Publication Type
Journal Article
Version
publishedVersion
Publication Date
10-2021
Abstract
The consistency of a response to a given post at the semantic level and emotional level is essential for a dialogue system to deliver humanlike interactions. However, this challenge is not well addressed in the literature, since most of the approaches neglect the emotional information conveyed by a post while generating responses. This article addresses this problem and proposes a unified end-to-end neural architecture, which is capable of simultaneously encoding the semantics and the emotions in a post and leveraging target information to generate more intelligent responses with appropriately expressed emotions. Extensive experiments on real-world data demonstrate that the proposed method outperforms the state-of-the-art methods in terms of both content coherence and emotion appropriateness.
Keywords
Dialogue generation, emotional conversation, emotional chatbot
Discipline
Databases and Information Systems | Programming Languages and Compilers
Research Areas
Data Science and Engineering
Publication
ACM Transactions on Information Systems
Volume
39
Issue
4
First Page
1
Last Page
24
ISSN
1046-8188
Identifier
10.1145/3456414
Publisher
Association for Computing Machinery (ACM)
Citation
WEI, Wei; MAO, Xianling; GUO, Guibing; ZHU, Feida; ZHU, Feida; HU, Yuchong; and FENG, Shanshan.
Target-guided emotion-aware chat machine. (2021). ACM Transactions on Information Systems. 39, (4), 1-24.
Available at: https://ink.library.smu.edu.sg/sis_research/6721
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.