Patent · US Active

Natural language processing using a neural network

US10699060B2 · kind B2 · utility

26Cited by
7References
23Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJun 5, 2018
Grant dateJun 30, 2020
Priority date
Expiry dateAug 22, 2038

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06F40/58
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A system includes a neural network for performing a first natural language processing task. The neural network includes a first rectifier linear unit capable of executing an activation function on a first input related to a first word sequence, and a second rectifier linear unit capable of executing an activation function on a second input related to a second word sequence. A first encoder is capable of receiving the result from the first rectifier linear unit and generating a first task specific representation relating to the first word sequence, and a second encoder is capable of receiving the result from the second rectifier linear unit and generating a second task specific representation relating to the second word sequence. A biattention mechanism is capable of computing, based on the first and second task specific representations, an interdependent representation related to the first and second word sequences. In some embodiments, the first natural processing task performed by the neural network is one of sentiment classification and entailment classification.

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