@inproceedings{hu-etal-2021-mmgcn,
title = "{MMGCN}: Multimodal Fusion via Deep Graph Convolution Network for Emotion Recognition in Conversation",
author = "Hu, Jingwen and
Liu, Yuchen and
Zhao, Jinming and
Jin, Qin",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.440",
doi = "10.18653/v1/2021.acl-long.440",
pages = "5666--5675",
abstract = "Emotion recognition in conversation (ERC) is a crucial component in affective dialogue systems, which helps the system understand users{'} emotions and generate empathetic responses. However, most works focus on modeling speaker and contextual information primarily on the textual modality or simply leveraging multimodal information through feature concatenation. In order to explore a more effective way of utilizing both multimodal and long-distance contextual information, we propose a new model based on multimodal fused graph convolutional network, MMGCN, in this work. MMGCN can not only make use of multimodal dependencies effectively, but also leverage speaker information to model inter-speaker and intra-speaker dependency. We evaluate our proposed model on two public benchmark datasets, IEMOCAP and MELD, and the results prove the effectiveness of MMGCN, which outperforms other SOTA methods by a significant margin under the multimodal conversation setting.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hu-etal-2021-mmgcn">
<titleInfo>
<title>MMGCN: Multimodal Fusion via Deep Graph Convolution Network for Emotion Recognition in Conversation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jingwen</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuchen</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinming</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qin</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Emotion recognition in conversation (ERC) is a crucial component in affective dialogue systems, which helps the system understand users’ emotions and generate empathetic responses. However, most works focus on modeling speaker and contextual information primarily on the textual modality or simply leveraging multimodal information through feature concatenation. In order to explore a more effective way of utilizing both multimodal and long-distance contextual information, we propose a new model based on multimodal fused graph convolutional network, MMGCN, in this work. MMGCN can not only make use of multimodal dependencies effectively, but also leverage speaker information to model inter-speaker and intra-speaker dependency. We evaluate our proposed model on two public benchmark datasets, IEMOCAP and MELD, and the results prove the effectiveness of MMGCN, which outperforms other SOTA methods by a significant margin under the multimodal conversation setting.</abstract>
<identifier type="citekey">hu-etal-2021-mmgcn</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.440</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.440</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>5666</start>
<end>5675</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MMGCN: Multimodal Fusion via Deep Graph Convolution Network for Emotion Recognition in Conversation
%A Hu, Jingwen
%A Liu, Yuchen
%A Zhao, Jinming
%A Jin, Qin
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F hu-etal-2021-mmgcn
%X Emotion recognition in conversation (ERC) is a crucial component in affective dialogue systems, which helps the system understand users’ emotions and generate empathetic responses. However, most works focus on modeling speaker and contextual information primarily on the textual modality or simply leveraging multimodal information through feature concatenation. In order to explore a more effective way of utilizing both multimodal and long-distance contextual information, we propose a new model based on multimodal fused graph convolutional network, MMGCN, in this work. MMGCN can not only make use of multimodal dependencies effectively, but also leverage speaker information to model inter-speaker and intra-speaker dependency. We evaluate our proposed model on two public benchmark datasets, IEMOCAP and MELD, and the results prove the effectiveness of MMGCN, which outperforms other SOTA methods by a significant margin under the multimodal conversation setting.
%R 10.18653/v1/2021.acl-long.440
%U https://aclanthology.org/2021.acl-long.440
%U https://doi.org/10.18653/v1/2021.acl-long.440
%P 5666-5675
Markdown (Informal)
[MMGCN: Multimodal Fusion via Deep Graph Convolution Network for Emotion Recognition in Conversation](https://aclanthology.org/2021.acl-long.440) (Hu et al., ACL-IJCNLP 2021)
ACL