<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-etal-2023-self">
    <titleInfo>
        <title>Self-distilled Transitive Instance Weighting for Denoised Distantly Supervised Relation Extraction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xiangyu</namePart>
        <namePart type="family">Lin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Weijia</namePart>
        <namePart type="family">Jia</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhiguo</namePart>
        <namePart type="family">Gong</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>The widespread existence of wrongly labeled instances is a challenge to distantly supervised relation extraction. Most of the previous works are trained in a bag-level setting to alleviate such noise. However, sentence-level training better utilizes the information than bag-level training, as long as combined with effective noise alleviation. In this work, we propose a novel Transitive Instance Weighting mechanism integrated with the self-distilled BERT backbone, utilizing information in the intermediate outputs to generate dynamic instance weights for denoised sentence-level training. By down-weighting wrongly labeled instances and discounting the weights of easy-to-fit ones, our method can effectively tackle wrongly labeled instances and prevent overfitting. Experiments on both held-out and manual datasets indicate that our method achieves state-of-the-art performance and consistent improvements over the baselines.</abstract>
    <identifier type="citekey">lin-etal-2023-self</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-emnlp.13</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-emnlp.13/</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>168</start>
            <end>180</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Self-distilled Transitive Instance Weighting for Denoised Distantly Supervised Relation Extraction
%A Lin, Xiangyu
%A Jia, Weijia
%A Gong, Zhiguo
%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 lin-etal-2023-self
%X The widespread existence of wrongly labeled instances is a challenge to distantly supervised relation extraction. Most of the previous works are trained in a bag-level setting to alleviate such noise. However, sentence-level training better utilizes the information than bag-level training, as long as combined with effective noise alleviation. In this work, we propose a novel Transitive Instance Weighting mechanism integrated with the self-distilled BERT backbone, utilizing information in the intermediate outputs to generate dynamic instance weights for denoised sentence-level training. By down-weighting wrongly labeled instances and discounting the weights of easy-to-fit ones, our method can effectively tackle wrongly labeled instances and prevent overfitting. Experiments on both held-out and manual datasets indicate that our method achieves state-of-the-art performance and consistent improvements over the baselines.
%R 10.18653/v1/2023.findings-emnlp.13
%U https://aclanthology.org/2023.findings-emnlp.13/
%U https://doi.org/10.18653/v1/2023.findings-emnlp.13
%P 168-180

Markdown (Informal)

[Self-distilled Transitive Instance Weighting for Denoised Distantly Supervised Relation Extraction](https://aclanthology.org/2023.findings-emnlp.13/) (Lin et al., Findings 2023)

• Self-distilled Transitive Instance Weighting for Denoised Distantly Supervised Relation Extraction (Lin et al., Findings 2023)

ACL

• Xiangyu Lin, Weijia Jia, and Zhiguo Gong. 2023. Self-distilled Transitive Instance Weighting for Denoised Distantly Supervised Relation Extraction. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 168–180, Singapore. Association for Computational Linguistics.