<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="teru-2023-semi">
    <titleInfo>
        <title>Semi-supervised Relation Extraction via Data Augmentation and Consistency-training</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Komal</namePart>
        <namePart type="family">Teru</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Andreas</namePart>
            <namePart type="family">Vlachos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Isabelle</namePart>
            <namePart type="family">Augenstein</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Dubrovnik, Croatia</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Due to the semantic complexity of the Relation extraction (RE) task, obtaining high-quality human labelled data is an expensive and noisy process. To improve the sample efficiency of the models, semi-supervised learning (SSL) methods aim to leverage unlabelled data in addition to learning from limited labelled data points. Recently, strong data augmentation combined with consistency-based semi-supervised learning methods have advanced the state of the art in several SSL tasks. However, adapting these methods to the RE task has been challenging due to the difficulty of data augmentation for RE. In this work, we leverage the recent advances in controlled text generation to perform high-quality data augmentation for the RE task. We further introduce small but significant changes to model architecture that allows for generation of more training data by interpolating different data points in their latent space. These data augmentations along with consistency training result in very competitive results for semi-supervised relation extraction on four benchmark datasets.</abstract>
    <identifier type="citekey">teru-2023-semi</identifier>
    <identifier type="doi">10.18653/v1/2023.eacl-main.79</identifier>
    <location>
        <url>https://aclanthology.org/2023.eacl-main.79</url>
    </location>
    <part>
        <date>2023-05</date>
        <extent unit="page">
            <start>1112</start>
            <end>1124</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Semi-supervised Relation Extraction via Data Augmentation and Consistency-training
%A Teru, Komal
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F teru-2023-semi
%X Due to the semantic complexity of the Relation extraction (RE) task, obtaining high-quality human labelled data is an expensive and noisy process. To improve the sample efficiency of the models, semi-supervised learning (SSL) methods aim to leverage unlabelled data in addition to learning from limited labelled data points. Recently, strong data augmentation combined with consistency-based semi-supervised learning methods have advanced the state of the art in several SSL tasks. However, adapting these methods to the RE task has been challenging due to the difficulty of data augmentation for RE. In this work, we leverage the recent advances in controlled text generation to perform high-quality data augmentation for the RE task. We further introduce small but significant changes to model architecture that allows for generation of more training data by interpolating different data points in their latent space. These data augmentations along with consistency training result in very competitive results for semi-supervised relation extraction on four benchmark datasets.
%R 10.18653/v1/2023.eacl-main.79
%U https://aclanthology.org/2023.eacl-main.79
%U https://doi.org/10.18653/v1/2023.eacl-main.79
%P 1112-1124

Markdown (Informal)

[Semi-supervised Relation Extraction via Data Augmentation and Consistency-training](https://aclanthology.org/2023.eacl-main.79) (Teru, EACL 2023)

• Semi-supervised Relation Extraction via Data Augmentation and Consistency-training (Teru, EACL 2023)

ACL

• Komal Teru. 2023. Semi-supervised Relation Extraction via Data Augmentation and Consistency-training. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 1112–1124, Dubrovnik, Croatia. Association for Computational Linguistics.