- 专利标题: ATTENTION-BASED DECODER-ONLY SEQUENCE TRANSDUCTION NEURAL NETWORKS
-
申请号: US18096946申请日: 2023-01-13
-
公开(公告)号: US20230153613A1公开(公告)日: 2023-05-18
- 发明人: Noam M. Shazeer , Lukasz Mieczyslaw Kaiser , Etienne Pot , Mohammad Saleh , Ben Goodrich , Peter J. Liu , Ryan Sepassi
- 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
- 主分类号: G06N3/08
- IPC分类号: G06N3/08 ; G06N3/045
摘要:
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an output sequence from an input sequence. One of the methods includes, at each of a plurality of generation time steps: generating a combined sequence for the generation time step that includes the input sequence followed by the output tokens that have already been generated as of the generation time step; processing the combined sequence using a self-attention decoder neural network to generate a time step output that defines a score distribution over a set of possible output tokens; and selecting, using the time step output, an output token from the set of possible output tokens as the next output token in the output sequence.
公开/授权文献
信息查询