@inproceedings{gong-etal-2023-eliciting,
title = "Eliciting Rich Positive Emotions in Dialogue Generation",
author = "Gong, Ziwei and
Min, Qingkai and
Zhang, Yue",
editor = "Chawla, Kushal and
Shi, Weiyan",
booktitle = "Proceedings of the First Workshop on Social Influence in Conversations (SICon 2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.sicon-1.1",
doi = "10.18653/v1/2023.sicon-1.1",
pages = "1--8",
abstract = "Positive emotion elicitation aims at evoking positive emotion states in human users in open-domain dialogue generation. However, most work focuses on inducing a single-dimension of positive sentiment using human annotated datasets, which limits the scale of the training dataset. In this paper, we propose to model various emotions in large unannotated conversations, such as joy, trust and anticipation, by leveraging a latent variable to control the emotional intention of the response. Our proposed emotion-eliciting-Conditional-Variational-AutoEncoder (EE-CVAE) model generates more diverse and emotionally-intelligent responses compared to single-dimension baseline models in human evaluation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gong-etal-2023-eliciting">
<titleInfo>
<title>Eliciting Rich Positive Emotions in Dialogue Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ziwei</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingkai</namePart>
<namePart type="family">Min</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</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>Proceedings of the First Workshop on Social Influence in Conversations (SICon 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kushal</namePart>
<namePart type="family">Chawla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weiyan</namePart>
<namePart type="family">Shi</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>Positive emotion elicitation aims at evoking positive emotion states in human users in open-domain dialogue generation. However, most work focuses on inducing a single-dimension of positive sentiment using human annotated datasets, which limits the scale of the training dataset. In this paper, we propose to model various emotions in large unannotated conversations, such as joy, trust and anticipation, by leveraging a latent variable to control the emotional intention of the response. Our proposed emotion-eliciting-Conditional-Variational-AutoEncoder (EE-CVAE) model generates more diverse and emotionally-intelligent responses compared to single-dimension baseline models in human evaluation.</abstract>
<identifier type="citekey">gong-etal-2023-eliciting</identifier>
<identifier type="doi">10.18653/v1/2023.sicon-1.1</identifier>
<location>
<url>https://aclanthology.org/2023.sicon-1.1</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1</start>
<end>8</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Eliciting Rich Positive Emotions in Dialogue Generation
%A Gong, Ziwei
%A Min, Qingkai
%A Zhang, Yue
%Y Chawla, Kushal
%Y Shi, Weiyan
%S Proceedings of the First Workshop on Social Influence in Conversations (SICon 2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F gong-etal-2023-eliciting
%X Positive emotion elicitation aims at evoking positive emotion states in human users in open-domain dialogue generation. However, most work focuses on inducing a single-dimension of positive sentiment using human annotated datasets, which limits the scale of the training dataset. In this paper, we propose to model various emotions in large unannotated conversations, such as joy, trust and anticipation, by leveraging a latent variable to control the emotional intention of the response. Our proposed emotion-eliciting-Conditional-Variational-AutoEncoder (EE-CVAE) model generates more diverse and emotionally-intelligent responses compared to single-dimension baseline models in human evaluation.
%R 10.18653/v1/2023.sicon-1.1
%U https://aclanthology.org/2023.sicon-1.1
%U https://doi.org/10.18653/v1/2023.sicon-1.1
%P 1-8
Markdown (Informal)
[Eliciting Rich Positive Emotions in Dialogue Generation](https://aclanthology.org/2023.sicon-1.1) (Gong et al., SICon 2023)
ACL