Zero-shot Fact Verification by Claim Generation
Liangming Pan, Wenhu Chen, Wenhan Xiong, Min-Yen Kan, William Yang Wang
Abstract
Neural models for automated fact verification have achieved promising results thanks to the availability of large, human-annotated datasets. However, for each new domain that requires fact verification, creating a dataset by manually writing claims and linking them to their supporting evidence is expensive. We develop QACG, a framework for training a robust fact verification model by using automatically generated claims that can be supported, refuted, or unverifiable from evidence from Wikipedia. QACG generates question-answer pairs from the evidence and then converts them into different types of claims. Experiments on the FEVER dataset show that our QACG framework significantly reduces the demand for human-annotated training data. In a zero-shot scenario, QACG improves a RoBERTa model’s F1 from 50% to 77%, equivalent in performance to 2K+ manually-curated examples. Our QACG code is publicly available.- Anthology ID:
- 2021.acl-short.61
- Volume:
- Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Editors:
- Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
- Venues:
- ACL | IJCNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 476–483
- Language:
- URL:
- https://aclanthology.org/2021.acl-short.61
- DOI:
- 10.18653/v1/2021.acl-short.61
- Cite (ACL):
- Liangming Pan, Wenhu Chen, Wenhan Xiong, Min-Yen Kan, and William Yang Wang. 2021. Zero-shot Fact Verification by Claim Generation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 476–483, Online. Association for Computational Linguistics.
- Cite (Informal):
- Zero-shot Fact Verification by Claim Generation (Pan et al., ACL-IJCNLP 2021)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2021.acl-short.61.pdf
- Code
- teacherpeterpan/Zero-shot-Fact-Verification
- Data
- FEVER, MultiNLI, QA2D