Applying Emotional Keyphrase Correlation for Diversity Enhancement in Empathetic Dialogue Response Generation

Jeremy Chang, Chung Hsien Wu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Developing an empathetic dialogue system has been facing challenges for years. Although most of the responses generated from the existing empathetic dialogue systems are to some extent grammatical and emotional, they are still far from human standards. The system-generated responses are usually uncorrelated to the user's emotional contexts. In this paper, we propose an approach to automatic extraction of the emotional keyphrases from the context, then the emotional keyphrases are fed into the Conditional Transformer language model as the conditional information. We also design a loss function called Keyphrase Correlation (KPC) to guide the model to generate responses with relevant emotional keyphrases. As a result, the diversity of the generated responses is highly enhanced. The experimental results also verified the effectiveness in terms of empathy capability and emotional correlation in the user-system conversation.

Original languageEnglish
Title of host publication2022 International Conference on Asian Language Processing, IALP 2022
EditorsRong Tong, Yanfeng Lu, Minghui Dong, Wengao Gong, Haizhou Li
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages286-291
Number of pages6
ISBN (Electronic)9781665476744
DOIs
Publication statusPublished - 2022
Event2022 International Conference on Asian Language Processing, IALP 2022 - Singapore, Singapore
Duration: 2022 Oct 272022 Oct 28

Publication series

Name2022 International Conference on Asian Language Processing, IALP 2022

Conference

Conference2022 International Conference on Asian Language Processing, IALP 2022
Country/TerritorySingapore
CitySingapore
Period22-10-2722-10-28

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Science Applications
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'Applying Emotional Keyphrase Correlation for Diversity Enhancement in Empathetic Dialogue Response Generation'. Together they form a unique fingerprint.

Cite this