-
1.
公开(公告)号:US20200104746A1
公开(公告)日:2020-04-02
申请号:US16611725
申请日:2018-12-14
申请人: Google LLC
发明人: Brian Strope , Yun-hsuan Sung , Wangqing Yuan
IPC分类号: G06N20/00 , G06F16/33 , G06F16/35 , G06F16/332 , G06N5/04
摘要: Systems, methods, and computer readable media related to: training an encoder model that can be utilized to determine semantic similarity of a natural language textual string to each of one or more additional natural language textual strings (directly and/or indirectly); and/or using a trained encoder model to determine one or more responsive actions to perform in response to a natural language query. The encoder model is a machine learning model, such as a neural network model. In some implementations of training the encoder model, the encoder model is trained as part of a larger network architecture trained based on one or more tasks that are distinct from a “semantic textual similarity” task for which the encoder model can be used.
-
公开(公告)号:US20190197101A1
公开(公告)日:2019-06-27
申请号:US15852916
申请日:2017-12-22
申请人: Google LLC
发明人: Paul Roland Lambert , Timothy Youngjin Sohn , Jacqueline Amy Tsay , Gagan Bansal , Cole Austin Bevis , Kaushik Roy , Justin Tzi-jay LU , Katherine Anna Evans , Tobias Bosch , Yinan Wang , Matthew Vincent Dierker , Gregory Russell Bullock , Ettore Randazzo , Tobias Kaufmann , Yonghui Wu , Benjamin N. Lee , Xu Chen , Brian Strope , Yun-hsuan Sung , Do Kook Choe , Rami Eid Sammour Al-Rfou'
IPC分类号: G06F17/27 , G06F3/0484 , G06N99/00
CPC分类号: G06F17/276 , G06F3/0237 , G06F3/04842 , G06F17/273 , G06F17/274 , G06F17/277 , G06F17/2785 , G06F21/6245 , G06N20/00
摘要: A computing system is described that includes user interface components configured to receive typed user input; and one or more processors. The one or more processors are configured to: receive, by a computing system and at a first time, a first portion of text typed by a user in an electronic message being edited; predict, based on the first portion of text, a first candidate portion of text to follow the first portion of text; output, for display, the predicted first candidate portion of text for optional selection to append to the first portion of text; determine, at a second time that is after the first time, that the electronic message is directed to a sensitive topic; and responsive to determining that the electronic message is directed to a sensitive topic, refrain from outputting subsequent candidate portions of text for optional selection to append to text in the electronic message.
-
公开(公告)号:US10783456B2
公开(公告)日:2020-09-22
申请号:US16611725
申请日:2018-12-14
申请人: Google LLC
发明人: Brian Strope , Yun-hsuan Sung , Wangqing Yuan
IPC分类号: G06N20/00 , G06F16/35 , G06F16/332 , G06F16/33 , G06N5/04
摘要: Systems, methods, and computer readable media related to: training an encoder model that can be utilized to determine semantic similarity of a natural language textual string to each of one or more additional natural language textual strings (directly and/or indirectly); and/or using a trained encoder model to determine one or more responsive actions to perform in response to a natural language query. The encoder model is a machine learning model, such as a neural network model. In some implementations of training the encoder model, the encoder model is trained as part of a larger network architecture trained based on one or more tasks that are distinct from a “semantic textual similarity” task for which the encoder model can be used.
-
公开(公告)号:US12086720B2
公开(公告)日:2024-09-10
申请号:US17502343
申请日:2021-10-15
申请人: Google LLC
摘要: Systems, methods, and computer readable media related to information retrieval. Some implementations are related to training and/or using a relevance model for information retrieval. The relevance model includes an input neural network model and a subsequent content neural network model. The input neural network model and the subsequent content neural network model can be separate, but trained and/or used cooperatively. The input neural network model and the subsequent content neural network model can be “separate” in that separate inputs are applied to the neural network models, and each of the neural network models is used to generate its own feature vector based on its applied input. A comparison of the feature vectors generated based on the separate network models can then be performed, where the comparison indicates relevance of the input applied to the input neural network model to the separate input applied to the subsequent content neural network model.
-
公开(公告)号:US20220036197A1
公开(公告)日:2022-02-03
申请号:US17502343
申请日:2021-10-15
申请人: Google LLC
IPC分类号: G06N3/08 , G06N5/04 , G06F16/00 , G06N3/04 , G06F16/335
摘要: Systems, methods, and computer readable media related to information retrieval. Some implementations are related to training and/or using a relevance model for information retrieval. The relevance model includes an input neural network model and a subsequent content neural network model. The input neural network model and the subsequent content neural network model can be separate, but trained and/or used cooperatively. The input neural network model and the subsequent content neural network model can be “separate” in that separate inputs are applied to the neural network models, and each of the neural network models is used to generate its own feature vector based on its applied input. A comparison of the feature vectors generated based on the separate network models can then be performed, where the comparison indicates relevance of the input applied to the input neural network model to the separate input applied to the subsequent content neural network model.
-
公开(公告)号:US11238211B2
公开(公告)日:2022-02-01
申请号:US16978658
申请日:2019-03-14
申请人: Google LLC
发明人: Jan van de Kerkhof , Balint Miklos , Amr Abdelfattah , Tobias Kaufmann , László Lukacs , Bjarke Ebert , Victor Anchidin , Brian Strope , Heeyoung Lee , Yun-hsuan Sung , Noah Constant , Neil Smith
IPC分类号: G06F17/00 , G06F40/134 , G06F40/166 , G06F40/30
摘要: A system may use a machine-learned model to determine whether to classify a sequence of one or more words within a first document that is being edited as a candidate hyperlink based at least in part on context associated with the first document. In response to classifying the sequence of one or more words as the candidate hyperlink, the system may use the machine-learned model and based at least in part on the sequence of one or more words and the context to determine one or more candidate document to be hyperlinked from the sequence of one or more words. In response to receiving an indication of a second document being selected out of the one or more candidate documents, the system may modify the first document to associate the sequence of one or more words with a hyperlink to the second document.
-
公开(公告)号:US11842253B2
公开(公告)日:2023-12-12
申请号:US16995149
申请日:2020-08-17
申请人: Google LLC
发明人: Brian Strope , Yun-hsuan Sung , Wangqing Yuan
IPC分类号: G06N20/00 , G06F16/35 , G06F16/332 , G06F16/33 , G06N5/04
CPC分类号: G06N20/00 , G06F16/3329 , G06F16/3344 , G06F16/3346 , G06F16/35 , G06N5/04
摘要: Systems, methods, and computer readable media related to: training an encoder model that can be utilized to determine semantic similarity of a natural language textual string to each of one or more additional natural language textual strings (directly and/or indirectly); and/or using a trained encoder model to determine one or more responsive actions to perform in response to a natural language query. The encoder model is a machine learning model, such as a neural network model. In some implementations of training the encoder model, the encoder model is trained as part of a larger network architecture trained based on one or more tasks that are distinct from a “semantic textual similarity” task for which the encoder model can be used.
-
公开(公告)号:US20230385543A1
公开(公告)日:2023-11-30
申请号:US18447186
申请日:2023-08-09
申请人: Google LLC
发明人: Paul Roland Lambert , Timothy Youngjin Sohn , Jacqueline Amy Tsay , Gagan Bansal , Cole Austin Bevis , Kaushik Roy , Justin Tzi-jay LU , Katherine Anna Evans , Tobias Bosch , Yinan Wang , Matthew Vincent Dierker , Greg Russell Bullock , Ettore Randazzo , Tobias Kaufmann , Yonghui Wu , Benjamin N. Lee , Xu Chen , Brian Strope , Yun-hsuan Sung , Do Kook Choe , Rami Eid Sammour Al-Rfou'
IPC分类号: G06F40/274 , G06F3/04842 , G06N20/00 , G06F21/62 , G06F3/023 , G06F40/30 , G06F40/232 , G06F40/253 , G06F40/284
CPC分类号: G06F40/274 , G06F3/04842 , G06N20/00 , G06F21/6245 , G06F40/284 , G06F40/30 , G06F40/232 , G06F40/253 , G06F3/0237
摘要: A computing system is described that includes user interface components configured to receive typed user input; and one or more processors. The one or more processors are configured to: receive, by a computing system and at a first time, a first portion of text typed by a user in an electronic message being edited; predict, based on the first portion of text, a first candidate portion of text to follow the first portion of text; output, for display, the predicted first candidate portion of text for optional selection to append to the first portion of text; determine, at a second time that is after the first time, that the electronic message is directed to a sensitive topic; and responsive to determining that the electronic message is directed to a sensitive topic, refrain from outputting subsequent candidate portions of text for optional selection to append to text in the electronic message.
-
公开(公告)号:US11755834B2
公开(公告)日:2023-09-12
申请号:US15852916
申请日:2017-12-22
申请人: Google LLC
发明人: Paul Roland Lambert , Timothy Youngjin Sohn , Jacqueline Amy Tsay , Gagan Bansal , Cole Austin Bevis , Kaushik Roy , Justin Tzi-jay Lu , Katherine Anna Evans , Tobias Bosch , Yinan Wang , Matthew Vincent Dierker , Gregory Russell Bullock , Ettore Randazzo , Tobias Kaufmann , Yonghui Wu , Benjamin N. Lee , Xu Chen , Brian Strope , Yun-hsuan Sung , Do Kook Choe , Rami Eid Sammouf Al-Rfou'
IPC分类号: G06F40/274 , G06F3/04842 , G06N20/00 , G06F21/62 , G06F3/023 , G06F40/30 , G06F40/232 , G06F40/253 , G06F40/284
CPC分类号: G06F40/274 , G06F3/0237 , G06F3/04842 , G06F21/6245 , G06F40/232 , G06F40/253 , G06F40/284 , G06F40/30 , G06N20/00
摘要: A computing system is described that includes user interface components configured to receive typed user input; and one or more processors. The one or more processors are configured to: receive, by a computing system and at a first time, a first portion of text typed by a user in an electronic message being edited; predict, based on the first portion of text, a first candidate portion of text to follow the first portion of text; output, for display, the predicted first candidate portion of text for optional selection to append to the first portion of text; determine, at a second time that is after the first time, that the electronic message is directed to a sensitive topic; and responsive to determining that the electronic message is directed to a sensitive topic, refrain from outputting subsequent candidate portions of text for optional selection to append to text in the electronic message.
-
10.
公开(公告)号:US20200380418A1
公开(公告)日:2020-12-03
申请号:US16995149
申请日:2020-08-17
申请人: Google LLC
发明人: Brian Strope , Yun-hsuan Sung , Wangqing Yuan
IPC分类号: G06N20/00 , G06F16/35 , G06F16/332 , G06F16/33 , G06N5/04
摘要: Systems, methods, and computer readable media related to: training an encoder model that can be utilized to determine semantic similarity of a natural language textual string to each of one or more additional natural language textual strings (directly and/or indirectly); and/or using a trained encoder model to determine one or more responsive actions to perform in response to a natural language query. The encoder model is a machine learning model, such as a neural network model. In some implementations of training the encoder model, the encoder model is trained as part of a larger network architecture trained based on one or more tasks that are distinct from a “semantic textual similarity” task for which the encoder model can be used.
-
-
-
-
-
-
-
-
-