<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-etal-2019-cost">
    <titleInfo>
        <title>Cost-sensitive Regularization for Label Confusion-aware Event Detection</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Hongyu</namePart>
        <namePart type="family">Lin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yaojie</namePart>
        <namePart type="family">Lu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xianpei</namePart>
        <namePart type="family">Han</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Le</namePart>
        <namePart type="family">Sun</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-jul</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Florence, Italy</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In supervised event detection, most of the mislabeling occurs between a small number of confusing type pairs, including trigger-NIL pairs and sibling sub-types of the same coarse type. To address this label confusion problem, this paper proposes cost-sensitive regularization, which can force the training procedure to concentrate more on optimizing confusing type pairs. Specifically, we introduce a cost-weighted term into the training loss, which penalizes more on mislabeling between confusing label pairs. Furthermore, we also propose two estimators which can effectively measure such label confusion based on instance-level or population-level statistics. Experiments on TAC-KBP 2017 datasets demonstrate that the proposed method can significantly improve the performances of different models in both English and Chinese event detection.</abstract>
    <identifier type="citekey">lin-etal-2019-cost</identifier>
    <identifier type="doi">10.18653/v1/P19-1521</identifier>
    <location>
        <url>https://aclanthology.org/P19-1521</url>
    </location>
    <part>
        <date>2019-jul</date>
        <extent unit="page">
            <start>5278</start>
            <end>5283</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Cost-sensitive Regularization for Label Confusion-aware Event Detection
%A Lin, Hongyu
%A Lu, Yaojie
%A Han, Xianpei
%A Sun, Le
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 jul
%I Association for Computational Linguistics
%C Florence, Italy
%F lin-etal-2019-cost
%X In supervised event detection, most of the mislabeling occurs between a small number of confusing type pairs, including trigger-NIL pairs and sibling sub-types of the same coarse type. To address this label confusion problem, this paper proposes cost-sensitive regularization, which can force the training procedure to concentrate more on optimizing confusing type pairs. Specifically, we introduce a cost-weighted term into the training loss, which penalizes more on mislabeling between confusing label pairs. Furthermore, we also propose two estimators which can effectively measure such label confusion based on instance-level or population-level statistics. Experiments on TAC-KBP 2017 datasets demonstrate that the proposed method can significantly improve the performances of different models in both English and Chinese event detection.
%R 10.18653/v1/P19-1521
%U https://aclanthology.org/P19-1521
%U https://doi.org/10.18653/v1/P19-1521
%P 5278-5283

Markdown (Informal)

[Cost-sensitive Regularization for Label Confusion-aware Event Detection](https://aclanthology.org/P19-1521) (Lin et al., ACL 2019)

• Cost-sensitive Regularization for Label Confusion-aware Event Detection (Lin et al., ACL 2019)

ACL

• Hongyu Lin, Yaojie Lu, Xianpei Han, and Le Sun. 2019. Cost-sensitive Regularization for Label Confusion-aware Event Detection. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5278–5283, Florence, Italy. Association for Computational Linguistics.