Patent · US Active

Disentangle syntax and semantics in sentence representation with decomposable variational autoencoder

US12039270B2 · kind B2 · utility

0Cited by
3References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateAug 5, 2020
Grant dateJul 16, 2024
Priority date
Expiry dateFeb 26, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06F40/211
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Described herein are embodiments of a framework named decomposable variational autoencoder (DecVAE) to disentangle syntax and semantics by using total correlation penalties of Kullback-Leibler (KL) divergences. KL divergence term of the original VAE is decomposed such that the hidden variables generated may be separated in a clear-cut and interpretable way. Embodiments of DecVAE models are evaluated on various semantic similarity and syntactic similarity datasets. Experimental results show that embodiments of DecVAE models achieve state-of-the-art (SOTA) performance in disentanglement between syntactic and semantic representations.

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