Patent · US Active

Representation learning for input classification via topic sparse autoencoder and entity embedding

US11615311B2 · kind B2 · utility

0Cited by
1References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateNov 21, 2019
Grant dateMar 28, 2023
Priority date
Expiry dateSep 8, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/09
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Described herein are embodiments of a unified neural network framework to integrate Topic modeling, Word embedding and Entity Embedding (TWEE) for representation learning of inputs. In one or more embodiments, a novel topic sparse autoencoder is introduced to incorporate discriminative topics into the representation learning of the input. Topic distributions of inputs are generated from a global viewpoint and are utilized to enable autoencoder to learn topical representations. A sparsity constraint may be added to ensure that the most discriminative representations are related to topics. In addition, both words and entity related information may be embedded into the network to help learn a more comprehensive input representation. Extensive empirical experiments show that embodiments of the TWEE framework outperform the state-of-the-art methods on different datasets.

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