Patent · US Active

Global normalized reader systems and methods

US10572595B2 · kind B2 · utility

0Cited by
5References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateSep 15, 2017
Grant dateFeb 25, 2020
Priority date
Expiry dateApr 13, 2038

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N7/01
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Presented herein are systems and methods for question answering (QA). In embodiments, extractive question answering (QA) is cast as an iterative search problem through the document's structure: select the answer's sentence, start word, and end word. This representation reduces the space of each search step and allows computation to be conditionally allocated to promising search paths. In embodiments, globally normalizing the decision process and back-propagating through beam search makes this representation viable and learning efficient. Various model embodiments, referred to as Globally Normalized Readers (GNR), achieve excellent performance. Also introduced are embodiments of data-augmentation to produce semantically valid examples by aligning named entities to a knowledge base and performing swaps new entities of the same type. This methodology also improved the performance of GNR models and is of independent interest for a variety of natural language processing (NLP) tasks.

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