Patent · US Active

Multi-scale model for semantic matching

US11295090B2 · kind B2 · utility

0Cited by
2References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateApr 27, 2020
Grant dateApr 5, 2022
Priority date
Expiry dateJun 4, 2040

Classification

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

Abstract

A method for applying a trained machine learning model to answer a user query comprises receiving a query text from a user. A previously-trained discriminator is received, the previously-trained discriminator configured to output, for a pair of sentences, a match value indicating a quality of semantic match between the pair of sentences. For each candidate answer text of a plurality of candidate answer texts, the previously-trained discriminator is operated to output a candidate match value for the query text and the candidate answer text based on comparing a first hierarchy of representations of the query text at increasing degrees of semantic compression to a second hierarchy of representations of the candidate answer text at increasing degrees of semantic compression. An answer text is output that is associated with a highest candidate match value among candidate match values.

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