Patent · US Active

Training a question-answer dialog system to avoid adversarial attacks

US11755657B2 · kind B2 · utility

0Cited by
1References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateSep 19, 2022
Grant dateSep 12, 2023
Priority date
Expiry dateSep 19, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N20/00
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A method, computer program product, and/or computer system generate a first adversarial statement via: (1) receiving a question and an original context for the question; (2) converting the question into a statement with a placeholder answer; (3) picking randomly an answer entity from a training text corpus; (4) replacing the placeholder answer with the randomly picked answer entity; and (5) leaving a correct question entity in the statement. The first adversarial statement is inserted into the original context to form a first adversarial context. The question and the first adversarial context as a first pair and the question and the original context as a second pair are input into a question-answer dialog system to train the question-answer dialog system.

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