<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shi-etal-2023-hybrid">
    <titleInfo>
        <title>A Hybrid Detection and Generation Framework with Separate Encoders for Event Extraction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ge</namePart>
        <namePart type="family">Shi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yunyue</namePart>
        <namePart type="family">Su</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yongliang</namePart>
        <namePart type="family">Ma</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ming</namePart>
        <namePart type="family">Zhou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Andreas</namePart>
            <namePart type="family">Vlachos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Isabelle</namePart>
            <namePart type="family">Augenstein</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Dubrovnik, Croatia</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>The event extraction task typically consists of event detection and event argument extraction. Most previous work models these two subtasks with shared representation by multiple classification tasks or a unified generative approach. In this paper, we revisit this pattern and propose to use independent encoders to model event detection and event argument extraction, respectively, and use the output of event detection to construct the input of event argument extraction. In addition, we use token-level features to precisely control the fusion between two encoders to achieve joint bridging training rather than directly reusing representations between different tasks. Through a series of careful experiments, we demonstrate the importance of avoiding feature interference of different tasks and the importance of joint bridging training. We achieved competitive results on standard benchmarks (ACE05-E, ACE05-E+, and ERE-EN) and established a solid baseline.</abstract>
    <identifier type="citekey">shi-etal-2023-hybrid</identifier>
    <identifier type="doi">10.18653/v1/2023.eacl-main.231</identifier>
    <location>
        <url>https://aclanthology.org/2023.eacl-main.231</url>
    </location>
    <part>
        <date>2023-05</date>
        <extent unit="page">
            <start>3163</start>
            <end>3180</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Hybrid Detection and Generation Framework with Separate Encoders for Event Extraction
%A Shi, Ge
%A Su, Yunyue
%A Ma, Yongliang
%A Zhou, Ming
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F shi-etal-2023-hybrid
%X The event extraction task typically consists of event detection and event argument extraction. Most previous work models these two subtasks with shared representation by multiple classification tasks or a unified generative approach. In this paper, we revisit this pattern and propose to use independent encoders to model event detection and event argument extraction, respectively, and use the output of event detection to construct the input of event argument extraction. In addition, we use token-level features to precisely control the fusion between two encoders to achieve joint bridging training rather than directly reusing representations between different tasks. Through a series of careful experiments, we demonstrate the importance of avoiding feature interference of different tasks and the importance of joint bridging training. We achieved competitive results on standard benchmarks (ACE05-E, ACE05-E+, and ERE-EN) and established a solid baseline.
%R 10.18653/v1/2023.eacl-main.231
%U https://aclanthology.org/2023.eacl-main.231
%U https://doi.org/10.18653/v1/2023.eacl-main.231
%P 3163-3180

Markdown (Informal)

[A Hybrid Detection and Generation Framework with Separate Encoders for Event Extraction](https://aclanthology.org/2023.eacl-main.231) (Shi et al., EACL 2023)

• A Hybrid Detection and Generation Framework with Separate Encoders for Event Extraction (Shi et al., EACL 2023)

ACL

• Ge Shi, Yunyue Su, Yongliang Ma, and Ming Zhou. 2023. A Hybrid Detection and Generation Framework with Separate Encoders for Event Extraction. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 3163–3180, Dubrovnik, Croatia. Association for Computational Linguistics.