<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ren-etal-2023-covariance">
    <titleInfo>
        <title>CoVariance-based Causal Debiasing for Entity and Relation Extraction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Lin</namePart>
        <namePart type="family">Ren</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yongbin</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yixin</namePart>
        <namePart type="family">Cao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chunping</namePart>
        <namePart type="family">Ouyang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Houda</namePart>
            <namePart type="family">Bouamor</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="family">Pino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kalika</namePart>
            <namePart type="family">Bali</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Joint entity and relation extraction tasks aim to recognize named entities and extract relations simultaneously. Suffering from a variety of data biases, such as data selection bias, and distribution bias (out of distribution, long-tail distribution), serious concerns can be witnessed to threaten the model‘s transferability, robustness, and generalization. In this work, we address the above problems from a causality perspective. We propose a novel causal framework called c\underlineovariance and \underlinevariance \underlineoptimization framework (OVO) to optimize feature representations and conduct general debiasing. In particular, the proposed \underlinecovariance \underlineoptimizing (COP) minimizes characterizing features’ covariance for alleviating the selection and distribution bias and enhances feature representation in the feature space. Furthermore, based on the causal backdoor adjustment, we propose \\underlinevariance \underlineoptimizing (VOP) separates samples in terms of label information and minimizes the variance of each dimension in the feature vectors of the same class label for mitigating the distribution bias further. By applying it to three strong baselines in two widely used datasets, the results demonstrate the effectiveness and generalization of OVO for joint entity and relation extraction tasks. Furthermore, a fine-grained analysis reveals that OVO possesses the capability to mitigate the impact of long-tail distribution.</abstract>
    <identifier type="citekey">ren-etal-2023-covariance</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-emnlp.173</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-emnlp.173/</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>2627</start>
            <end>2640</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T CoVariance-based Causal Debiasing for Entity and Relation Extraction
%A Ren, Lin
%A Liu, Yongbin
%A Cao, Yixin
%A Ouyang, Chunping
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F ren-etal-2023-covariance
%X Joint entity and relation extraction tasks aim to recognize named entities and extract relations simultaneously. Suffering from a variety of data biases, such as data selection bias, and distribution bias (out of distribution, long-tail distribution), serious concerns can be witnessed to threaten the model‘s transferability, robustness, and generalization. In this work, we address the above problems from a causality perspective. We propose a novel causal framework called c\underlineovariance and \underlinevariance \underlineoptimization framework (OVO) to optimize feature representations and conduct general debiasing. In particular, the proposed \underlinecovariance \underlineoptimizing (COP) minimizes characterizing features’ covariance for alleviating the selection and distribution bias and enhances feature representation in the feature space. Furthermore, based on the causal backdoor adjustment, we propose \\underlinevariance \underlineoptimizing (VOP) separates samples in terms of label information and minimizes the variance of each dimension in the feature vectors of the same class label for mitigating the distribution bias further. By applying it to three strong baselines in two widely used datasets, the results demonstrate the effectiveness and generalization of OVO for joint entity and relation extraction tasks. Furthermore, a fine-grained analysis reveals that OVO possesses the capability to mitigate the impact of long-tail distribution.
%R 10.18653/v1/2023.findings-emnlp.173
%U https://aclanthology.org/2023.findings-emnlp.173/
%U https://doi.org/10.18653/v1/2023.findings-emnlp.173
%P 2627-2640

Markdown (Informal)

[CoVariance-based Causal Debiasing for Entity and Relation Extraction](https://aclanthology.org/2023.findings-emnlp.173/) (Ren et al., Findings 2023)

• CoVariance-based Causal Debiasing for Entity and Relation Extraction (Ren et al., Findings 2023)

ACL

• Lin Ren, Yongbin Liu, Yixin Cao, and Chunping Ouyang. 2023. CoVariance-based Causal Debiasing for Entity and Relation Extraction. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 2627–2640, Singapore. Association for Computational Linguistics.