Patent · US Active

Constituent centric architecture for reading comprehension

US10706234B2 · kind B2 · utility

0Cited by
4References
16Claims
0Family size

Assignee

Inventors

Key dates

Filing dateApr 9, 2018
Grant dateJul 7, 2020
Priority date
Expiry dateAug 2, 2038

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N5/04
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A constituent-centric neural architecture for reading comprehension is disclosed. One embodiment provides a method that performs reading comprehension comprising encoding individual constituents from a text passage using a chain of trees long short-term encoding, encodes question related to the text passage using a tree long short-term memory encoding, generates a question-aware representation for each constituent in the passage using a tree-guided attention mechanism, generates a plurality of candidate answers from the question-aware representation using hierarchical relations among constituents, and predicts an answer to the question in relation to the text passage using a feed-forward network. Other embodiments are disclosed herein.

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