Patents by Inventor Shiun-Zu Kuo
Shiun-Zu Kuo 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: 11507876Abstract: Systems, methods, and non-transitory computer-readable media can be configured to acquire at least one instance of positive training data based at least in part on at least one source. A set of supplemental positive training data can be generated based at least in part on the at least one instance of positive training data. A machine learning model can be trained to identify inappropriate material based at least in part on the set of supplemental positive training data.Type: GrantFiled: December 21, 2018Date of Patent: November 22, 2022Assignee: Meta Platforms, Inc.Inventors: Shiun-Zu Kuo, Ziqi Wang, Bi Xue, Yuxiang Liu
-
Patent number: 10726022Abstract: In one embodiment, a method includes receiving a search query inputted by a first user, wherein the search query comprises one or more n-grams; calculating a needle-confidence score for the search query that is calculated by a needle-intent classifier based on at least the n-grams of the search query and a language model analysis of the n-grams, and wherein the needle-confidence score represents a probability that the search query was intended as a needle search; classifying the search query as a needle search if the calculated needle-confidence score is above a threshold confidence score; and generating a plurality of search-result modules, each search-result module comprising one or more search results matching the search query, wherein one of the search-result modules is a social module, and wherein the number of search results in the social module is based on the classification of the search query as a needle search.Type: GrantFiled: August 26, 2016Date of Patent: July 28, 2020Assignee: Facebook, Inc.Inventors: Shiun-Zu Kuo, Veselin S. Stoyanov, Rose Marie Philip, Melissa Rose Winstanley
-
Patent number: 10019984Abstract: Techniques and technologies for diagnosing speech recognition errors are described. In an example implementation, a system for diagnosing speech recognition errors may include an error detection module configured to determine that a speech recognition result is least partially erroneous, and a recognition error diagnostics module. The recognition error diagnostics module may be configured to (a) perform a first error analysis of the at least partially erroneous speech recognition result to provide a first error analysis result; (b) perform a second error analysis of the at least partially erroneous speech recognition result to provide a second error analysis result; and (c) determine at least one category of recognition error associated with the at least partially erroneous speech recognition result based on a combination of the first error analysis result and the second error analysis result.Type: GrantFiled: February 27, 2015Date of Patent: July 10, 2018Assignee: Microsoft Technology Licensing, LLCInventors: Shiun-Zu Kuo, Thomas Reutter, Yifan Gong, Mark T. Hanson, Ye Tian, Shuangyu Chang, Jonathan Hamaker, Qi Miao, Yuancheng Tu
-
Publication number: 20180060326Abstract: In one embodiment, a method includes receiving a search query inputted by a first user, wherein the search query comprises one or more n-grams; calculating a needle-confidence score for the search query that is calculated by a needle-intent classifier based on at least the n-grams of the search query and a language model analysis of the n-grams, and wherein the needle-confidence score represents a probability that the search query was intended as a needle search; classifying the search query as a needle search if the calculated needle-confidence score is above a threshold confidence score; and generating a plurality of search-result modules, each search-result module comprising one or more search results matching the search query, wherein one of the search-result modules is a social module, and wherein the number of search results in the social module is based on the classification of the search query as a needle search.Type: ApplicationFiled: August 26, 2016Publication date: March 1, 2018Inventors: Shiun-Zu Kuo, Veselin S. Stoyanov, Rose Marie Philip, Melissa Rose Winstanley
-
Publication number: 20160253989Abstract: Techniques and technologies for diagnosing speech recognition errors are described. In an example implementation, a system for diagnosing speech recognition errors may include an error detection module configured to determine that a speech recognition result is least partially erroneous, and a recognition error diagnostics module. The recognition error diagnostics module may be configured to (a) perform a first error analysis of the at least partially erroneous speech recognition result to provide a first error analysis result; (b) perform a second error analysis of the at least partially erroneous speech recognition result to provide a second error analysis result; and (c) determine at least one category of recognition error associated with the at least partially erroneous speech recognition result based on a combination of the first error analysis result and the second error analysis result.Type: ApplicationFiled: February 27, 2015Publication date: September 1, 2016Inventors: Shiun-Zu Kuo, Thomas Reutter, Yifan Gong, Mark T. Hanson, Ye Tian, Shuangyu Chang, Jon Hamaker, Qi Miao, Yuancheng Tu
-
Patent number: 8457946Abstract: Architecture for correcting incorrect recognition results in an Asian language speech recognition system. A spelling mode can be launched in response to receiving speech input, the spelling mode for correcting incorrect spelling of the recognition results or generating new words. Correction can be obtained using speech and/or manual selection and entry. The architecture facilitates correction in a single pass, rather than multiples times as in conventional systems. Words corrected using the spelling mode are corrected as a unit and treated as a word. The spelling mode applies to languages of at least the Asian continent, such as Simplified Chinese, Traditional Chinese, and/or other Asian languages such as Japanese.Type: GrantFiled: April 26, 2007Date of Patent: June 4, 2013Assignee: Microsoft CorporationInventors: Shiun-Zu Kuo, Kevin E. Feige, Yifan Gong, Taro Miwa, Arun Chitrapu
-
Publication number: 20130006986Abstract: Automatically classifying content into a given project workspace is provided. New electronic mail items, documents, meeting requests, tasks, calendar items, and the like are automatically classified into a project workspace. Thus, a user is not required to engage in a time-consuming task of identifying, collecting, and associating such content with a given project workspace. In addition, feedback may be provided to the user on the quality of automatic assignments of content items to the desired workspace for editing content associated with the desired workspace and for improving the automatic classification process.Type: ApplicationFiled: June 28, 2011Publication date: January 3, 2013Applicant: MICROSOFT CORPORATIONInventors: Tu Huy Phan, Shiun-Zu Kuo, Nicholas Caldwell, Saliha Azzam
-
Patent number: 8185376Abstract: The language of origin of a word is determined by analyzing non-uniform letter sequence portions of the word.Type: GrantFiled: March 20, 2006Date of Patent: May 22, 2012Assignee: Microsoft CorporationInventors: Min Chu, Yi Ning Chen, Shiun-Zu Kuo, Xiaodong He, Megan Riley, Kevin E. Feige, Yifan Gong
-
Publication number: 20110179061Abstract: An analysis module, when triggered by a synchronization framework when a new data item is added to a project data store, runs a series of analysis feature extractors on the new content. An analysis may be conducted, and features of interest may be extracted from the data item. The analysis utilizes natural language processing, as well as other technologies, to provide an automatic or semi-automatic extraction of information. The extracted features of interest are saved as metadata within the project data store, and are associated with the data item from which it was extracted. The analysis module may be utilized to discover additional information that may be gleaned from content that is already in the project data store.Type: ApplicationFiled: June 18, 2010Publication date: July 21, 2011Applicant: Microsoft CorporationInventors: Venkat Pradeep Chilakamarri, Nicholas Caldwell, Saliha Azzam, Yizheng Cai, Benjamin Edward Childs, Arun Chitrapu, Steven Dimmick, Michael Gamon, Bernhard SJ Kohlmeier, Shiun-Zu Kuo, Jonathan C. Ludwig, Kimberly Manis, Courtney Anne O'Keefe, Diego Perez Del Carpio, Tu Huy Phan, Kevin Powell, Jignesh Shah, Ashish Sharma, Paulus Willem ter Horst, Mukta Pramod Walvekar, Ye-Yi Wang
-
Publication number: 20110179060Abstract: An automatic discovery of content to add to a data store for a project is disclosed. A data item may be parsed for data features that are contextually relevant to a given project or task. Discovered interesting data may be extracted and mapped to various search mechanisms. A search may be built and applied to various data sources to discover data items based on the contextually relevant data features. Search results from various search mechanisms may be displayed in a single user interface and may be presented to a user.Type: ApplicationFiled: June 18, 2010Publication date: July 21, 2011Applicant: Microsoft CorporationInventors: Venkat Pradeep Chilakamarri, Nicholas Caldwell, Saliha Azzam, Benjamin Edward Childs, Arun Chitrapu, Steven Dimmick, Bernhard SJ Kohlmeier, Shiun-Zu Kuo, Jonathan C. Ludwig, Kimberly Manis, Courtney Anne O'Keefe, Diego Perez Del Carpio, Tu Huy Phan, Kevin Powell, Jignesh Shah, Ashish Sharma, Paulus Willem ter Horst, Mukta Pramod Walvekar
-
Publication number: 20110179049Abstract: Project-related data may be aggregated from various data sources, given context, and may be stored in a data repository or organizational knowledge base that may be available to and accessed by others. Documents, emails, contact information, calendar data, social networking data, and any other content that is related to a project may be brought together within a single user interface, irrespective of its data type. A user may organize and understand content, discover relevant information, and act on it without regard to where the information resides or how it was created.Type: ApplicationFiled: June 18, 2010Publication date: July 21, 2011Applicant: Microsoft CorporationInventors: Nicholas Caldwell, Venkat Pradeep Chilakamarri, Saliha Azzam, Yizheng Cai, Michael Calcagno, Benjamin Edward Childs, Arun Chitrapu, Steven Dimmick, Michael Gamon, Bernhard SJ Kohlmeier, Shiun-Zu Kuo, Jonathan C. Ludwig, Kimberly Manis, Courtney Anne O'Keefe, Diego Perez Del Carpio, Tu Huy Phan, Kevin Powell, Jignesh Shah, Ashish Sharma, Paulus Willem ter Horst, Mukta Pramod Walvekar, Ye-Yi Wang
-
Publication number: 20080270118Abstract: Architecture for correcting incorrect recognition results in an Asian language speech recognition system. A spelling mode can be launched in response to receiving speech input, the spelling mode for correcting incorrect spelling of the recognition results or generating new words. Correction can be obtained using speech and/or manual selection and entry. The architecture facilitates correction in a single pass, rather than multiples times as in conventional systems. Words corrected using the spelling mode are corrected as a unit and treated as a word. The spelling mode applies to languages of at least the Asian continent, such as Simplified Chinese, Traditional Chinese, and/or other Asian languages such as Japanese.Type: ApplicationFiled: April 26, 2007Publication date: October 30, 2008Applicant: Microsoft CorporationInventors: Shiun-Zu Kuo, Kevin E. Feige, Yifan Gong, Taro Miwa, Arun Chitrapu
-
Publication number: 20070219777Abstract: The language of origin of a word is determined by analyzing non-uniform letter sequence portions of the word.Type: ApplicationFiled: March 20, 2006Publication date: September 20, 2007Applicant: Microsoft CorporationInventors: Min Chu, Yi Chen, Shiun-Zu Kuo, Xiaodong He, Megan Riley, Kevin Feige, Yifan Gong