Retrieve, Discriminate and Rewrite: A Simple and Effective Framework for Obtaining Affective Response in Retrieval-Based Chatbots

Xin Lu, Yijian Tian, Yanyan Zhao, Bing Qin


Abstract
Obtaining affective response is a key step in building empathetic dialogue systems. This task has been studied a lot in generation-based chatbots, but the related research in retrieval-based chatbots is still in the early stage. Existing works in retrieval-based chatbots are based on Retrieve-and-Rerank framework, which have a common problem of satisfying affect label at the expense of response quality. To address this problem, we propose a simple and effective Retrieve-Discriminate-Rewrite framework. The framework replaces the reranking mechanism with a new discriminate-and-rewrite mechanism, which predicts the affect label of the retrieved high-quality response via discrimination module and further rewrites the affect unsatisfied response via rewriting module. This can not only guarantee the quality of the response, but also satisfy the given affect label. In addition, another challenge for this line of research is the lack of an off-the-shelf affective response dataset. To address this problem and test our proposed framework, we annotate a Sentimental Douban Conversation Corpus based on the original Douban Conversation Corpus. Experimental results show that our proposed framework is effective and outperforms competitive baselines.
Anthology ID:
2021.findings-emnlp.168
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1956–1969
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.168
DOI:
10.18653/v1/2021.findings-emnlp.168
Bibkey:
Cite (ACL):
Xin Lu, Yijian Tian, Yanyan Zhao, and Bing Qin. 2021. Retrieve, Discriminate and Rewrite: A Simple and Effective Framework for Obtaining Affective Response in Retrieval-Based Chatbots. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 1956–1969, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Retrieve, Discriminate and Rewrite: A Simple and Effective Framework for Obtaining Affective Response in Retrieval-Based Chatbots (Lu et al., Findings 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.168.pdf
Video:
 https://aclanthology.org/2021.findings-emnlp.168.mp4
Data
DoubanDouban Conversation Corpus