-
公开(公告)号：US20210026846A1
公开(公告)日：2021-01-28
申请号：US16949076
申请日：2020-10-13
Applicant: GOOGLE LLC
Inventor： Amarnag Subramanya , Fernando Pereira , Ni Lao , John Blitzer , Rahul Gupta
IPC: G06F16/245
Abstract: Implementations include systems and methods for querying a data graph. An example method includes receiving a machine learning module trained to produce a model with multiple features for a query, each feature representing a path in a data graph. The method also includes receiving a search query that includes a first search term, mapping the search query to the query, and mapping the first search term to a first entity in the data graph. The method may also include identifying a second entity in the data graph using the first entity and at least one of the multiple weighted features, and providing information relating to the second entity in a response to the search query. Some implementations may also include training the machine learning module by, for example, generating positive and negative training examples from an answer to a query.
-
公开(公告)号：US10452694B2
公开(公告)日：2019-10-22
申请号：US15849212
申请日：2017-12-20
Applicant: Google LLC
Inventor： Wei Lwun Lu , Denis Savenkov , Amarnag Subramanya , Jeffrey Dalton , Evgeniy Gabrilovich , Eugene Agichtein
IPC: G06F17/00 , G06F16/332 , G06F17/27
Abstract: Methods, systems, and apparatus for obtaining a resource, identifying a first portion of text of the resource that is characterized as a question, and a second part of text of the resource that is characterized as an answer to the question, identifying an entity that is referenced by one or more terms of the text that is characterized as the question, a relationship type that is referenced by one or more other terms of the text that is characterized as the question, and an entity that is referenced by the text that is characterized as the answer to the question, and adjusting a score for a relationship of the relationship type for the entity that is referenced by the one or more terms of the text that is characterized as the question and the entity that is referenced by the text that is characterized as the answer to the question.
-
公开(公告)号：US11942082B2
公开(公告)日：2024-03-26
申请号：US17825778
申请日：2022-05-26
Applicant: GOOGLE LLC
Inventor： 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
IPC: G06F40/47 , G06F16/33 , G06F16/332 , G06F18/22 , G06F40/58 , G06N20/00 , G10L15/00 , G10L15/183 , G10L15/22 , H04L51/02
CPC classification number: G10L15/183 , G06F16/3329 , G06F16/3337 , G06F18/22 , G06F40/47 , G06F40/58 , G06N20/00 , G10L15/005 , G10L15/22 , H04L51/02
Abstract: 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.
-
公开(公告)号：US11875788B2
公开(公告)日：2024-01-16
申请号：US17211488
申请日：2021-03-24
Applicant: Google LLC
Inventor： 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
IPC: G06F40/00 , G10L15/183 , G10L15/00 , G10L15/22 , G06F16/33 , G06N20/00 , G06F16/332 , G06F40/47 , G06F40/58 , H04L51/02 , G06F18/22
CPC classification number: G10L15/183 , G06F16/3329 , G06F16/3337 , G06F18/22 , G06F40/47 , G06F40/58 , G06N20/00 , G10L15/005 , G10L15/22 , H04L51/02
Abstract: 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.
-
公开(公告)号：US20220284198A1
公开(公告)日：2022-09-08
申请号：US17825778
申请日：2022-05-26
Applicant: GOOGLE LLC
Inventor： 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
Abstract: 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.
-
Patent Agency Ranking
公开(公告)号：US20180267948A1
公开(公告)日：2018-09-20
申请号：US15981055
申请日：2018-05-16
Applicant: Google LLC
Inventor： Amarnag Subramanya , Edgar Gonzalez Pellicer , Shalini Agarwal
CPC classification number: G06F17/243 , G06F17/241 , G06F17/274 , G06F17/2765 , G06Q10/107 , G06Q10/1097 , H04L51/08 , H04M1/72552
Abstract: Methods and apparatus are described herein for identifying tasks in messages. In various implementations, natural language processing may be performed on a received message to generate an annotated message. The annotated message may be analyzed pursuant to a grammar. A portion of the message may be classified as a user task entry based on the analysis of the annotated message.
-
公开(公告)号：US20180150468A1
公开(公告)日：2018-05-31
申请号：US15849212
申请日：2017-12-20
Applicant: Google LLC
Inventor： Wei Lwun Lu , Denis Savenkov , Amarnag Subramanya , Jeffrey Dalton , Evgeniy Gabrilovich , Eugene Agichtein
CPC classification number: G06F16/3322 , G06F17/2705 , G06F17/2785
Abstract: Methods, systems, and apparatus for obtaining a resource, identifying a first portion of text of the resource that is characterized as a question, and a second part of text of the resource that is characterized as an answer to the question, identifying an entity that is referenced by one or more terms of the text that is characterized as the question, a relationship type that is referenced by one or more other terms of the text that is characterized as the question, and an entity that is referenced by the text that is characterized as the answer to the question, and adjusting a score for a relationship of the relationship type for the entity that is referenced by the one or more terms of the text that is characterized as the question and the entity that is referenced by the text that is characterized as the answer to the question.
-
公开(公告)号：US11915692B2
公开(公告)日：2024-02-27
申请号：US17211488
申请日：2021-03-24
Applicant: Google LLC
Inventor： 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
IPC: G06F40/00 , G10L15/183 , G10L15/00 , G10L15/22 , G06F16/33 , G06N20/00 , G06F16/332 , G06F40/47 , G06F40/58 , H04L51/02 , G06F18/22
CPC classification number: G10L15/183 , G06F16/3329 , G06F16/3337 , G06F18/22 , G06F40/47 , G06F40/58 , G06N20/00 , G10L15/005 , G10L15/22 , H04L51/02
Abstract: 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.
-
公开(公告)号：US11354521B2
公开(公告)日：2022-06-07
申请号：US16792572
申请日：2020-02-17
Applicant: Google LLC
Inventor： 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
Abstract: 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.
-
公开(公告)号：US20210210076A1
公开(公告)日：2021-07-08
申请号：US17211488
申请日：2021-03-24
Applicant: Google LLC
Inventor： 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
IPC: G10L15/183 , G10L15/00 , G10L15/22
Abstract: 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.
-
-
-
-
-
-
-
-
-
Search Results
14
records
(took 0.017 seconds)
