Enhancing Structured Evidence Extraction for Fact Verification

Zirui Wu, Nan Hu, Yansong Feng


Abstract
Open-domain fact verification is the task of verifying claims in natural language texts against extracted evidence. FEVEROUS is a benchmark that requires extracting and integrating both unstructured and structured evidence to verify a given claim. Previous models suffer from low recall of structured evidence extraction, i.e., table extraction and cell selection. In this paper, we propose a simple but effective method to enhance the extraction of structured evidence by leveraging the row and column semantics of tables. Our method comprises two components: (i) a coarse-grained table extraction module that selects tables based on rows and columns relevant to the claim and (ii) a fine-grained cell selection graph that combines both formats of evidence and enables multi-hop and numerical reasoning. We evaluate our method on FEVEROUS and achieve an evidence recall of 60.01% on the test set, which is 6.14% higher than the previous state-of-the-art performance. Our results demonstrate that our method can extract tables and select cells effectively, and provide better evidence sets for verdict prediction. Our code is released at https://github.com/WilliamZR/see-st
Anthology ID:
2023.emnlp-main.409
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6631–6641
Language:
URL:
https://aclanthology.org/2023.emnlp-main.409
DOI:
10.18653/v1/2023.emnlp-main.409
Bibkey:
Cite (ACL):
Zirui Wu, Nan Hu, and Yansong Feng. 2023. Enhancing Structured Evidence Extraction for Fact Verification. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 6631–6641, Singapore. Association for Computational Linguistics.
Cite (Informal):
Enhancing Structured Evidence Extraction for Fact Verification (Wu et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.409.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.409.mp4