- Patent Title: Attention-based decoder-only sequence transduction neural networks
-
Application No.: US18096946Application Date: 2023-01-13
-
Publication No.: US11886998B2Publication Date: 2024-01-30
- Inventor: Noam M. Shazeer , Lukasz Mieczyslaw Kaiser , Etienne Pot , Mohammad Saleh , Ben Goodrich , Peter J. Liu , Ryan Sepassi
- Applicant: Google LLC
- Applicant Address: US CA Mountain View
- Assignee: Google LLC
- Current Assignee: Google LLC
- Current Assignee Address: US CA Mountain View
- Agency: Fish & Richardson P.C.
- Main IPC: G06N3/08
- IPC: G06N3/08 ; G06N3/045

Abstract:
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.
Public/Granted literature
- US20230153613A1 ATTENTION-BASED DECODER-ONLY SEQUENCE TRANSDUCTION NEURAL NETWORKS Public/Granted day:2023-05-18
Information query