- 专利标题: Depthwise separable convolutions for neural machine translation
-
申请号: US16688958申请日: 2019-11-19
-
公开(公告)号: US10853590B2公开(公告)日: 2020-12-01
- 发明人: Aidan Nicholas Gomez , Lukasz Mieczyslaw Kaiser , Francois Chollet
- 申请人: Google LLC
- 申请人地址: US CA Mountain View
- 专利权人: Google LLC
- 当前专利权人: Google LLC
- 当前专利权人地址: US CA Mountain View
- 代理机构: Fish & Richardson P.C.
- 主分类号: G10L25/30
- IPC分类号: G10L25/30 ; G06F40/58 ; G06F40/263 ; G06N3/04 ; G06N3/08
摘要:
Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing machine translation tasks. One method includes receiving an input text segment in an input language; processing the input text segment using an encoder neural network to generate an encoder neural network output, the encoder neural network comprising multiple depth wise separable convolutional neural network layers; processing the encoder neural network output using an autoregressive decoder neural network to generate a decoder neural network output; and processing the decoder neural network output to generate a predicted output text segment in a target natural language.
公开/授权文献
信息查询