EMNLP Findings2021
Table-based Fact Verification With Salience-aware Learning
Fei Wang, Kexuan Sun, Jay Pujara, Pedro A. Szekely, Muhao Chen
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 salienceaware 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. 1
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
3 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data cites TabFact: A Large-scale Dataset for Table-based Fact Verification
- Understanding tables with intermediate pre-training cites TabFact: A Large-scale Dataset for Table-based Fact Verification
- Understanding tables with intermediate pre-training cites Learning The Difference That Makes A Difference With Counterfactually-Augmented Data
- ToTTo: A Controlled Table-To-Text Generation Dataset cites TabFact: A Large-scale Dataset for Table-based Fact Verification
- PASTA: Table-Operations Aware Fact Verification via Sentence-Table Cloze Pre-training cites TabFact: A Large-scale Dataset for Table-based Fact Verification
- PASTA: Table-Operations Aware Fact Verification via Sentence-Table Cloze Pre-training cites Understanding tables with intermediate pre-training
Cited by top-tier papers3
- Salience Allocation as Guidance for Abstractive SummarizationFei Wang, Kaiqiang Song, Hongming Zhang, Lifeng Jin et al.EMNLP 2022 · 26 citations
- PASTA: Table-Operations Aware Fact Verification via Sentence-Table Cloze Pre-trainingZihui Gu, Ju Fan, Nan Tang, Preslav Nakov et al.EMNLP 2022 · 19 citations
- Enhancing Multi-Hop Fact Verification with Structured Knowledge-Augmented Large Language ModelsHan Cao, Lingwei Wei, Wei Zhou, Songlin HuAAAI 2025 · 1 citation
Builds on13
- TabFact: A Large-scale Dataset for Table-based Fact VerificationWenhu Chen, Hongmin Wang, Jianshu Chen, Yunkai Zhang et al.ICLR 2020 · 674 citations
- Learning The Difference That Makes A Difference With Counterfactually-Augmented DataDivyansh Kaushik, Eduard H. Hovy, Zachary Chase LiptonICLR 2020 · 625 citations
- HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual DataWenhu Chen, Hanwen Zha, Zhiyu Chen, Wenhan Xiong et al.EMNLP Findings 2020 · 205 citations
- Understanding tables with intermediate pre-trainingJulian Martin Eisenschlos, Syrine Krichene, Thomas MüllerEMNLP Findings 2020 · 88 citations
- ToTTo: A Controlled Table-To-Text Generation DatasetAnkur P. Parikh, Xuezhi Wang, Sebastian Gehrmann, Manaal Faruqui et al.EMNLP 2020 · 69 citations
Related papers
- Exploring Decomposition for Table-based Fact VerificationXiaoyu Yang, Xiaodan ZhuEMNLP Findings 2021 · 16 citations
- Learning to Generate Programs for Table Fact Verification via Structure-Aware Semantic ParsingSuixin Ou, Yongmei LiuACL 2022 · 14 citations
- Program Enhanced Fact Verification with Verbalization and Graph Attention NetworkXiaoyu Yang, Feng Nie, Yufei Feng, Quan Liu et al.EMNLP 2020 · 48 citations
- TWT: Table with Written Text for Controlled Data-to-Text GenerationTongliang Li, Lei Fang, Jian-Guang Lou, Zhoujun LiEMNLP Findings 2021 · 12 citations
- Test-time Augmentation for Factual ProbingGo Kamoda, Benjamin Heinzerling, Keisuke Sakaguchi, Kentaro InuiEMNLP Findings 2023
