Patent · US Active

Minimization of computational demands in model agnostic cross-lingual transfer with neural task representations as weak supervision

US11556776B2 · kind B2 · utility

0Cited by
2References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateOct 18, 2018
Grant dateJan 17, 2023
Priority date
Expiry dateSep 18, 2041

Classification

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

Abstract

A task agnostic framework for neural model transfer from a first language to a second language, that can minimize computational and monetary costs by accurately forming predictions in a model of the second language by relying on only a labeled data set in the first language, a parallel data set between both languages, a labeled loss function, and an unlabeled loss function. The models may be trained jointly or in a two-stage process.

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