公开(公告)号：US10984784B2

公开(公告)日：2021-04-20

申请号：US16082175

申请日：2018-04-16

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: G10L15/00 ,  G10L15/183 ,  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.

公开(公告)号：US20210064828A1

公开(公告)日：2021-03-04

申请号：US16621578

申请日：2019-05-02

Applicant: Google LLC

Inventor： Melvin Jose Johnson Premkumar ,  Vladimir Vuskovic ,  James Kuczmarski ,  Hongjie Chai

IPC: G06F40/58 ,  G10L15/22 ,  G10L15/06 ,  G10L19/008 ,  G06F40/51 ,  G06F40/30

Abstract: 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.

公开(公告)号：US20200320984A1

公开(公告)日：2020-10-08

申请号：US16082175

申请日：2018-04-16

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 ,  G10L15/22 ,  G10L15/00

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：US20200184158A1

公开(公告)日：2020-06-11

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

IPC: G06F40/58 ,  G06F40/47 ,  G06F16/33 ,  G06F16/332 ,  H04L12/58 ,  G06N20/00 ,  G06K9/62

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：US20200034436A1

公开(公告)日：2020-01-30

申请号：US16521780

申请日：2019-07-25

Applicant: Google LLC

Inventor： Zhifeng Chen ,  Macduff Richard Hughes ,  Yonghui Wu ,  Michael Schuster ,  Xu Chen ,  Llion Owen Jones ,  Niki J. Parmar ,  George Foster ,  Orhan Firat ,  Ankur Bapna ,  Wolfgang Macherey ,  Melvin Jose Johnson Premkumar

IPC: G06F17/28 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for machine translation using neural networks. In some implementations, a text in one language is translated into a second language using a neural network model. The model can include an encoder neural network comprising a plurality of bidirectional recurrent neural network layers. The encoding vectors are processed using a multi-headed attention module configured to generate multiple attention context vectors for each encoding vector. A decoder neural network generates a sequence of decoder output vectors using the attention context vectors. The decoder output vectors can represent distributions over various language elements of the second language, allowing a translation of the text into the second language to be determined based on the sequence of decoder output vectors.