@inproceedings{zhang-tan-2025-ecerc,
title = "{ECERC}: Evidence-Cause Attention Network for Multi-Modal Emotion Recognition in Conversation",
author = "Zhang, Tao and
Tan, Zhenhua",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.102/",
doi = "10.18653/v1/2025.acl-long.102",
pages = "2064--2077",
ISBN = "979-8-89176-251-0",
abstract = "Multi-modal Emotion Recognition in Conversation (MMERC) aims to identify speakers' emotional states using multi-modal conversational data, significant for various domains. MMERC requires addressing emotional causes: contextual factors that influence emotions, alongside emotional evidence directly expressed in the target utterance. Existing methods primarily model general conversational dependencies, such as sequential utterance relationships or inter-speaker dynamics, but fall short in capturing diverse and detailed emotional causes, including emotional contagion, influences from others, and self-referenced or externally introduced events. To address these limitations, we propose the Evidence-Cause Attention Network for Multi-Modal Emotion Recognition in Conversation (ECERC). ECERC integrates emotional evidence with contextual causes through five stages: Evidence Gating extracts and refines emotional evidence across modalities; Cause Encoding captures causes from conversational context; Evidence-Cause Interaction uses attention to integrate evidence with diverse causes, generating rich candidate features for emotion inference; Feature Gating adaptively weights contributions of candidate features; and Emotion Classification classifies emotions. We evaluate ECERC on two widely used benchmark datasets, IEMOCAP and MELD. Experimental results show that ECERC achieves competitive performance in weighted F1-score and accuracy, demonstrating its effectiveness in MMERC"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-tan-2025-ecerc">
<titleInfo>
<title>ECERC: Evidence-Cause Attention Network for Multi-Modal Emotion Recognition in Conversation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenhua</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Multi-modal Emotion Recognition in Conversation (MMERC) aims to identify speakers’ emotional states using multi-modal conversational data, significant for various domains. MMERC requires addressing emotional causes: contextual factors that influence emotions, alongside emotional evidence directly expressed in the target utterance. Existing methods primarily model general conversational dependencies, such as sequential utterance relationships or inter-speaker dynamics, but fall short in capturing diverse and detailed emotional causes, including emotional contagion, influences from others, and self-referenced or externally introduced events. To address these limitations, we propose the Evidence-Cause Attention Network for Multi-Modal Emotion Recognition in Conversation (ECERC). ECERC integrates emotional evidence with contextual causes through five stages: Evidence Gating extracts and refines emotional evidence across modalities; Cause Encoding captures causes from conversational context; Evidence-Cause Interaction uses attention to integrate evidence with diverse causes, generating rich candidate features for emotion inference; Feature Gating adaptively weights contributions of candidate features; and Emotion Classification classifies emotions. We evaluate ECERC on two widely used benchmark datasets, IEMOCAP and MELD. Experimental results show that ECERC achieves competitive performance in weighted F1-score and accuracy, demonstrating its effectiveness in MMERC</abstract>
<identifier type="citekey">zhang-tan-2025-ecerc</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.102</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.102/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>2064</start>
<end>2077</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ECERC: Evidence-Cause Attention Network for Multi-Modal Emotion Recognition in Conversation
%A Zhang, Tao
%A Tan, Zhenhua
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F zhang-tan-2025-ecerc
%X Multi-modal Emotion Recognition in Conversation (MMERC) aims to identify speakers’ emotional states using multi-modal conversational data, significant for various domains. MMERC requires addressing emotional causes: contextual factors that influence emotions, alongside emotional evidence directly expressed in the target utterance. Existing methods primarily model general conversational dependencies, such as sequential utterance relationships or inter-speaker dynamics, but fall short in capturing diverse and detailed emotional causes, including emotional contagion, influences from others, and self-referenced or externally introduced events. To address these limitations, we propose the Evidence-Cause Attention Network for Multi-Modal Emotion Recognition in Conversation (ECERC). ECERC integrates emotional evidence with contextual causes through five stages: Evidence Gating extracts and refines emotional evidence across modalities; Cause Encoding captures causes from conversational context; Evidence-Cause Interaction uses attention to integrate evidence with diverse causes, generating rich candidate features for emotion inference; Feature Gating adaptively weights contributions of candidate features; and Emotion Classification classifies emotions. We evaluate ECERC on two widely used benchmark datasets, IEMOCAP and MELD. Experimental results show that ECERC achieves competitive performance in weighted F1-score and accuracy, demonstrating its effectiveness in MMERC
%R 10.18653/v1/2025.acl-long.102
%U https://aclanthology.org/2025.acl-long.102/
%U https://doi.org/10.18653/v1/2025.acl-long.102
%P 2064-2077
Markdown (Informal)
[ECERC: Evidence-Cause Attention Network for Multi-Modal Emotion Recognition in Conversation](https://aclanthology.org/2025.acl-long.102/) (Zhang & Tan, ACL 2025)
ACL