@inproceedings{wan-etal-2026-locate,
title = "Locate and Explain: Joint Multimodal Emotion Cause Extraction and Summarization in Conversation",
author = "Wan, Jikun and
Gong, Chen and
Fu, Guohong",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.2012/",
pages = "43472--43489",
ISBN = "979-8-89176-390-6",
abstract = "Multimodal emotion cause analysis in conversation aims to identify the causes of emotions by leveraging multimodal information. Existing studies mainly formulate this problem as either utterance-level emotion cause extraction, which provides clear cause localization but limited explanation, or multimodal emotion cause generation, which offers fine-grained explanations but lacks explicit traceability to source utterances. Moreover, existing datasets rely heavily on human judgment and lack well-defined structured theoretical guidance, leading to subjective and inconsistent annotations. To address these issues, we introduce joint Multimodal Emotion Cause Extraction and Summarization in conversation (MECES), a new task that simultaneously extracts emotion cause utterances and generates cause summaries, enabling both precise localization and interpretable explanations of emotion cause. We further construct a MECES dataset guided by the Activating Events{--}Beliefs{--}Consequences theory from psychology. This dataset consists of 5,787 emotion utterances annotated with causes, comprising 12,231 emotion-cause pairs and 6,040 cause summaries. We also propose an effective end-to-end joint learning approach for MECES task, establishing strong benchmark results for this newly introduced task and dataset."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wan-etal-2026-locate">
<titleInfo>
<title>Locate and Explain: Joint Multimodal Emotion Cause Extraction and Summarization in Conversation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jikun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guohong</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Multimodal emotion cause analysis in conversation aims to identify the causes of emotions by leveraging multimodal information. Existing studies mainly formulate this problem as either utterance-level emotion cause extraction, which provides clear cause localization but limited explanation, or multimodal emotion cause generation, which offers fine-grained explanations but lacks explicit traceability to source utterances. Moreover, existing datasets rely heavily on human judgment and lack well-defined structured theoretical guidance, leading to subjective and inconsistent annotations. To address these issues, we introduce joint Multimodal Emotion Cause Extraction and Summarization in conversation (MECES), a new task that simultaneously extracts emotion cause utterances and generates cause summaries, enabling both precise localization and interpretable explanations of emotion cause. We further construct a MECES dataset guided by the Activating Events–Beliefs–Consequences theory from psychology. This dataset consists of 5,787 emotion utterances annotated with causes, comprising 12,231 emotion-cause pairs and 6,040 cause summaries. We also propose an effective end-to-end joint learning approach for MECES task, establishing strong benchmark results for this newly introduced task and dataset.</abstract>
<identifier type="citekey">wan-etal-2026-locate</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.2012/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>43472</start>
<end>43489</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Locate and Explain: Joint Multimodal Emotion Cause Extraction and Summarization in Conversation
%A Wan, Jikun
%A Gong, Chen
%A Fu, Guohong
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F wan-etal-2026-locate
%X Multimodal emotion cause analysis in conversation aims to identify the causes of emotions by leveraging multimodal information. Existing studies mainly formulate this problem as either utterance-level emotion cause extraction, which provides clear cause localization but limited explanation, or multimodal emotion cause generation, which offers fine-grained explanations but lacks explicit traceability to source utterances. Moreover, existing datasets rely heavily on human judgment and lack well-defined structured theoretical guidance, leading to subjective and inconsistent annotations. To address these issues, we introduce joint Multimodal Emotion Cause Extraction and Summarization in conversation (MECES), a new task that simultaneously extracts emotion cause utterances and generates cause summaries, enabling both precise localization and interpretable explanations of emotion cause. We further construct a MECES dataset guided by the Activating Events–Beliefs–Consequences theory from psychology. This dataset consists of 5,787 emotion utterances annotated with causes, comprising 12,231 emotion-cause pairs and 6,040 cause summaries. We also propose an effective end-to-end joint learning approach for MECES task, establishing strong benchmark results for this newly introduced task and dataset.
%U https://aclanthology.org/2026.acl-long.2012/
%P 43472-43489
Markdown (Informal)
[Locate and Explain: Joint Multimodal Emotion Cause Extraction and Summarization in Conversation](https://aclanthology.org/2026.acl-long.2012/) (Wan et al., ACL 2026)
ACL