<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qin-etal-2018-dsgan">
    <titleInfo>
        <title>DSGAN: Generative Adversarial Training for Distant Supervision Relation Extraction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Pengda</namePart>
        <namePart type="family">Qin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Weiran</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">William</namePart>
        <namePart type="given">Yang</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Iryna</namePart>
            <namePart type="family">Gurevych</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yusuke</namePart>
            <namePart type="family">Miyao</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Melbourne, Australia</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Distant supervision can effectively label data for relation extraction, but suffers from the noise labeling problem. Recent works mainly perform soft bag-level noise reduction strategies to find the relatively better samples in a sentence bag, which is suboptimal compared with making a hard decision of false positive samples in sentence level. In this paper, we introduce an adversarial learning framework, which we named DSGAN, to learn a sentence-level true-positive generator. Inspired by Generative Adversarial Networks, we regard the positive samples generated by the generator as the negative samples to train the discriminator. The optimal generator is obtained until the discrimination ability of the discriminator has the greatest decline. We adopt the generator to filter distant supervision training dataset and redistribute the false positive instances into the negative set, in which way to provide a cleaned dataset for relation classification. The experimental results show that the proposed strategy significantly improves the performance of distant supervision relation extraction comparing to state-of-the-art systems.</abstract>
    <identifier type="citekey">qin-etal-2018-dsgan</identifier>
    <identifier type="doi">10.18653/v1/P18-1046</identifier>
    <location>
        <url>https://aclanthology.org/P18-1046</url>
    </location>
    <part>
        <date>2018-07</date>
        <extent unit="page">
            <start>496</start>
            <end>505</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T DSGAN: Generative Adversarial Training for Distant Supervision Relation Extraction
%A Qin, Pengda
%A Xu, Weiran
%A Wang, William Yang
%Y Gurevych, Iryna
%Y Miyao, Yusuke
%S Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F qin-etal-2018-dsgan
%X Distant supervision can effectively label data for relation extraction, but suffers from the noise labeling problem. Recent works mainly perform soft bag-level noise reduction strategies to find the relatively better samples in a sentence bag, which is suboptimal compared with making a hard decision of false positive samples in sentence level. In this paper, we introduce an adversarial learning framework, which we named DSGAN, to learn a sentence-level true-positive generator. Inspired by Generative Adversarial Networks, we regard the positive samples generated by the generator as the negative samples to train the discriminator. The optimal generator is obtained until the discrimination ability of the discriminator has the greatest decline. We adopt the generator to filter distant supervision training dataset and redistribute the false positive instances into the negative set, in which way to provide a cleaned dataset for relation classification. The experimental results show that the proposed strategy significantly improves the performance of distant supervision relation extraction comparing to state-of-the-art systems.
%R 10.18653/v1/P18-1046
%U https://aclanthology.org/P18-1046
%U https://doi.org/10.18653/v1/P18-1046
%P 496-505

Markdown (Informal)

[DSGAN: Generative Adversarial Training for Distant Supervision Relation Extraction](https://aclanthology.org/P18-1046) (Qin et al., ACL 2018)

• DSGAN: Generative Adversarial Training for Distant Supervision Relation Extraction (Qin et al., ACL 2018)

ACL

• Pengda Qin, Weiran Xu, and William Yang Wang. 2018. DSGAN: Generative Adversarial Training for Distant Supervision Relation Extraction. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 496–505, Melbourne, Australia. Association for Computational Linguistics.