Teresa E Marshall

US Patent:

20210397799, Dec 23, 2021

Filed:

Aug 31, 2021

Appl. No.:

17/463227

Inventors:

- San Francisco CA, US
Raffaella Buschiazzo - San Francisco CA, US
James Bradbury - Mountain View CA, US
Teresa Anna Marshall - Sunnyvale CA, US
Caiming Xiong - Menlo Park CA, US
Richard Socher - Menlo Park CA, US

International Classification:

G06F 40/58

Abstract:

Approaches for the translation of structured text include an embedding module for encoding and embedding source text in a first language, an encoder for encoding output of the embedding module, a decoder for iteratively decoding output of the encoder based on generated tokens in translated text from previous iterations, a beam module for constraining output of the decoder with respect to possible embedded tags to include in the translated text for a current iteration using a beam search, and a layer for selecting a token to be included in the translated text for the current iteration. The translated text is in a second language different from the first language. In some embodiments, the approach further includes scoring and pointer modules for selecting the token based on the output of the beam module or copied from the source text or reference text from a training pair best matching the source text.