@inproceedings{xu-etal-2022-mmdag,
title = "{MMDAG}: Multimodal Directed Acyclic Graph Network for Emotion Recognition in Conversation",
author = "Xu, Shuo and
Jia, Yuxiang and
Niu, Changyong and
Zan, Hongying",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.733/",
pages = "6802--6807",
abstract = "Emotion recognition in conversation is important for an empathetic dialogue system to understand the user`s emotion and then generate appropriate emotional responses. However, most previous researches focus on modeling conversational contexts primarily based on the textual modality or simply utilizing multimodal information through feature concatenation. In order to exploit multimodal information and contextual information more effectively, we propose a multimodal directed acyclic graph (MMDAG) network by injecting information flows inside modality and across modalities into the DAG architecture. Experiments on IEMOCAP and MELD show that our model outperforms other state-of-the-art models. Comparative studies validate the effectiveness of the proposed modality fusion method."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2022-mmdag">
<titleInfo>
<title>MMDAG: Multimodal Directed Acyclic Graph Network for Emotion Recognition in Conversation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shuo</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxiang</namePart>
<namePart type="family">Jia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Changyong</namePart>
<namePart type="family">Niu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongying</namePart>
<namePart type="family">Zan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Emotion recognition in conversation is important for an empathetic dialogue system to understand the user‘s emotion and then generate appropriate emotional responses. However, most previous researches focus on modeling conversational contexts primarily based on the textual modality or simply utilizing multimodal information through feature concatenation. In order to exploit multimodal information and contextual information more effectively, we propose a multimodal directed acyclic graph (MMDAG) network by injecting information flows inside modality and across modalities into the DAG architecture. Experiments on IEMOCAP and MELD show that our model outperforms other state-of-the-art models. Comparative studies validate the effectiveness of the proposed modality fusion method.</abstract>
<identifier type="citekey">xu-etal-2022-mmdag</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.733/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>6802</start>
<end>6807</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MMDAG: Multimodal Directed Acyclic Graph Network for Emotion Recognition in Conversation
%A Xu, Shuo
%A Jia, Yuxiang
%A Niu, Changyong
%A Zan, Hongying
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F xu-etal-2022-mmdag
%X Emotion recognition in conversation is important for an empathetic dialogue system to understand the user‘s emotion and then generate appropriate emotional responses. However, most previous researches focus on modeling conversational contexts primarily based on the textual modality or simply utilizing multimodal information through feature concatenation. In order to exploit multimodal information and contextual information more effectively, we propose a multimodal directed acyclic graph (MMDAG) network by injecting information flows inside modality and across modalities into the DAG architecture. Experiments on IEMOCAP and MELD show that our model outperforms other state-of-the-art models. Comparative studies validate the effectiveness of the proposed modality fusion method.
%U https://aclanthology.org/2022.lrec-1.733/
%P 6802-6807
Markdown (Informal)
[MMDAG: Multimodal Directed Acyclic Graph Network for Emotion Recognition in Conversation](https://aclanthology.org/2022.lrec-1.733/) (Xu et al., LREC 2022)
ACL