@inproceedings{feng-lakshmanan-2024-dure,
title = "{D}u{RE}: Dual Contrastive Self Training for Semi-Supervised Relation Extraction",
author = "Feng, Yuxi and
Lakshmanan, Laks",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.30",
pages = "540--555",
abstract = "Document-level Relation Extraction (RE) aims to extract relation triples from documents. Existing document-RE models typically rely on supervised learning which requires substantial labeled data. To alleviate the amount of human supervision, Self-training (ST) has prospered again in language understanding by augmenting the fine-tuning of big pre-trained models whenever labeled data is insufficient. However, existing ST methods in RE fail to tackle the challenge of long-tail relations. In this work, we propose DuRE, a novel ST framework to tackle these problems. DuRE jointly models RE classification and text generation as a dual process. In this way, our model could construct and utilize both pseudo text generated from given labels and pseudo labels predicted from available unlabeled text, which are gradually refined during the ST phase. We proposed a contrastive loss to leverage the signal of the RE classifier to improve generation quality. In addition, we propose a self-adaptive way to sample pseudo text from different relation classes. Experiments on two document-level RE tasks show that DuRE significantly boosts recall and F1 score with comparable precision, especially for long-tail relations against several strong baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="feng-lakshmanan-2024-dure">
<titleInfo>
<title>DuRE: Dual Contrastive Self Training for Semi-Supervised Relation Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuxi</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laks</namePart>
<namePart type="family">Lakshmanan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Document-level Relation Extraction (RE) aims to extract relation triples from documents. Existing document-RE models typically rely on supervised learning which requires substantial labeled data. To alleviate the amount of human supervision, Self-training (ST) has prospered again in language understanding by augmenting the fine-tuning of big pre-trained models whenever labeled data is insufficient. However, existing ST methods in RE fail to tackle the challenge of long-tail relations. In this work, we propose DuRE, a novel ST framework to tackle these problems. DuRE jointly models RE classification and text generation as a dual process. In this way, our model could construct and utilize both pseudo text generated from given labels and pseudo labels predicted from available unlabeled text, which are gradually refined during the ST phase. We proposed a contrastive loss to leverage the signal of the RE classifier to improve generation quality. In addition, we propose a self-adaptive way to sample pseudo text from different relation classes. Experiments on two document-level RE tasks show that DuRE significantly boosts recall and F1 score with comparable precision, especially for long-tail relations against several strong baselines.</abstract>
<identifier type="citekey">feng-lakshmanan-2024-dure</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.30</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>540</start>
<end>555</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DuRE: Dual Contrastive Self Training for Semi-Supervised Relation Extraction
%A Feng, Yuxi
%A Lakshmanan, Laks
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F feng-lakshmanan-2024-dure
%X Document-level Relation Extraction (RE) aims to extract relation triples from documents. Existing document-RE models typically rely on supervised learning which requires substantial labeled data. To alleviate the amount of human supervision, Self-training (ST) has prospered again in language understanding by augmenting the fine-tuning of big pre-trained models whenever labeled data is insufficient. However, existing ST methods in RE fail to tackle the challenge of long-tail relations. In this work, we propose DuRE, a novel ST framework to tackle these problems. DuRE jointly models RE classification and text generation as a dual process. In this way, our model could construct and utilize both pseudo text generated from given labels and pseudo labels predicted from available unlabeled text, which are gradually refined during the ST phase. We proposed a contrastive loss to leverage the signal of the RE classifier to improve generation quality. In addition, we propose a self-adaptive way to sample pseudo text from different relation classes. Experiments on two document-level RE tasks show that DuRE significantly boosts recall and F1 score with comparable precision, especially for long-tail relations against several strong baselines.
%U https://aclanthology.org/2024.naacl-long.30
%P 540-555
Markdown (Informal)
[DuRE: Dual Contrastive Self Training for Semi-Supervised Relation Extraction](https://aclanthology.org/2024.naacl-long.30) (Feng & Lakshmanan, NAACL 2024)
ACL