Abstract
Tables provide valuable knowledge that can be used to verify textual statements. While a number of works have considered table-based fact verification, direct alignments of tabular data with tokens in textual statements are rarely available. Moreover, training a generalized fact verification model requires abundant labeled training data. In this paper, we propose a novel system to address these problems. Inspired by counterfactual causality, our system identifies token-level salience in the statement with probing-based salience estimation. Salience estimation allows enhanced learning of fact verification from two perspectives. From one perspective, our system conducts masked salient token prediction to enhance the model for alignment and reasoning between the table and the statement. From the other perspective, our system applies salience-aware data augmentation to generate a more diverse set of training instances by replacing non-salient terms. Experimental results on TabFact show the effective improvement by the proposed salience-aware learning techniques, leading to the new SOTA performance on the benchmark.- Anthology ID:
- 2021.findings-emnlp.338
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2021
- Month:
- November
- Year:
- 2021
- Address:
- Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- Findings
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4025–4036
- Language:
- URL:
- https://aclanthology.org/2021.findings-emnlp.338
- DOI:
- 10.18653/v1/2021.findings-emnlp.338
- Cite (ACL):
- Fei Wang, Kexuan Sun, Jay Pujara, Pedro Szekely, and Muhao Chen. 2021. Table-based Fact Verification With Salience-aware Learning. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 4025–4036, Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Table-based Fact Verification With Salience-aware Learning (Wang et al., Findings 2021)
- PDF:
- https://preview.aclanthology.org/add_acl24_videos/2021.findings-emnlp.338.pdf
- Code
- luka-group/salience-aware-learning
- Data
- TabFact