TY - CHAP
T1 - PubHealthTab
T2 - 2022 Findings of the Association for Computational Linguistics: NAACL 2022
AU - Akhtar, Mubashara
AU - Cocarascu, Oana
AU - Simperl, Elena
N1 - Funding Information:
The authors acknowledge support from the Distributed AI (DAI) research group at King’s College London for creating the dataset.
Publisher Copyright:
© Findings of the Association for Computational Linguistics: NAACL 2022 - Findings.
PY - 2022
Y1 - 2022
N2 - Inspired by human fact checkers, who use different types of evidence (e.g. tables, images, audio) in addition to text, several datasets with tabular evidence data have been released in recent years. Whilst the datasets encourage research on table fact-checking, they rely on information from restricted data sources, such as Wikipedia for creating claims and extracting evidence data, making the fact-checking process different from the real-world process used by fact checkers. In this paper, we introduce PubHealthTab, a table fact-checking dataset based on real-world public health claims and noisy evidence tables from sources similar to those used by real fact checkers. We outline our approach for collecting evidence data from various websites and present an in-depth analysis of our dataset. Finally, we evaluate state-of-theart table representation and pre-trained models fine-tuned on our dataset, achieving an overall F1 score of 0.73.
AB - Inspired by human fact checkers, who use different types of evidence (e.g. tables, images, audio) in addition to text, several datasets with tabular evidence data have been released in recent years. Whilst the datasets encourage research on table fact-checking, they rely on information from restricted data sources, such as Wikipedia for creating claims and extracting evidence data, making the fact-checking process different from the real-world process used by fact checkers. In this paper, we introduce PubHealthTab, a table fact-checking dataset based on real-world public health claims and noisy evidence tables from sources similar to those used by real fact checkers. We outline our approach for collecting evidence data from various websites and present an in-depth analysis of our dataset. Finally, we evaluate state-of-theart table representation and pre-trained models fine-tuned on our dataset, achieving an overall F1 score of 0.73.
UR - http://www.scopus.com/inward/record.url?scp=85137370433&partnerID=8YFLogxK
M3 - Conference paper
AN - SCOPUS:85137370433
T3 - Findings of the Association for Computational Linguistics: NAACL 2022 - Findings
SP - 1
EP - 16
BT - Findings of the Association for Computational Linguistics
PB - Association for Computational Linguistics (ACL)
Y2 - 10 July 2022 through 15 July 2022
ER -