Abstract
Automatic fact-checking is crucial for recognizing misinformation spreading on the internet. Most existing fact-checkers break down the process into several subtasks, one of which determines candidate evidence sentences that can potentially support or refute the claim to be verified; typically, evidence sentences with gold-standard labels are needed for this. In a more realistic setting, however, such sentence-level annotations are not available. In this paper, we tackle the natural language inference (NLI) subtask—given a document and a (sentence) claim, determine whether the document supports or refutes the claim—only using document-level annotations. Using fine-tuned BERT and multiple instance learning, we achieve 81.9% accuracy, significantly outperforming the existing results on the WikiFactCheck-English dataset.- Anthology ID:
- 2021.fever-1.11
- Volume:
- Proceedings of the Fourth Workshop on Fact Extraction and VERification (FEVER)
- Month:
- November
- Year:
- 2021
- Address:
- Dominican Republic
- Editors:
- Rami Aly, Christos Christodoulopoulos, Oana Cocarascu, Zhijiang Guo, Arpit Mittal, Michael Schlichtkrull, James Thorne, Andreas Vlachos
- Venue:
- FEVER
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 101–107
- Language:
- URL:
- https://aclanthology.org/2021.fever-1.11
- DOI:
- 10.18653/v1/2021.fever-1.11
- Cite (ACL):
- Aalok Sathe and Joonsuk Park. 2021. Automatic Fact-Checking with Document-level Annotations using BERT and Multiple Instance Learning. In Proceedings of the Fourth Workshop on Fact Extraction and VERification (FEVER), pages 101–107, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Automatic Fact-Checking with Document-level Annotations using BERT and Multiple Instance Learning (Sathe & Park, FEVER 2021)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2021.fever-1.11.pdf
- Data
- FEVER, GLUE