Hierarchical Prediction and Adversarial Learning for Conditional Response Generation

Yanran Li, Ruixiang Zhang, Wenjie Li, Ziqiang Cao

Research output: Journal article publicationJournal articleAcademic researchpeer-review

1 Citation (Scopus)

Abstract

There are a variety of underlying factors influencing what and how people communicate in their daily life. The ability to capture and utilize these factors enables the conversational systems to generate favorable responses and set up amicable connections with users. In this work, we investigate two major factors in response generation, i.e., emotion and intention. To explore the dependency between them, we develop a hierarchical variational model that predicts in sequence the emotion and intention to be conveyed in a response. The response can then be generated word-by-word based on the predictions. We also apply a novel adversarial-augmented inference network to facilitate model training. The experimental results demonstrate the effectiveness of the proposed model as well as the novel adversarial objective. The hypothesis that emotion shapes human communication behavior is also validated.

Original languageEnglish
Pages (from-to)314-327
Number of pages14
JournalIEEE Transactions on Knowledge and Data Engineering
Volume34
Issue number1
DOIs
Publication statusPublished - 1 Jan 2022

Keywords

  • Conversation model
  • Dialog system
  • Emotion and intention prediction
  • Response generation

ASJC Scopus subject areas

  • Information Systems
  • Computer Science Applications
  • Computational Theory and Mathematics

Fingerprint

Dive into the research topics of 'Hierarchical Prediction and Adversarial Learning for Conditional Response Generation'. Together they form a unique fingerprint.

Cite this