Toward Explainable Dialogue System Using Two-stage Response Generation

Shaobo Li, Chengjie Sun*, Zhen Xu, Prayag Tiwari*, Bingquan Liu, Deepak Gupta, K. Shankar, Zhenzhou Ji, Mingjiang Wang

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

4 Citations (Scopus)

Abstract

In recent years, neural networks have achieved impressive performance on dialogue response generation. However, most of these models still suffer from some shortcomings, such as yielding uninformative responses and lacking explainable ability. This article proposes a Two-stage Dialogue Response Generation model (TSRG), which specifies a method to generate diverse and informative responses based on an interpretable procedure between stages. TSRG involves a two-stage framework that generates a candidate response first and then instantiates it as the final response. The positional information and a resident token are injected into the candidate response to stabilize the multi-stage framework, alleviating the shortcomings in the multi-stage framework. Additionally, TSRG allows adjusting and interpreting the interaction pattern between the two generation stages, making the generation response somewhat explainable and controllable. We evaluate the proposed model on three dialogue datasets that contain millions of single-turn message-response pairs between web users. The results show that, compared with the previous multi-stage dialogue generation models, TSRG can produce more diverse and informative responses and maintain fluency and relevance.

Original languageEnglish
Article number3551869
JournalACM Transactions on Asian and Low-Resource Language Information Processing
Volume22
Issue number3
DOIs
Publication statusPublished - 10 Mar 2023
MoE publication typeA1 Journal article-refereed

Keywords

  • Asian language
  • explainable text generation
  • Natural language processing
  • neural response generation

Fingerprint

Dive into the research topics of 'Toward Explainable Dialogue System Using Two-stage Response Generation'. Together they form a unique fingerprint.

Cite this