Method and apparatus with model training and/or sequence recognition
A processor-implemented method includes: using an encoder, determining, for each of a plurality of tokens included in an input sequence, a self-attention weight based on a token and one or more tokens that precede the token in the input sequence; using the encoder, determining context information co...
Saved in:
Main Author | |
---|---|
Format | Patent |
Language | English |
Published |
11.10.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | A processor-implemented method includes: using an encoder, determining, for each of a plurality of tokens included in an input sequence, a self-attention weight based on a token and one or more tokens that precede the token in the input sequence; using the encoder, determining context information corresponding to the input sequence based on the determined self-attention weights; and using a decoder, determining an output sequence corresponding to the input sequence based on the determined context information. |
---|---|
Bibliography: | Application Number: US202016831206 |