Patent · US Active

Processing text sequences using neural networks

US10354015B2 · kind B2 · utility

21Cited by
7References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJul 11, 2018
Grant dateJul 16, 2019
Priority date
Expiry dateJul 11, 2038

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L15/197
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for neural machine translation. In one aspect, a system is configured to receive an input sequence of source embeddings representing a source sequence of words in a source natural language and to generate an output sequence of target embeddings representing a target sequence of words that is a translation of the source sequence into a target natural language, the system comprising: a dilated convolutional neural network configured to process the input sequence of source embeddings to generate an encoded representation of the source sequence, and a masked dilated convolutional neural network configured to process the encoded representation of the source sequence to generate the output sequence of target embeddings.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.