
    Filed: May 10, 2013
    Date of Patent: November 8, 2016
    Assignee: SRI INTERNATIONAL
    Inventors: Edgar T. Kalns, Dayne B. Freitag, William S. Mark, Necip Fazil Ayan, Michael J. Wolverton, Thomas J. Lee
  • Publication number: 20160191448
    Abstract: The present disclosure is directed toward systems and methods for providing translations of electronic messages via a social networking system. For example, systems and methods described herein involve determining whether to provide an electronic message or a translation of the electronic message to a recipient based on social networking activities of the recipient. Furthermore, systems and methods described herein can provide a translation of an electronic message based on an analysis of social networking activities of one or more recipients of the electronic message.
    Type: Application
    Filed: December 31, 2014
    Publication date: June 30, 2016
    Inventors: Matthias Eck, Necip Fazil Ayan, Ying Zhang, Kay Rottman, Lukasz Langa
  • Publication number: 20160063093
    Abstract: In one embodiment, a method includes receiving from a client system of a first user an unstructured text query. The method includes parsing the text query to identify one or more n-grams. At least one of the n-grams is an ambiguous n-gram. The method includes searching a plurality of keyword generators to identify one or more keyword suggestions matching the ambiguous n-gram. The method further includes calculating a keyword score for each identified keyword suggestions and generating one or more suggested queries including one or more n-grams identified from the text query. The one or more identified keyword suggestions having a keyword score greater than a threshold keyword score. The method includes sending one or more of the suggested queries to the client system of the first user for display.
    Type: Application
    Filed: August 27, 2014
    Publication date: March 3, 2016
    Inventors: Maxime Boucher, Xiao Li, Alexander Perelygin, Veselin S. Stoyanov, Russell Lee-Goldman, Necip Fazil Ayan
  • Publication number: 20160063115
    Abstract: In one embodiment, a method includes receiving a search query from a first user and identifying one or more second nodes that match the search query. The method includes determining one or more search intents of the search query. Search intent may be based on one or more topics associated with the identified nodes and one or more node-types of the identified nodes. The method includes generating one or more search results corresponding to the search query, the search-results being generated based on the determined search intents. The method includes sending a search-results page to the client system of the first user for display. The search-results page may include one or more of the generated search results.
    Type: Application
    Filed: August 27, 2014
    Publication date: March 3, 2016
    Inventors: Necip Fazil Ayan, Maxime Boucher, Xiao Li, Alexander Perelygin