Fact Extraction and VERification (FEVER) is a recently introduced task that consists of the following subtasks (i) document retrieval, (ii) sentence retrieval, and (iii) claim verification. In this work, we focus on the subtask of sentence retrieval. Specifically, we propose an evidence-aware transformer-based model that outperforms all other models in terms of FEVER score by using a subset of training instances. In addition, we conduct a large experimental study to get a better understanding of the problem, while we summarize our findings by presenting future research challenges.
Bekoulis, I, Papagiannopoulou, C & Deligiannis, N 2021, Understanding the Impact of Evidence-Aware Sentence Selection for Fact Checking. in A Feldman, G Da San Martino, C Leberknight & P Nakov (eds), Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda. NLP4IF 2021 - NLP for Internet Freedom: Censorship, Disinformation, and Propaganda, Proceedings of the 4th Workshop, Association for Computational Linguistics, pp. 23-28, 2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics, 6/06/21. <https://www.aclweb.org/anthology/2021.nlp4if-1.4.pdf>
Bekoulis, I., Papagiannopoulou, C., & Deligiannis, N. (2021). Understanding the Impact of Evidence-Aware Sentence Selection for Fact Checking. In A. Feldman, G. Da San Martino, C. Leberknight, & P. Nakov (Eds.), Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda (pp. 23-28). (NLP4IF 2021 - NLP for Internet Freedom: Censorship, Disinformation, and Propaganda, Proceedings of the 4th Workshop). Association for Computational Linguistics. https://www.aclweb.org/anthology/2021.nlp4if-1.4.pdf
@inproceedings{8eaee4f964ae49a49db4b4cc5b94df03,
title = "Understanding the Impact of Evidence-Aware Sentence Selection for Fact Checking",
abstract = "Fact Extraction and VERification (FEVER) is a recently introduced task that consists of the following subtasks (i) document retrieval, (ii) sentence retrieval, and (iii) claim verification. In this work, we focus on the subtask of sentence retrieval. Specifically, we propose an evidence-aware transformer-based model that outperforms all other models in terms of FEVER score by using a subset of training instances. In addition, we conduct a large experimental study to get a better understanding of the problem, while we summarize our findings by presenting future research challenges.",
author = "Ioannis Bekoulis and Christina Papagiannopoulou and Nikos Deligiannis",
note = "Publisher Copyright: {\textcopyright} 2021 Association for Computational Linguistics. Copyright: Copyright 2022 Elsevier B.V., All rights reserved.; 2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics, NAACL ; Conference date: 06-06-2021 Through 11-06-2021",
year = "2021",
month = jun,
language = "English",
series = "NLP4IF 2021 - NLP for Internet Freedom: Censorship, Disinformation, and Propaganda, Proceedings of the 4th Workshop",
publisher = "Association for Computational Linguistics",
pages = "23--28",
editor = "Anna Feldman and {Da San Martino}, Giovanni and Chris Leberknight and Preslav Nakov",
booktitle = "Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda",
url = "https://2021.naacl.org/",
}