Patent · US Active

Total correlation variational autoencoder strengthened with attentions for segmenting syntax and semantics

US11748567B2 · kind B2 · utility

0Cited by
3References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJul 10, 2020
Grant dateSep 5, 2023
Priority date
Expiry dateAug 7, 2040

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/044
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Described herein are embodiments of a framework named as total correlation variational autoencoder (TC_VAE) to disentangle syntax and semantics by making use of total correlation penalties of KL divergences. One or more Kullback-Leibler (KL) divergence terms in a loss for a variational autoencoder are discomposed so that generated hidden variables may be separated. Embodiments of the TC_VAE framework were examined on semantic similarity tasks and syntactic similarity tasks. Experimental results show that better disentanglement between syntactic and semantic representations have been achieved compared with state-of-the-art (SOTA) results on the same data sets in similar settings.

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