Patents by Inventor Jiangbo Miao

Jiangbo Miao 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: 10430520
    Abstract: Sentence internationalization methods and systems are disclosed.
    Type: Grant
    Filed: February 13, 2017
    Date of Patent: October 1, 2019
    Assignee: FACEBOOK, INC.
    Inventors: Ling Bao, Hugo Johan van Heuven, Jiangbo Miao, Li Tan, David Mercurio, Maximilian Machedon
  • Patent number: 10157179
    Abstract: Some embodiments include a computer-implement method of producing a flexible sentence syntax to facilitate one or more computer applications to generate and publish sentence expressions. For example, the method can include providing a developer interface to define a flexible sentence syntax that controls one or more sentences publishable by an application service. A developer of the application service can customize the flexible sentence syntax including selecting at least one of selectable tokens that is associated with another element to incorporate in the flexible sentence syntax. Based on the selected token, a computing device can generate and publish a target sentence according to the flexible sentence syntax on the application service's behalf.
    Type: Grant
    Filed: July 18, 2017
    Date of Patent: December 18, 2018
    Assignee: FACEBOOK, INC.
    Inventors: Ling Bao, Hugo Johan van Heuven, Jiangbo Miao
  • Publication number: 20170315993
    Abstract: Some embodiments include a computer-implement method of producing a flexible sentence syntax to facilitate one or more computer applications to generate and publish sentence expressions. For example, the method can include providing a developer interface to define a flexible sentence syntax that controls one or more sentences publishable by an application service. A developer of the application service can customize the flexible sentence syntax including selecting at least one of selectable tokens that is associated with another element to incorporate in the flexible sentence syntax. Based on the selected token, a computing device can generate and publish a target sentence according to the flexible sentence syntax on the application service's behalf.
    Type: Application
    Filed: July 18, 2017
    Publication date: November 2, 2017
    Inventors: Ling Bao, Hugo Johan van Heuven, Jiangbo Miao
  • Patent number: 9740690
    Abstract: Some embodiments include a computer-implement method of producing a flexible sentence syntax to facilitate one or more computer applications to generate and publish sentence expressions. For example, the method can include providing a developer interface to define a flexible sentence syntax that controls one or more sentences publishable by an application service. A developer of the application service can customize the flexible sentence syntax including selecting at least one of selectable tokens that is associated with another element to incorporate in the flexible sentence syntax. Based on the selected token, a computing device can generate and publish a target sentence according to the flexible sentence syntax on the application service's behalf.
    Type: Grant
    Filed: February 22, 2017
    Date of Patent: August 22, 2017
    Assignee: Facebook, Inc.
    Inventors: Ling Bao, Hugo Johan van Heuven, Jiangbo Miao
  • Publication number: 20170169016
    Abstract: Sentence internationalization methods and systems are disclosed.
    Type: Application
    Filed: February 13, 2017
    Publication date: June 15, 2017
    Inventors: Ling Bao, Hugo Johan van Heuven, Jiangbo Miao, Li Tan, David Mercurio, Maximilian Machedon
  • Publication number: 20170161265
    Abstract: Some embodiments include a computer-implement method of producing a flexible sentence syntax to facilitate one or more computer applications to generate and publish sentence expressions. For example, the method can include providing a developer interface to define a flexible sentence syntax that controls one or more sentences publishable by an application service. A developer of the application service can customize the flexible sentence syntax including selecting at least one of selectable tokens that is associated with another element to incorporate in the flexible sentence syntax. Based on the selected token, a computing device can generate and publish a target sentence according to the flexible sentence syntax on the application service's behalf.
    Type: Application
    Filed: February 22, 2017
    Publication date: June 8, 2017
    Inventors: Ling Bao, Hugo Johan van Heuven, Jiangbo Miao
  • Patent number: 9619456
    Abstract: Some embodiments include a computer-implement method of producing a flexible sentence syntax to facilitate one or more computer applications to generate and publish sentence expressions. For example, the method can include providing a developer interface to define a flexible sentence syntax that controls one or more sentences publishable by an application service. A developer of the application service can customize the flexible sentence syntax including selecting at least one of selectable tokens that is associated with a specific sentence element to incorporate in the flexible sentence syntax. Based on the selected token, a computing device can generate and publish a target sentence according to the flexible sentence syntax on the application service's behalf.
    Type: Grant
    Filed: May 8, 2015
    Date of Patent: April 11, 2017
    Assignee: Facebook, Inc.
    Inventors: Ling Bao, Hugo Johan van Heuven, Jiangbo Miao
  • Patent number: 9606987
    Abstract: Sentence internationalization methods and systems are disclosed.
    Type: Grant
    Filed: May 6, 2013
    Date of Patent: March 28, 2017
    Assignee: Facebook, Inc.
    Inventors: Ling Bao, Hugo Johan van Heuven, Jiangbo Miao, Li Tan, David Mercurio, Maximilian Machedon
  • Patent number: 9448990
    Abstract: A statistical language model (SLM) may be iteratively refined by considering N-gram counts in new data, and blending the information contained in the new data with the existing SLM. A first group of documents is evaluated to determine the probabilities associated with the different N-grams observed in the documents. An SLM is constructed based on these probabilities. A second group of documents is then evaluated to determine the probabilities associated with each N-gram in that second group. The existing SLM is then evaluated to determine how well it explains the probabilities in the second group of documents, and a weighting parameter is calculated from that evaluation. Using the weighting parameter, a new SLM is then constructed as a weighted average of the existing SLM and the new probabilities.
    Type: Grant
    Filed: November 5, 2013
    Date of Patent: September 20, 2016
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Kuansan Wang, Xiaolong Li, Jiangbo Miao, Frederic H. Behr, Jr.
  • Publication number: 20150242385
    Abstract: Some embodiments include a computer-implement method of producing a flexible sentence syntax to facilitate one or more computer applications to generate and publish sentence expressions. For example, the method can include providing a developer interface to define a flexible sentence syntax that controls one or more sentences publishable by an application service. A developer of the application service can customize the flexible sentence syntax including selecting at least one of selectable tokens that is associated with a specific sentence element to incorporate in the flexible sentence syntax. Based on the selected token, a computing device can generate and publish a target sentence according to the flexible sentence syntax on the application service's behalf.
    Type: Application
    Filed: May 8, 2015
    Publication date: August 27, 2015
    Inventors: Ling Bao, Hugo Johan van Heuven, Jiangbo Miao
  • Patent number: 9110889
    Abstract: A method and system for providing flexible sentences are disclosed. The system includes a developer interface for providing options to define actor, edge, target and aggregation of a flexible sentence syntax. In one embodiment, tokens are provided to define property expressions of the edge and/or target of the flexible sentence syntax. Based on the defined edge and target, the developer interface may generate a plurality of flexible sentence syntaxes for a developer to select. In some embodiments, the developer can add additional property expressions to further define the edge and/or target of the flexible sentence syntax. In some instances, the plurality of flexible sentence syntaxes may be prioritized based on a percentage coverage, which is determined by the impressions received over a given time frame.
    Type: Grant
    Filed: April 23, 2013
    Date of Patent: August 18, 2015
    Assignee: FACEBOOK, INC.
    Inventors: Ling Bao, Hugo Johan van Heuven, Jiangbo Miao
  • Publication number: 20140330551
    Abstract: Sentence internationalization methods and systems are disclosed.
    Type: Application
    Filed: May 6, 2013
    Publication date: November 6, 2014
    Inventors: Ling Bao, Hugo Johan van Heuven, Jiangbo Miao, Li Tan, David Mercurio, Maximilian Machedon
  • Publication number: 20140316766
    Abstract: A method and system for providing flexible sentences are disclosed. The system includes a developer interface for providing options to define actor, edge, target and aggregation of a flexible sentence syntax. In one embodiment, tokens are provided to define property expressions of the edge and/or target of the flexible sentence syntax. Based on the defined edge and target, the developer interface may generate a plurality of flexible sentence syntaxes for a developer to select. In some embodiments, the developer can add additional property expressions to further define the edge and/or target of the flexible sentence syntax. In some instances, the plurality of flexible sentence syntaxes may be prioritized based on a percentage coverage, which is determined by the impressions received over a given time frame.
    Type: Application
    Filed: April 23, 2013
    Publication date: October 23, 2014
    Inventors: Ling Bao, Hugo van Heuven, Jiangbo Miao
  • Publication number: 20140149108
    Abstract: A statistical language model (SLM) may be iteratively refined by considering N-gram counts in new data, and blending the information contained in the new data with the existing SLM. A first group of documents is evaluated to determine the probabilities associated with the different N-grams observed in the documents. An SLM is constructed based on these probabilities. A second group of documents is then evaluated to determine the probabilities associated with each N-gram in that second group. The existing SLM is then evaluated to determine how well it explains the probabilities in the second group of documents, and a weighting parameter is calculated from that evaluation. Using the weighting parameter, a new SLM is then constructed as a weighted average of the existing SLM and the new probabilities.
    Type: Application
    Filed: November 5, 2013
    Publication date: May 29, 2014
    Applicant: MICROSOFT CORPORATION
    Inventors: Kuansan Wang, Xiaolong Li, Jiangbo Miao, Frederic H. Behr, JR.
  • Patent number: 8577670
    Abstract: A statistical language model (SLM) may be iteratively refined by considering N-gram counts in new data, and blending the information contained in the new data with the existing SLM. A first group of documents is evaluated to determine the probabilities associated with the different N-grams observed in the documents. An SLM is constructed based on these probabilities. A second group of documents is then evaluated to determine the probabilities associated with each N-gram in that second group. The existing SLM is then evaluated to determine how well it explains the probabilities in the second group of documents, and a weighting parameter is calculated from that evaluation. Using the weighting parameter, a new SLM is then constructed as a weighted average of the existing SLM and the new probabilities.
    Type: Grant
    Filed: January 8, 2010
    Date of Patent: November 5, 2013
    Assignee: Microsoft Corporation
    Inventors: Kuansan Wang, Xiaolong Li, Jiangbo Miao, Frederic H. Behr, Jr.
  • Publication number: 20110172988
    Abstract: A statistical language model (SLM) may be iteratively refined by considering N-gram counts in new data, and blending the information contained in the new data with the existing SLM. A first group of documents is evaluated to determine the probabilities associated with the different N-grams observed in the documents. An SLM is constructed based on these probabilities. A second group of documents is then evaluated to determine the probabilities associated with each N-gram in that second group. The existing SLM is then evaluated to determine how well it explains the probabilities in the second group of documents, and a weighting parameter is calculated from that evaluation. Using the weighting parameter, a new SLM is then constructed as a weighted average of the existing SLM and the new probabilities.
    Type: Application
    Filed: January 8, 2010
    Publication date: July 14, 2011
    Applicant: MICROSOFT CORPORATION
    Inventors: Kuansan Wang, Xiaolong Li, Jiangbo Miao, Frederic H. Behr, Jr.