Patent · US Active

Machine learning systems and methods for many-hop fact extraction and claim verification

US12406150B2 · kind B2 · utility

0Cited by
1References
39Claims
0Family size

Assignee

Inventors

Key dates

Filing dateNov 24, 2021
Grant dateSep 2, 2025
Priority date
Expiry dateAug 24, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N5/045
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Machine learning (ML) systems and methods for fact extraction and claim verification are provided. The system receives a claim and retrieves a document from a dataset. The document has a first relatedness score higher than a first threshold, which indicates that ML models of the system determine that the document is most likely to be relevant to the claim. The dataset includes supporting documents and claims including a first group of claims supported by facts from more than two supporting documents and a second group of claims not supported by the supporting documents. The system selects a set of sentences from the document. The set of sentences have second relatedness scores higher than a second threshold, which indicate that the ML models determine that the set of sentences are most likely to be relevant to the claim. The system determines whether the claim includes facts from the set of sentences.

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