@inproceedings{cai-etal-2023-improving,
title = "Improving Empathetic Dialogue Generation by Dynamically Infusing Commonsense Knowledge",
author = "Cai, Hua and
Shen, Xuli and
Xu, Qing and
Shen, Weilin and
Wang, Xiaomei and
Ge, Weifeng and
Zheng, Xiaoqing and
Xue, Xiangyang",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.498",
doi = "10.18653/v1/2023.findings-acl.498",
pages = "7858--7873",
abstract = "In empathetic conversations, individuals express their empathy towards others. Previous work has mainly focused on generating empathetic responses by utilizing the speaker{'}s emotion. Besides, external commonsense knowledge has been applied to enhance the system{'}s understandings of the speaker{'}s situation. However, given an event, commonsense knowledge base contains various relations, potentially leading to confusion for the dialogue system. Consequently, inconsistencies arise among the emotion, generated response and speaker{'}s contextual information. To this end, we propose a novel approach for empathetic response generation, which incorporates an adaptive module for commonsense knowledge selection to ensure consistency between the generated empathetic responses and the speaker{'}s situation. This selected knowledge is used to refine the commonsense cognition and empathy expression for generated responses. Experimental results show that our approach significantly outperforms baseline models in both automatic and human evaluations, exhibiting the generation of more coherent and empathetic responses. Moreover, case studies highlight the interpretability of knowledge selection in the responses and the effectiveness of adaptive module in our model. Code: \url{https://github.com/Hanscal/DCKS}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cai-etal-2023-improving">
<titleInfo>
<title>Improving Empathetic Dialogue Generation by Dynamically Infusing Commonsense Knowledge</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuli</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qing</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weilin</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaomei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weifeng</namePart>
<namePart type="family">Ge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoqing</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangyang</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In empathetic conversations, individuals express their empathy towards others. Previous work has mainly focused on generating empathetic responses by utilizing the speaker’s emotion. Besides, external commonsense knowledge has been applied to enhance the system’s understandings of the speaker’s situation. However, given an event, commonsense knowledge base contains various relations, potentially leading to confusion for the dialogue system. Consequently, inconsistencies arise among the emotion, generated response and speaker’s contextual information. To this end, we propose a novel approach for empathetic response generation, which incorporates an adaptive module for commonsense knowledge selection to ensure consistency between the generated empathetic responses and the speaker’s situation. This selected knowledge is used to refine the commonsense cognition and empathy expression for generated responses. Experimental results show that our approach significantly outperforms baseline models in both automatic and human evaluations, exhibiting the generation of more coherent and empathetic responses. Moreover, case studies highlight the interpretability of knowledge selection in the responses and the effectiveness of adaptive module in our model. Code: https://github.com/Hanscal/DCKS.</abstract>
<identifier type="citekey">cai-etal-2023-improving</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.498</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.498</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>7858</start>
<end>7873</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Empathetic Dialogue Generation by Dynamically Infusing Commonsense Knowledge
%A Cai, Hua
%A Shen, Xuli
%A Xu, Qing
%A Shen, Weilin
%A Wang, Xiaomei
%A Ge, Weifeng
%A Zheng, Xiaoqing
%A Xue, Xiangyang
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F cai-etal-2023-improving
%X In empathetic conversations, individuals express their empathy towards others. Previous work has mainly focused on generating empathetic responses by utilizing the speaker’s emotion. Besides, external commonsense knowledge has been applied to enhance the system’s understandings of the speaker’s situation. However, given an event, commonsense knowledge base contains various relations, potentially leading to confusion for the dialogue system. Consequently, inconsistencies arise among the emotion, generated response and speaker’s contextual information. To this end, we propose a novel approach for empathetic response generation, which incorporates an adaptive module for commonsense knowledge selection to ensure consistency between the generated empathetic responses and the speaker’s situation. This selected knowledge is used to refine the commonsense cognition and empathy expression for generated responses. Experimental results show that our approach significantly outperforms baseline models in both automatic and human evaluations, exhibiting the generation of more coherent and empathetic responses. Moreover, case studies highlight the interpretability of knowledge selection in the responses and the effectiveness of adaptive module in our model. Code: https://github.com/Hanscal/DCKS.
%R 10.18653/v1/2023.findings-acl.498
%U https://aclanthology.org/2023.findings-acl.498
%U https://doi.org/10.18653/v1/2023.findings-acl.498
%P 7858-7873
Markdown (Informal)
[Improving Empathetic Dialogue Generation by Dynamically Infusing Commonsense Knowledge](https://aclanthology.org/2023.findings-acl.498) (Cai et al., Findings 2023)
ACL
- Hua Cai, Xuli Shen, Qing Xu, Weilin Shen, Xiaomei Wang, Weifeng Ge, Xiaoqing Zheng, and Xiangyang Xue. 2023. Improving Empathetic Dialogue Generation by Dynamically Infusing Commonsense Knowledge. In Findings of the Association for Computational Linguistics: ACL 2023, pages 7858–7873, Toronto, Canada. Association for Computational Linguistics.