@inproceedings{sathe-etal-2020-automated,
title = "Automated Fact-Checking of Claims from {W}ikipedia",
author = "Sathe, Aalok and
Ather, Salar and
Le, Tuan Manh and
Perry, Nathan and
Park, Joonsuk",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.849",
pages = "6874--6882",
abstract = "Automated fact checking is becoming increasingly vital as both truthful and fallacious information accumulate online. Research on fact checking has benefited from large-scale datasets such as FEVER and SNLI. However, such datasets suffer from limited applicability due to the synthetic nature of claims and/or evidence written by annotators that differ from real claims and evidence on the internet. To this end, we present WikiFactCheck-English, a dataset of 124k+ triples consisting of a claim, context and an evidence document extracted from English Wikipedia articles and citations, as well as 34k+ manually written claims that are refuted by the evidence documents. This is the largest fact checking dataset consisting of real claims and evidence to date; it will allow the development of fact checking systems that can better process claims and evidence in the real world. We also show that for the NLI subtask, a logistic regression system trained using existing and novel features achieves peak accuracy of 68{\%}, providing a competitive baseline for future work. Also, a decomposable attention model trained on SNLI significantly underperforms the models trained on this dataset, suggesting that models trained on manually generated data may not be sufficiently generalizable or suitable for fact checking real-world claims.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sathe-etal-2020-automated">
<titleInfo>
<title>Automated Fact-Checking of Claims from Wikipedia</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aalok</namePart>
<namePart type="family">Sathe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salar</namePart>
<namePart type="family">Ather</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tuan</namePart>
<namePart type="given">Manh</namePart>
<namePart type="family">Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Perry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joonsuk</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Automated fact checking is becoming increasingly vital as both truthful and fallacious information accumulate online. Research on fact checking has benefited from large-scale datasets such as FEVER and SNLI. However, such datasets suffer from limited applicability due to the synthetic nature of claims and/or evidence written by annotators that differ from real claims and evidence on the internet. To this end, we present WikiFactCheck-English, a dataset of 124k+ triples consisting of a claim, context and an evidence document extracted from English Wikipedia articles and citations, as well as 34k+ manually written claims that are refuted by the evidence documents. This is the largest fact checking dataset consisting of real claims and evidence to date; it will allow the development of fact checking systems that can better process claims and evidence in the real world. We also show that for the NLI subtask, a logistic regression system trained using existing and novel features achieves peak accuracy of 68%, providing a competitive baseline for future work. Also, a decomposable attention model trained on SNLI significantly underperforms the models trained on this dataset, suggesting that models trained on manually generated data may not be sufficiently generalizable or suitable for fact checking real-world claims.</abstract>
<identifier type="citekey">sathe-etal-2020-automated</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.849</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>6874</start>
<end>6882</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automated Fact-Checking of Claims from Wikipedia
%A Sathe, Aalok
%A Ather, Salar
%A Le, Tuan Manh
%A Perry, Nathan
%A Park, Joonsuk
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F sathe-etal-2020-automated
%X Automated fact checking is becoming increasingly vital as both truthful and fallacious information accumulate online. Research on fact checking has benefited from large-scale datasets such as FEVER and SNLI. However, such datasets suffer from limited applicability due to the synthetic nature of claims and/or evidence written by annotators that differ from real claims and evidence on the internet. To this end, we present WikiFactCheck-English, a dataset of 124k+ triples consisting of a claim, context and an evidence document extracted from English Wikipedia articles and citations, as well as 34k+ manually written claims that are refuted by the evidence documents. This is the largest fact checking dataset consisting of real claims and evidence to date; it will allow the development of fact checking systems that can better process claims and evidence in the real world. We also show that for the NLI subtask, a logistic regression system trained using existing and novel features achieves peak accuracy of 68%, providing a competitive baseline for future work. Also, a decomposable attention model trained on SNLI significantly underperforms the models trained on this dataset, suggesting that models trained on manually generated data may not be sufficiently generalizable or suitable for fact checking real-world claims.
%U https://aclanthology.org/2020.lrec-1.849
%P 6874-6882
Markdown (Informal)
[Automated Fact-Checking of Claims from Wikipedia](https://aclanthology.org/2020.lrec-1.849) (Sathe et al., LREC 2020)
ACL
- Aalok Sathe, Salar Ather, Tuan Manh Le, Nathan Perry, and Joonsuk Park. 2020. Automated Fact-Checking of Claims from Wikipedia. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 6874–6882, Marseille, France. European Language Resources Association.