@inproceedings{li-etal-2019-gan,
title = "{GAN} Driven Semi-distant Supervision for Relation Extraction",
author = "Li, Pengshuai and
Zhang, Xinsong and
Jia, Weijia and
Zhao, Hai",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1307",
doi = "10.18653/v1/N19-1307",
pages = "3026--3035",
abstract = "Distant supervision has been widely used in relation extraction tasks without hand-labeled datasets recently. However, the automatically constructed datasets comprise numbers of wrongly labeled negative instances due to the incompleteness of knowledge bases, which is neglected by current distant supervised methods resulting in seriously misleading in both training and testing processes. To address this issue, we propose a novel semi-distant supervision approach for relation extraction by constructing a small accurate dataset and properly leveraging numerous instances without relation labels. In our approach, we construct accurate instances by both knowledge base and entity descriptions determined to avoid wrong negative labeling and further utilize unlabeled instances sufficiently using generative adversarial network (GAN) framework. Experimental results on real-world datasets show that our approach can achieve significant improvements in distant supervised relation extraction over strong baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2019-gan">
<titleInfo>
<title>GAN Driven Semi-distant Supervision for Relation Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pengshuai</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinsong</namePart>
<namePart type="family">Zhang</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">Hai</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-jun</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Distant supervision has been widely used in relation extraction tasks without hand-labeled datasets recently. However, the automatically constructed datasets comprise numbers of wrongly labeled negative instances due to the incompleteness of knowledge bases, which is neglected by current distant supervised methods resulting in seriously misleading in both training and testing processes. To address this issue, we propose a novel semi-distant supervision approach for relation extraction by constructing a small accurate dataset and properly leveraging numerous instances without relation labels. In our approach, we construct accurate instances by both knowledge base and entity descriptions determined to avoid wrong negative labeling and further utilize unlabeled instances sufficiently using generative adversarial network (GAN) framework. Experimental results on real-world datasets show that our approach can achieve significant improvements in distant supervised relation extraction over strong baselines.</abstract>
<identifier type="citekey">li-etal-2019-gan</identifier>
<identifier type="doi">10.18653/v1/N19-1307</identifier>
<location>
<url>https://aclanthology.org/N19-1307</url>
</location>
<part>
<date>2019-jun</date>
<extent unit="page">
<start>3026</start>
<end>3035</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GAN Driven Semi-distant Supervision for Relation Extraction
%A Li, Pengshuai
%A Zhang, Xinsong
%A Jia, Weijia
%A Zhao, Hai
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 jun
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F li-etal-2019-gan
%X Distant supervision has been widely used in relation extraction tasks without hand-labeled datasets recently. However, the automatically constructed datasets comprise numbers of wrongly labeled negative instances due to the incompleteness of knowledge bases, which is neglected by current distant supervised methods resulting in seriously misleading in both training and testing processes. To address this issue, we propose a novel semi-distant supervision approach for relation extraction by constructing a small accurate dataset and properly leveraging numerous instances without relation labels. In our approach, we construct accurate instances by both knowledge base and entity descriptions determined to avoid wrong negative labeling and further utilize unlabeled instances sufficiently using generative adversarial network (GAN) framework. Experimental results on real-world datasets show that our approach can achieve significant improvements in distant supervised relation extraction over strong baselines.
%R 10.18653/v1/N19-1307
%U https://aclanthology.org/N19-1307
%U https://doi.org/10.18653/v1/N19-1307
%P 3026-3035
Markdown (Informal)
[GAN Driven Semi-distant Supervision for Relation Extraction](https://aclanthology.org/N19-1307) (Li et al., NAACL 2019)
ACL
- Pengshuai Li, Xinsong Zhang, Weijia Jia, and Hai Zhao. 2019. GAN Driven Semi-distant Supervision for Relation Extraction. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 3026–3035, Minneapolis, Minnesota. Association for Computational Linguistics.