@inproceedings{bhartiya-etal-2022-dis,
title = "{D}i{S}-{R}e{X}: A Multilingual Dataset for Distantly Supervised Relation Extraction",
author = "Bhartiya, Abhyuday and
Badola, Kartikeya and
{Mausam}",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-short.95",
doi = "10.18653/v1/2022.acl-short.95",
pages = "849--863",
abstract = {Our goal is to study the novel task of distant supervision for multilingual relation extraction (Multi DS-RE). Research in Multi DS-RE has remained limited due to the absence of a reliable benchmarking dataset. The only available dataset for this task, RELX-Distant (K{\"o}ksal and {\"O}zg{\"u}r, 2020), displays several unrealistic characteristics, leading to a systematic overestimation of model performance. To alleviate these concerns, we release a new benchmark dataset for the task, named DiS-ReX. We also modify the widely-used bag attention models using an mBERT encoder and provide the first baseline results on the proposed task. We show that DiS-ReX serves as a more challenging dataset than RELX-Distant, leaving ample room for future research in this domain.},
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhartiya-etal-2022-dis">
<titleInfo>
<title>DiS-ReX: A Multilingual Dataset for Distantly Supervised Relation Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abhyuday</namePart>
<namePart type="family">Bhartiya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kartikeya</namePart>
<namePart type="family">Badola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name>
<namePart>Mausam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Our goal is to study the novel task of distant supervision for multilingual relation extraction (Multi DS-RE). Research in Multi DS-RE has remained limited due to the absence of a reliable benchmarking dataset. The only available dataset for this task, RELX-Distant (Köksal and Özgür, 2020), displays several unrealistic characteristics, leading to a systematic overestimation of model performance. To alleviate these concerns, we release a new benchmark dataset for the task, named DiS-ReX. We also modify the widely-used bag attention models using an mBERT encoder and provide the first baseline results on the proposed task. We show that DiS-ReX serves as a more challenging dataset than RELX-Distant, leaving ample room for future research in this domain.</abstract>
<identifier type="citekey">bhartiya-etal-2022-dis</identifier>
<identifier type="doi">10.18653/v1/2022.acl-short.95</identifier>
<location>
<url>https://aclanthology.org/2022.acl-short.95</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>849</start>
<end>863</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DiS-ReX: A Multilingual Dataset for Distantly Supervised Relation Extraction
%A Bhartiya, Abhyuday
%A Badola, Kartikeya
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%A Mausam
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F bhartiya-etal-2022-dis
%X Our goal is to study the novel task of distant supervision for multilingual relation extraction (Multi DS-RE). Research in Multi DS-RE has remained limited due to the absence of a reliable benchmarking dataset. The only available dataset for this task, RELX-Distant (Köksal and Özgür, 2020), displays several unrealistic characteristics, leading to a systematic overestimation of model performance. To alleviate these concerns, we release a new benchmark dataset for the task, named DiS-ReX. We also modify the widely-used bag attention models using an mBERT encoder and provide the first baseline results on the proposed task. We show that DiS-ReX serves as a more challenging dataset than RELX-Distant, leaving ample room for future research in this domain.
%R 10.18653/v1/2022.acl-short.95
%U https://aclanthology.org/2022.acl-short.95
%U https://doi.org/10.18653/v1/2022.acl-short.95
%P 849-863
Markdown (Informal)
[DiS-ReX: A Multilingual Dataset for Distantly Supervised Relation Extraction](https://aclanthology.org/2022.acl-short.95) (Bhartiya et al., ACL 2022)
ACL