<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="do-etal-2026-wisteria">
    <titleInfo>
        <title>WISTERIA: Weak Implicit Signal-based Temporal Relation Extraction with Attention</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Duy</namePart>
        <namePart type="given">Dao</namePart>
        <namePart type="family">DO</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Anaïs</namePart>
        <namePart type="family">Halftermeyer</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Thi</namePart>
        <namePart type="given">Bich</namePart>
        <namePart type="given">Hanh</namePart>
        <namePart type="family">DAO</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Stelios</namePart>
            <namePart type="family">Piperidis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Núria</namePart>
            <namePart type="family">Bel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Henk</namePart>
            <namePart type="family">van den Heuvel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nancy</namePart>
            <namePart type="family">Ide</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Simon</namePart>
            <namePart type="family">Krek</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Antonio</namePart>
            <namePart type="family">Toral</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>ELRA Language Resource Association</publisher>
            <place>
                <placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Temporal Relation Extraction (TRE) requires identifying how two events or temporal expressions are related in time. Existing attention-based models often highlight globally salient tokens but overlook the pair-specific cues that actually determine the temporal relation. We propose WISTERIA (Weak Implicit Signal-based Temporal Relation Extraction with Attention), a framework that examines whether the top-K attention components conditioned on each event pair truly encode interpretable evidence for temporal classification. Unlike prior works assuming explicit markers such as before, after, or when, WISTERIA considers signals as any lexical, syntactic, or morphological element implicitly expressing temporal order. By combining multi-head attention with pair-conditioned top-K pooling, the model isolates the most informative contextual tokens for each pair. We conduct extensive experiments on TimeBank-Dense, MATRES, TDDMan, and TDDAuto, including linguistic analyses of top-K tokens. Results show that WISTERIA achieves competitive accuracy and reveals pair-level rationales aligned with temporal linguistic cues, offering a localized and interpretable view of temporal reasoning.</abstract>
    <identifier type="citekey">do-etal-2026-wisteria</identifier>
    <identifier type="doi">10.63317/2bk5hugowdxa</identifier>
    <location>
        <url>https://aclanthology.org/2026.lrec-1.194/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>2471</start>
            <end>2489</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T WISTERIA: Weak Implicit Signal-based Temporal Relation Extraction with Attention
%A DO, Duy Dao
%A Halftermeyer, Anaïs
%A DAO, Thi Bich Hanh
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F do-etal-2026-wisteria
%X Temporal Relation Extraction (TRE) requires identifying how two events or temporal expressions are related in time. Existing attention-based models often highlight globally salient tokens but overlook the pair-specific cues that actually determine the temporal relation. We propose WISTERIA (Weak Implicit Signal-based Temporal Relation Extraction with Attention), a framework that examines whether the top-K attention components conditioned on each event pair truly encode interpretable evidence for temporal classification. Unlike prior works assuming explicit markers such as before, after, or when, WISTERIA considers signals as any lexical, syntactic, or morphological element implicitly expressing temporal order. By combining multi-head attention with pair-conditioned top-K pooling, the model isolates the most informative contextual tokens for each pair. We conduct extensive experiments on TimeBank-Dense, MATRES, TDDMan, and TDDAuto, including linguistic analyses of top-K tokens. Results show that WISTERIA achieves competitive accuracy and reveals pair-level rationales aligned with temporal linguistic cues, offering a localized and interpretable view of temporal reasoning.
%R 10.63317/2bk5hugowdxa
%U https://aclanthology.org/2026.lrec-1.194/
%U https://doi.org/10.63317/2bk5hugowdxa
%P 2471-2489

Markdown (Informal)

[WISTERIA: Weak Implicit Signal-based Temporal Relation Extraction with Attention](https://aclanthology.org/2026.lrec-1.194/) (DO et al., LREC 2026)

• WISTERIA: Weak Implicit Signal-based Temporal Relation Extraction with Attention (DO et al., LREC 2026)

ACL

• Duy Dao DO, Anaïs Halftermeyer, and Thi Bich Hanh DAO. 2026. WISTERIA: Weak Implicit Signal-based Temporal Relation Extraction with Attention. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 2471–2489, Palma de Mallorca, Spain. ELRA Language Resource Association.