Patent · US Active

Cold fusing sequence-to-sequence models with language models

US11620986B2 · kind B2 · utility

2Cited by
12References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateOct 1, 2020
Grant dateApr 4, 2023
Priority date
Expiry dateOct 1, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L15/16
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Described herein are systems and methods for generating natural language sentences with Sequence-to-sequence (Seq2Seq) models with attention. The Seq2Seq models may be implemented in applications, such as machine translation, image captioning, and speech recognition. Performance has further been improved by leveraging unlabeled data, often in the form of a language models. Disclosed herein are “Cold Fusion” architecture embodiments that leverage a pre-trained language model during training. The Seq2Seq models with Cold Fusion embodiments are able to better utilize language information enjoying faster convergence, better generalization, and almost complete transfer to a new domain while using less labeled training data.

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