@inproceedings{sarrouti-etal-2021-evidence-based,
title = "Evidence-based Fact-Checking of Health-related Claims",
author = "Sarrouti, Mourad and
Ben Abacha, Asma and
Mrabet, Yassine and
Demner-Fushman, Dina",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.297",
doi = "10.18653/v1/2021.findings-emnlp.297",
pages = "3499--3512",
abstract = "The task of verifying the truthfulness of claims in textual documents, or fact-checking, has received significant attention in recent years. Many existing evidence-based factchecking datasets contain synthetic claims and the models trained on these data might not be able to verify real-world claims. Particularly few studies addressed evidence-based fact-checking of health-related claims that require medical expertise or evidence from the scientific literature. In this paper, we introduce HEALTHVER, a new dataset for evidence-based fact-checking of health-related claims that allows to study the validity of real-world claims by evaluating their truthfulness against scientific articles. Using a three-step data creation method, we first retrieved real-world claims from snippets returned by a search engine for questions about COVID-19. Then we automatically retrieved and re-ranked relevant scientific papers using a T5 relevance-based model. Finally, the relations between each evidence statement and the associated claim were manually annotated as SUPPORT, REFUTE and NEUTRAL. To validate the created dataset of 14,330 evidence-claim pairs, we developed baseline models based on pretrained language models. Our experiments showed that training deep learning models on real-world medical claims greatly improves performance compared to models trained on synthetic and open-domain claims. Our results and manual analysis suggest that HEALTHVER provides a realistic and challenging dataset for future efforts on evidence-based fact-checking of health-related claims. The dataset, source code, and a leaderboard are available at \url{https://github.com/sarrouti/healthver}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sarrouti-etal-2021-evidence-based">
<titleInfo>
<title>Evidence-based Fact-Checking of Health-related Claims</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mourad</namePart>
<namePart type="family">Sarrouti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asma</namePart>
<namePart type="family">Ben Abacha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yassine</namePart>
<namePart type="family">Mrabet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The task of verifying the truthfulness of claims in textual documents, or fact-checking, has received significant attention in recent years. Many existing evidence-based factchecking datasets contain synthetic claims and the models trained on these data might not be able to verify real-world claims. Particularly few studies addressed evidence-based fact-checking of health-related claims that require medical expertise or evidence from the scientific literature. In this paper, we introduce HEALTHVER, a new dataset for evidence-based fact-checking of health-related claims that allows to study the validity of real-world claims by evaluating their truthfulness against scientific articles. Using a three-step data creation method, we first retrieved real-world claims from snippets returned by a search engine for questions about COVID-19. Then we automatically retrieved and re-ranked relevant scientific papers using a T5 relevance-based model. Finally, the relations between each evidence statement and the associated claim were manually annotated as SUPPORT, REFUTE and NEUTRAL. To validate the created dataset of 14,330 evidence-claim pairs, we developed baseline models based on pretrained language models. Our experiments showed that training deep learning models on real-world medical claims greatly improves performance compared to models trained on synthetic and open-domain claims. Our results and manual analysis suggest that HEALTHVER provides a realistic and challenging dataset for future efforts on evidence-based fact-checking of health-related claims. The dataset, source code, and a leaderboard are available at https://github.com/sarrouti/healthver.</abstract>
<identifier type="citekey">sarrouti-etal-2021-evidence-based</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.297</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.297</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>3499</start>
<end>3512</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evidence-based Fact-Checking of Health-related Claims
%A Sarrouti, Mourad
%A Ben Abacha, Asma
%A Mrabet, Yassine
%A Demner-Fushman, Dina
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F sarrouti-etal-2021-evidence-based
%X The task of verifying the truthfulness of claims in textual documents, or fact-checking, has received significant attention in recent years. Many existing evidence-based factchecking datasets contain synthetic claims and the models trained on these data might not be able to verify real-world claims. Particularly few studies addressed evidence-based fact-checking of health-related claims that require medical expertise or evidence from the scientific literature. In this paper, we introduce HEALTHVER, a new dataset for evidence-based fact-checking of health-related claims that allows to study the validity of real-world claims by evaluating their truthfulness against scientific articles. Using a three-step data creation method, we first retrieved real-world claims from snippets returned by a search engine for questions about COVID-19. Then we automatically retrieved and re-ranked relevant scientific papers using a T5 relevance-based model. Finally, the relations between each evidence statement and the associated claim were manually annotated as SUPPORT, REFUTE and NEUTRAL. To validate the created dataset of 14,330 evidence-claim pairs, we developed baseline models based on pretrained language models. Our experiments showed that training deep learning models on real-world medical claims greatly improves performance compared to models trained on synthetic and open-domain claims. Our results and manual analysis suggest that HEALTHVER provides a realistic and challenging dataset for future efforts on evidence-based fact-checking of health-related claims. The dataset, source code, and a leaderboard are available at https://github.com/sarrouti/healthver.
%R 10.18653/v1/2021.findings-emnlp.297
%U https://aclanthology.org/2021.findings-emnlp.297
%U https://doi.org/10.18653/v1/2021.findings-emnlp.297
%P 3499-3512
Markdown (Informal)
[Evidence-based Fact-Checking of Health-related Claims](https://aclanthology.org/2021.findings-emnlp.297) (Sarrouti et al., Findings 2021)
ACL
- Mourad Sarrouti, Asma Ben Abacha, Yassine Mrabet, and Dina Demner-Fushman. 2021. Evidence-based Fact-Checking of Health-related Claims. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 3499–3512, Punta Cana, Dominican Republic. Association for Computational Linguistics.