@inproceedings{xu-etal-2023-s2ynre,
title = "{S}2yn{RE}: Two-stage Self-training with Synthetic data for Low-resource Relation Extraction",
author = "Xu, Benfeng and
Wang, Quan and
Lyu, Yajuan and
Dai, Dai and
Zhang, Yongdong and
Mao, Zhendong",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.455/",
doi = "10.18653/v1/2023.acl-long.455",
pages = "8186--8207",
abstract = "Current relation extraction methods suffer from the inadequacy of large-scale annotated data. While distant supervision alleviates the problem of data quantities, there still exists domain disparity in data qualities due to its reliance on domain-restrained knowledge bases. In this work, we propose S2ynRE, a framework of two-stage Self-training with Synthetic data for Relation Extraction.We first leverage the capability of large language models to adapt to the target domain and automatically synthesize large quantities of coherent, realistic training data. We then propose an accompanied two-stage self-training algorithm that iteratively and alternately learns from synthetic and golden data together. We conduct comprehensive experiments and detailed ablations on popular relation extraction datasets to demonstrate the effectiveness of the proposed framework."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2023-s2ynre">
<titleInfo>
<title>S2ynRE: Two-stage Self-training with Synthetic data for Low-resource Relation Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Benfeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Quan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yajuan</namePart>
<namePart type="family">Lyu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dai</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongdong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhendong</namePart>
<namePart type="family">Mao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Current relation extraction methods suffer from the inadequacy of large-scale annotated data. While distant supervision alleviates the problem of data quantities, there still exists domain disparity in data qualities due to its reliance on domain-restrained knowledge bases. In this work, we propose S2ynRE, a framework of two-stage Self-training with Synthetic data for Relation Extraction.We first leverage the capability of large language models to adapt to the target domain and automatically synthesize large quantities of coherent, realistic training data. We then propose an accompanied two-stage self-training algorithm that iteratively and alternately learns from synthetic and golden data together. We conduct comprehensive experiments and detailed ablations on popular relation extraction datasets to demonstrate the effectiveness of the proposed framework.</abstract>
<identifier type="citekey">xu-etal-2023-s2ynre</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.455</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.455/</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>8186</start>
<end>8207</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T S2ynRE: Two-stage Self-training with Synthetic data for Low-resource Relation Extraction
%A Xu, Benfeng
%A Wang, Quan
%A Lyu, Yajuan
%A Dai, Dai
%A Zhang, Yongdong
%A Mao, Zhendong
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F xu-etal-2023-s2ynre
%X Current relation extraction methods suffer from the inadequacy of large-scale annotated data. While distant supervision alleviates the problem of data quantities, there still exists domain disparity in data qualities due to its reliance on domain-restrained knowledge bases. In this work, we propose S2ynRE, a framework of two-stage Self-training with Synthetic data for Relation Extraction.We first leverage the capability of large language models to adapt to the target domain and automatically synthesize large quantities of coherent, realistic training data. We then propose an accompanied two-stage self-training algorithm that iteratively and alternately learns from synthetic and golden data together. We conduct comprehensive experiments and detailed ablations on popular relation extraction datasets to demonstrate the effectiveness of the proposed framework.
%R 10.18653/v1/2023.acl-long.455
%U https://aclanthology.org/2023.acl-long.455/
%U https://doi.org/10.18653/v1/2023.acl-long.455
%P 8186-8207
Markdown (Informal)
[S2ynRE: Two-stage Self-training with Synthetic data for Low-resource Relation Extraction](https://aclanthology.org/2023.acl-long.455/) (Xu et al., ACL 2023)
ACL