<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shaar-etal-2025-triggers">
    <titleInfo>
        <title>Are Triggers Needed for Document-Level Event Extraction?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Shaden</namePart>
        <namePart type="family">Shaar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wayne</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Maitreyi</namePart>
        <namePart type="family">Chatterjee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Barry</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wenting</namePart>
        <namePart type="family">Zhao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Claire</namePart>
        <namePart type="family">Cardie</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>Most existing work on event extraction has focused on sentence-level texts and presumes the identification of a trigger-span—a word or phrase in the input that evokes the occurrence of an event of interest. Event arguments are then extracted with respect to the trigger. Indeed, triggers are treated as integral to, and trigger detection as an essential component of, event extraction. In this paper, we provide the first investigation of the role of triggers for the more difficult and much less studied task of document-level event extraction. We analyze their usefulness in multiple end-to-end and pipelined transformer-based event extraction models for three document-level event extraction datasets, measuring performance using triggers of varying quality (human-annotated, LLM-generated, keyword-based, and random). We find that whether or not systems benefit from explicitly extracting triggers depends both on dataset characteristics (i.e., the typical number of events per document) and task-specific information available during extraction (i.e., natural language event schemas). Perhaps surprisingly, we also observe that the mere existence of triggers in the input, even random ones, is important for prompt-based in-context learning approaches to the task.</abstract>
    <identifier type="citekey">shaar-etal-2025-triggers</identifier>
    <identifier type="doi">10.1162/tacl.a.51</identifier>
    <location>
        <url>https://aclanthology.org/2025.tacl-1.71/</url>
    </location>
    <part>
        <date>2025</date>
        <detail type="volume"><number>13</number></detail>
        <extent unit="page">
            <start>1560</start>
            <end>1577</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Are Triggers Needed for Document-Level Event Extraction?
%A Shaar, Shaden
%A Chen, Wayne
%A Chatterjee, Maitreyi
%A Wang, Barry
%A Zhao, Wenting
%A Cardie, Claire
%J Transactions of the Association for Computational Linguistics
%D 2025
%V 13
%I MIT Press
%C Cambridge, MA
%F shaar-etal-2025-triggers
%X Most existing work on event extraction has focused on sentence-level texts and presumes the identification of a trigger-span—a word or phrase in the input that evokes the occurrence of an event of interest. Event arguments are then extracted with respect to the trigger. Indeed, triggers are treated as integral to, and trigger detection as an essential component of, event extraction. In this paper, we provide the first investigation of the role of triggers for the more difficult and much less studied task of document-level event extraction. We analyze their usefulness in multiple end-to-end and pipelined transformer-based event extraction models for three document-level event extraction datasets, measuring performance using triggers of varying quality (human-annotated, LLM-generated, keyword-based, and random). We find that whether or not systems benefit from explicitly extracting triggers depends both on dataset characteristics (i.e., the typical number of events per document) and task-specific information available during extraction (i.e., natural language event schemas). Perhaps surprisingly, we also observe that the mere existence of triggers in the input, even random ones, is important for prompt-based in-context learning approaches to the task.
%R 10.1162/tacl.a.51
%U https://aclanthology.org/2025.tacl-1.71/
%U https://doi.org/10.1162/tacl.a.51
%P 1560-1577

Markdown (Informal)

[Are Triggers Needed for Document-Level Event Extraction?](https://aclanthology.org/2025.tacl-1.71/) (Shaar et al., TACL 2025)

• Are Triggers Needed for Document-Level Event Extraction? (Shaar et al., TACL 2025)

ACL

• Shaden Shaar, Wayne Chen, Maitreyi Chatterjee, Barry Wang, Wenting Zhao, and Claire Cardie. 2025. Are Triggers Needed for Document-Level Event Extraction?. Transactions of the Association for Computational Linguistics, 13:1560–1577.