Understanding the Impact of Evidence-Aware Sentence Selection for Fact Checking
Giannis Bekoulis, Christina Papagiannopoulou, Nikos Deligiannis
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.- Anthology ID:
- 2021.nlp4if-1.4
- Original:
- 2021.nlp4if-1.4v1
- Version 2:
- 2021.nlp4if-1.4v2
- Volume:
- Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda
- Month:
- June
- Year:
- 2021
- Address:
- Online
- Editors:
- Anna Feldman, Giovanni Da San Martino, Chris Leberknight, Preslav Nakov
- Venue:
- NLP4IF
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 23–28
- Language:
- URL:
- https://aclanthology.org/2021.nlp4if-1.4
- DOI:
- 10.18653/v1/2021.nlp4if-1.4
- Cite (ACL):
- Giannis Bekoulis, Christina Papagiannopoulou, and Nikos Deligiannis. 2021. Understanding the Impact of Evidence-Aware Sentence Selection for Fact Checking. In Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda, pages 23–28, Online. Association for Computational Linguistics.
- Cite (Informal):
- Understanding the Impact of Evidence-Aware Sentence Selection for Fact Checking (Bekoulis et al., NLP4IF 2021)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2021.nlp4if-1.4.pdf
- Code
- bekou/evidence_aware_nlp4if
- Data
- FEVER