Patent · US Active

Systems and methods for factual extraction from language model

US12112131B2 · kind B2 · utility

0Cited by
1References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJan 28, 2022
Grant dateOct 8, 2024
Priority date
Expiry dateMay 5, 2043

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/096
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Embodiments described herein provide a system and method for extracting factual information. The system transforms a query into a natural language prompt in a format of a query subject and a queried relation. The system encodes, via an embedding layer of a pre-trained language model, the natural language prompt into a first embedding. The system encodes, via the adapter model, the first embedding into a second embedding based on a probability that the second embedding returns the factual information when the second embedding is fed the first attention layer of the pre-trained language model. The system decodes, by the first attention layer of the pre-trained language mode, the second embedding into a response to the query. The system extracts the factual information from the decoded response to the query.

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