Abstract
In Automated Claim Verification, we retrieve evidence from a knowledge base to determine the veracity of a claim. Intuitively, the retrieval of the correct evidence plays a crucial role in this process. Often, evidence selection is tackled as a pairwise sentence classification task, i.e., we train a model to predict for each sentence individually whether it is evidence for a claim. In this work, we fine-tune document level transformers to extract all evidence from a Wikipedia document at once. We show that this approach performs better than a comparable model classifying sentences individually on all relevant evidence selection metrics in FEVER. Our complete pipeline building on this evidence selection procedure produces a new state-of-the-art result on FEVER, a popular claim verification benchmark.- Anthology ID:
- 2021.fever-1.2
- Volume:
- Proceedings of the Fourth Workshop on Fact Extraction and VERification (FEVER)
- Month:
- November
- Year:
- 2021
- Address:
- Dominican Republic
- Venue:
- FEVER
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 14–20
- Language:
- URL:
- https://aclanthology.org/2021.fever-1.2
- DOI:
- 10.18653/v1/2021.fever-1.2
- Cite (ACL):
- Dominik Stammbach. 2021. Evidence Selection as a Token-Level Prediction Task. In Proceedings of the Fourth Workshop on Fact Extraction and VERification (FEVER), pages 14–20, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Evidence Selection as a Token-Level Prediction Task (Stammbach, FEVER 2021)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2021.fever-1.2.pdf
- Code
- dominiksinsaarland/document-level-fever
- Data
- FEVER