Patents by Inventor Hongjie Chai
Hongjie Chai 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: 11942082Abstract: Techniques described herein relate to facilitating end-to-end multilingual communications with automated assistants. In various implementations, speech recognition output may be generated based on voice input in a first language. A first language intent may be identified based on the speech recognition output and fulfilled in order to generate a first natural language output candidate in the first language. At least part of the speech recognition output may be translated to a second language to generate an at least partial translation, which may then be used to identify a second language intent that is fulfilled to generate a second natural language output candidate in the second language. Scores may be determined for the first and second natural language output candidates, and based on the scores, a natural language output may be selected for presentation.Type: GrantFiled: May 26, 2022Date of Patent: March 26, 2024Assignee: GOOGLE LLCInventors: James Kuczmarski, Vibhor Jain, Amarnag Subramanya, Nimesh Ranjan, Melvin Jose Johnson Premkumar, Vladimir Vuskovic, Luna Dai, Daisuke Ikeda, Nihal Sandeep Balani, Jinna Lei, Mengmeng Niu, Hongjie Chai, Wangqing Yuan
-
Publication number: 20230275900Abstract: A method for protecting against exposure to content violating a content policy, the method including receiving a number of content items including a first set of content items associated with a content group, determining a measurement associated with an amount of the first set of content items belonging to a specific content category, assigning one or more of the number of content items to be categorized by at least one of the machine learning algorithm or a manual review process, automatically applying the specific content category to one or more other content items of the content group such that the one or more other content items are not reviewed by the manual review process, and transmitting at least one of the number of content items, wherein the content category of each of the number of content items indicates whether the specific content item violates any content policies.Type: ApplicationFiled: February 13, 2023Publication date: August 31, 2023Inventors: Hongjie Chai, Vincent Zanotti, Bruce Feldman, Houman Alborzi, Robert Malkin, Girija Narlikar, Brianna Burr, Mark Russell
-
Patent number: 11582243Abstract: A method for protecting against exposure to content violating a content policy, the method including receiving a number of content items including a first set of content items associated with a content group, determining a measurement associated with an amount of the first set of content items belonging to a specific content category, assigning one or more of the number of content items to be categorized by at least one of the machine learning algorithm or a manual review process, automatically applying the specific content category to one or more other content items of the content group such that the one or more other content items are not reviewed by the manual review process, and transmitting at least one of the number of content items, wherein the content category of each of the number of content items indicates whether the specific content item violates any content policies.Type: GrantFiled: October 8, 2020Date of Patent: February 14, 2023Assignee: GOOGLE LLCInventors: Hongjie Chai, Vincent Zanotti, Bruce Feldman, Houman Alborzi, Robert Malkin, Girija Narlikar, Brianna Burr, Mark Russell
-
Publication number: 20220284198Abstract: Techniques described herein relate to facilitating end-to-end multilingual communications with automated assistants. In various implementations, speech recognition output may be generated based on voice input in a first language. A first language intent may be identified based on the speech recognition output and fulfilled in order to generate a first natural language output candidate in the first language. At least part of the speech recognition output may be translated to a second language to generate an at least partial translation, which may then be used to identify a second language intent that is fulfilled to generate a second natural language output candidate in the second language. Scores may be determined for the first and second natural language output candidates, and based on the scores, a natural language output may be selected for presentation.Type: ApplicationFiled: May 26, 2022Publication date: September 8, 2022Inventors: James Kuczmarski, Vibhor Jain, Amarnag Subramanya, Nimesh Ranjan, Melvin Jose Johnson Premkumar, Vladimir Vuskovic, Luna Dai, Daisuke Ikeda, Nihal Sandeep Balani, Jinna Lei, Mengmeng Niu, Hongjie Chai, Wangqing Yuan
-
Patent number: 11354521Abstract: Techniques described herein relate to facilitating end-to-end multilingual communications with automated assistants. In various implementations, speech recognition output may be generated based on voice input in a first language. A first language intent may be identified based on the speech recognition output and fulfilled in order to generate a first natural language output candidate in the first language. At least part of the speech recognition output may be translated to a second language to generate an at least partial translation, which may then be used to identify a second language intent that is fulfilled to generate a second natural language output candidate in the second language. Scores may be determined for the first and second natural language output candidates, and based on the scores, a natural language output may be selected for presentation.Type: GrantFiled: February 17, 2020Date of Patent: June 7, 2022Assignee: GOOGLE LLCInventors: James Kuczmarski, Vibhor Jain, Amarnag Subramanya, Nimesh Ranjan, Melvin Jose Johnson Premkumar, Vladimir Vuskovic, Luna Dai, Daisuke Ikeda, Nihal Sandeep Balani, Jinna Lei, Mengmeng Niu, Hongjie Chai, Wangqing Yuan
-
Publication number: 20220116402Abstract: A method for protecting against exposure to content violating a content policy, the method including receiving a number of content items including a first set of content items associated with a content group, determining a measurement associated with an amount of the first set of content items belonging to a specific content category, assigning one or more of the number of content items to be categorized by at least one of the machine learning algorithm or a manual review process, automatically applying the specific content category to one or more other content items of the content group such that the one or more other content items are not reviewed by the manual review process, and transmitting at least one of the number of content items, wherein the content category of each of the number of content items indicates whether the specific content item violates any content policies.Type: ApplicationFiled: October 8, 2020Publication date: April 14, 2022Applicant: GOOGLE LLCInventors: Hongjie Chai, Vincent Zanotti, Bruce Feldman, Houman Alborzi, Robert Malkin, Girija Narlikar, Brianna Burr, Mark Russell
-
Patent number: 11113481Abstract: Techniques described herein may serve to increase the language coverage of an automated assistant system, i.e. they may serve to increase the number of queries in one or more non-native languages for which the automated assistant is able to deliver reasonable responses. For example, techniques are described herein for training and utilizing a machine translation model to map a plurality of semantically-related natural language inputs in one language to one or more canonical translations in another language. In various implementations, the canonical translations may be selected and/or optimized for determining an intent of the speaker by the automated assistant, so that one or more responsive actions can be performed based on the speaker's intent. Put another way, the canonical translations may be specifically formatted for indicating the intent of the speaker to the automated assistant.Type: GrantFiled: May 2, 2019Date of Patent: September 7, 2021Assignee: GOOGLE LLCInventors: Melvin Jose Johnson Premkumar, Vladimir Vuskovic, James Kuczmarski, Hongjie Chai
-
Publication number: 20210064828Abstract: Techniques described herein may serve to increase the language coverage of an automated assistant system, i.e. they may serve to increase the number of queries in one or more non-native languages for which the automated assistant is able to deliver reasonable responses. For example, techniques are described herein for training and utilizing a machine translation model to map a plurality of semantically-related natural language inputs in one language to one or more canonical translations in another language. In various implementations, the canonical translations may be selected and/or optimized for determining an intent of the speaker by the automated assistant, so that one or more responsive actions can be performed based on the speaker's intent. Put another way, the canonical translations may be specifically formatted for indicating the intent of the speaker to the automated assistant.Type: ApplicationFiled: May 2, 2019Publication date: March 4, 2021Inventors: Melvin Jose Johnson Premkumar, Vladimir Vuskovic, James Kuczmarski, Hongjie Chai
-
Publication number: 20200184158Abstract: Techniques described herein relate to facilitating end-to-end multilingual communications with automated assistants. In various implementations, speech recognition output may be generated based on voice input in a first language. A first language intent may be identified based on the speech recognition output and fulfilled in order to generate a first natural language output candidate in the first language. At least part of the speech recognition output may be translated to a second language to generate an at least partial translation, which may then be used to identify a second language intent that is fulfilled to generate a second natural language output candidate in the second language. Scores may be determined for the first and second natural language output candidates, and based on the scores, a natural language output may be selected for presentation.Type: ApplicationFiled: February 17, 2020Publication date: June 11, 2020Inventors: James Kuczmarski, Vibhor Jain, Amarnag Subramanya, Nimesh Ranjan, Melvin Jose Johnson Premkumar, Vladimir Vuskovic, Luna Dai, Daisuke Ikeda, Nihal Sandeep Balani, Jinna Lei, Mengmeng Niu, Hongjie Chai, Wangqing Yuan