Patent · US Active

N-best softmax smoothing for minimum bayes risk training of attention based sequence-to-sequence models

US11551136B2 · kind B2 · utility

0Cited by
3References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateNov 14, 2018
Grant dateJan 10, 2023
Priority date
Expiry dateNov 11, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/08
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A method and apparatus are provided that analyzing sequence-to-sequence data, such as sequence-to-sequence speech data or sequence-to-sequence machine translation data for example, by minimum Bayes risk (MBR) training a sequence-to-sequence model and within introduction of applications of softmax smoothing to an N-best generation of the MBR training of the sequence-to-sequence model.

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