Skip to main navigation Skip to search Skip to main content

Knowledge-grounded chatbot based on dual wasserstein generative adversarial networks with effective attention mechanisms

  • Kangwon National University
  • Electronics and Telecommunications Research Institute

Research output: Contribution to journal › Article › peer-review

23 Scopus citations

Abstract

A conversation is based on internal knowledge that the participants already know or external knowledge that they have gained during the conversation. A chatbot that communicates with humans by using its internal and external knowledge is called a knowledge-grounded chatbot. Although previous studies on knowledge-grounded chatbots have achieved reasonable performance, they may still generate unsuitable responses that are not associated with the given knowledge. To address this problem, we propose a knowledge-grounded chatbot model that effectively reflects the dialogue context and given knowledge by using well-designed attention mechanisms. The proposed model uses three kinds of attention: Query-context attention, query-knowledge attention, and context-knowledge attention. In our experiments with the Wizard-of-Wikipedia dataset, the proposed model showed better performances than the state-of-the-art model in a variety of measures.

Original languageEnglish
Article number3335
JournalApplied Sciences (Switzerland)
Volume10
Issue number9
DOIs
StatePublished - 1 May 2020

Keywords

  • Context-knowledge attention mechanism
  • Knowledge-grounded chatbot
  • Multi-turn chatbot

Fingerprint

Dive into the research topics of 'Knowledge-grounded chatbot based on dual wasserstein generative adversarial networks with effective attention mechanisms'. Together they form a unique fingerprint.

Cite this