@inproceedings{he-etal-2025-dialoguemmt,
title = "{D}ialogue{MMT}: Dialogue Scenes Understanding Enhanced Multi-modal Multi-task Tuning for Emotion Recognition in Conversations",
author = "He, ChenYuan and
Zhu, Senbin and
Liu, Hongde and
Gao, Fei and
Jia, Yuxiang and
Zan, Hongying and
Peng, Min",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.170/",
pages = "2497--2512",
abstract = "Emotion recognition in conversations (ERC) has garnered significant attention from the research community. However, due to the complexity of visual scenes and dialogue contextual dependencies in conversations, previous ERC methods fail to handle emotional cues from both visual sources and discourse structures. Furthermore, existing state-of-the-art ERC models are trained and tested separately on each single ERC dataset, not verifying their effectiveness across multiple datasets simultaneously. To address these challenges, this paper proposes an innovative framework for ERC, called Dialogue Scenes Understanding Enhanced Multi-modal Multi-task Tuning (DialogueMMT). More concretely, a novel video-language connector is applied within the large vision-language model for capturing video features effectively. Additionally, we utilize multi-task instruction tuning with a unified ERC dataset to enhance the model`s understanding of multi-modal dialogue scenes and employ a chain-of-thought strategy to improve emotion classification performance. Extensive experimental results on three benchmark ERC datasets indicate that the proposed DialogueMMT framework consistently outperforms existing state-of-the-art approaches in terms of overall performance."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="he-etal-2025-dialoguemmt">
<titleInfo>
<title>DialogueMMT: Dialogue Scenes Understanding Enhanced Multi-modal Multi-task Tuning for Emotion Recognition in Conversations</title>
</titleInfo>
<name type="personal">
<namePart type="given">ChenYuan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Senbin</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongde</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Gao</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">Hongying</namePart>
<namePart type="family">Zan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Emotion recognition in conversations (ERC) has garnered significant attention from the research community. However, due to the complexity of visual scenes and dialogue contextual dependencies in conversations, previous ERC methods fail to handle emotional cues from both visual sources and discourse structures. Furthermore, existing state-of-the-art ERC models are trained and tested separately on each single ERC dataset, not verifying their effectiveness across multiple datasets simultaneously. To address these challenges, this paper proposes an innovative framework for ERC, called Dialogue Scenes Understanding Enhanced Multi-modal Multi-task Tuning (DialogueMMT). More concretely, a novel video-language connector is applied within the large vision-language model for capturing video features effectively. Additionally, we utilize multi-task instruction tuning with a unified ERC dataset to enhance the model‘s understanding of multi-modal dialogue scenes and employ a chain-of-thought strategy to improve emotion classification performance. Extensive experimental results on three benchmark ERC datasets indicate that the proposed DialogueMMT framework consistently outperforms existing state-of-the-art approaches in terms of overall performance.</abstract>
<identifier type="citekey">he-etal-2025-dialoguemmt</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.170/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>2497</start>
<end>2512</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DialogueMMT: Dialogue Scenes Understanding Enhanced Multi-modal Multi-task Tuning for Emotion Recognition in Conversations
%A He, ChenYuan
%A Zhu, Senbin
%A Liu, Hongde
%A Gao, Fei
%A Jia, Yuxiang
%A Zan, Hongying
%A Peng, Min
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F he-etal-2025-dialoguemmt
%X Emotion recognition in conversations (ERC) has garnered significant attention from the research community. However, due to the complexity of visual scenes and dialogue contextual dependencies in conversations, previous ERC methods fail to handle emotional cues from both visual sources and discourse structures. Furthermore, existing state-of-the-art ERC models are trained and tested separately on each single ERC dataset, not verifying their effectiveness across multiple datasets simultaneously. To address these challenges, this paper proposes an innovative framework for ERC, called Dialogue Scenes Understanding Enhanced Multi-modal Multi-task Tuning (DialogueMMT). More concretely, a novel video-language connector is applied within the large vision-language model for capturing video features effectively. Additionally, we utilize multi-task instruction tuning with a unified ERC dataset to enhance the model‘s understanding of multi-modal dialogue scenes and employ a chain-of-thought strategy to improve emotion classification performance. Extensive experimental results on three benchmark ERC datasets indicate that the proposed DialogueMMT framework consistently outperforms existing state-of-the-art approaches in terms of overall performance.
%U https://aclanthology.org/2025.coling-main.170/
%P 2497-2512
Markdown (Informal)
[DialogueMMT: Dialogue Scenes Understanding Enhanced Multi-modal Multi-task Tuning for Emotion Recognition in Conversations](https://aclanthology.org/2025.coling-main.170/) (He et al., COLING 2025)
ACL