<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hu-etal-2026-sufficiency">
    <titleInfo>
        <title>Sufficiency-Aware Adversarial Evidence Masking for Textual Emotion-Cause Pair Extraction in Conversations</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mengqiang</namePart>
        <namePart type="family">Hu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Qian</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xin</namePart>
        <namePart type="family">Guo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Suge</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Textual Emotion-Cause Pair Extraction in Conversations (TECPE) requires identifying emotion utterances, their categories, and the textual cause spans that explain them. Although recent systems improve aggregate scores, clean supervision can induce evidence bias: models exploit explicit emotion cues, cause–emotion proximity, and speaker/discourse priors rather than evidence sufficient for causal explanation. We introduce SAAM-EC, a sufficiency-aware adversarial evidence masking framework for span-grounded TECPE. SAAM-EC adversarially masks high-impact conversational evidence units during training, but treats masking as a semantic intervention rather than a label-preserving perturbation. When masking removes the cause span or necessary bridge context, the original span may no longer be extractable or justified. SAAM-EC therefore combines adversarial masking with a sufficiency gate and an extractability guard, training masked examples to recover the original span only when the remaining dialogue still supports the emotion–cause relation and preserves the annotated span; otherwise, it trains the model with an unanswerability objective. All auxiliary components are discarded at inference, leaving the backbone unchanged. Experiments on span-level TECPE and utterance-level ECPE benchmarks show consistent performance gains over clean backbones and masking-based alternatives. Diagnostics further show better recovery on distant and cross-speaker causes and stronger abstention under destructive masks.</abstract>
    <identifier type="citekey">hu-etal-2026-sufficiency</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.971/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>22394</start>
            <end>22413</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Sufficiency-Aware Adversarial Evidence Masking for Textual Emotion-Cause Pair Extraction in Conversations
%A Hu, Mengqiang
%A Chen, Qian
%A Guo, Xin
%A Wang, Suge
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F hu-etal-2026-sufficiency
%X Textual Emotion-Cause Pair Extraction in Conversations (TECPE) requires identifying emotion utterances, their categories, and the textual cause spans that explain them. Although recent systems improve aggregate scores, clean supervision can induce evidence bias: models exploit explicit emotion cues, cause–emotion proximity, and speaker/discourse priors rather than evidence sufficient for causal explanation. We introduce SAAM-EC, a sufficiency-aware adversarial evidence masking framework for span-grounded TECPE. SAAM-EC adversarially masks high-impact conversational evidence units during training, but treats masking as a semantic intervention rather than a label-preserving perturbation. When masking removes the cause span or necessary bridge context, the original span may no longer be extractable or justified. SAAM-EC therefore combines adversarial masking with a sufficiency gate and an extractability guard, training masked examples to recover the original span only when the remaining dialogue still supports the emotion–cause relation and preserves the annotated span; otherwise, it trains the model with an unanswerability objective. All auxiliary components are discarded at inference, leaving the backbone unchanged. Experiments on span-level TECPE and utterance-level ECPE benchmarks show consistent performance gains over clean backbones and masking-based alternatives. Diagnostics further show better recovery on distant and cross-speaker causes and stronger abstention under destructive masks.
%U https://aclanthology.org/2026.emnlp-main.971/
%P 22394-22413

Markdown (Informal)

[Sufficiency-Aware Adversarial Evidence Masking for Textual Emotion-Cause Pair Extraction in Conversations](https://aclanthology.org/2026.emnlp-main.971/) (Hu et al., EMNLP 2026)

• Sufficiency-Aware Adversarial Evidence Masking for Textual Emotion-Cause Pair Extraction in Conversations (Hu et al., EMNLP 2026)

ACL

• Mengqiang Hu, Qian Chen, Xin Guo, and Suge Wang. 2026. Sufficiency-Aware Adversarial Evidence Masking for Textual Emotion-Cause Pair Extraction in Conversations. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 22394–22413, Budapest, Hungary. Association for Computational Linguistics.