Learn to Combine Linguistic and Symbolic Information for Table-based Fact Verification

Shi, Qi; Yu, Zhang; Yin, Qinye; Liu, Ting

doi:10.18653/v1/2020.coling-main.466

Cited by 20 publications

(21 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Main Results. We compare our model with different baselines on TABFACT, including LPA , Table-BERT , LogicalFactChecker (Zhong et al, 2020), HeterTFV (Shi et al, 2020), SAT (Zhang et al, 2020), ProgVGAT , and TAPAS . Details of the compared systems can be found in Appendix A.4.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Exploring Decomposition for Table-based Fact Verification

Yang¹,

Zhu²

2021

Preprint

View full text Add to dashboard Cite

Fact verification based on structured data is challenging as it requires models to understand both natural language and symbolic operations performed over tables. Although pretrained language models have demonstrated a strong capability in verifying simple statements, they struggle with complex statements that involve multiple operations. In this paper, we improve fact verification by decomposing complex statements into simpler subproblems. Leveraging the programs synthesized by a weakly supervised semantic parser, we propose a program-guided approach to constructing a pseudo dataset for decomposition model training. The subproblems, together with their predicted answers, serve as the intermediate evidence to enhance our fact verification model. Experiments show that our proposed approach achieves the new state-of-theart performance, an 82.7% accuracy, on the TABFACT benchmark.

show abstract

Section: Methodsmentioning

confidence: 99%

“…Our work focuses on fact verification based on structured tables . Unlike the previous work Zhong et al, 2020;Shi et al, 2020;, we propose a framework to verify statements via decomposition.…”

Section: Related Workmentioning

confidence: 99%

Exploring Decomposition for Table-based Fact Verification

Yang¹,

Zhu²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Recently, there has been work in areas related to table fact verification, especially since the release of the TabFact dataset. Many of these approaches are graph-based in nature (Shi et al, 2020;. The current stateof-the-art on the TabFact dataset is the recently released TAPAS model, which outperforms its predecessor by approximately 6%.…”

Section: Related Workmentioning

confidence: 99%

AttesTable at SemEval-2021 Task 9: Extending Statement Verification with Tables for Unknown Class, and Semantic Evidence Finding

Varma¹,

Jain²,

Ratadiya³

et al. 2021

Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)

View full text Add to dashboard Cite

This paper describes our approach for Task 9 of SemEval 2021: Statement Verification and Evidence Finding with Tables. We participated in both subtasks, namely statement verification and evidence finding. For the subtask of statement verification, we extend the TAPAS model to adapt to the 'unknown' class of statements by finetuning it on an augmented version of the task data. For the subtask of evidence finding, we finetune the DistilBERT model in a Siamese setting.

show abstract

“…propose to utilize masking in the self attention layer to model table structure. Shi et al (2020) and explore how to effectively combine both linguistic information and symbolic information for table-based fact verification. generate synthetic datasets to pre-train a TAPAS model to better understand tables for downstream tasks such as table-based fact verification and question answering.…”

Section: Related Workmentioning

confidence: 99%

Structural Encoding and Pre-training Matter: Adapting BERT for Table-Based Fact Verification

Dong¹,

Smith²

2021

Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume

View full text Add to dashboard Cite

Growing concern with online misinformation has encouraged NLP research on fact verification. Since writers often base their assertions on structured data, we focus here on verifying textual statements given evidence in tables. Starting from the Table Parsing (TAPAS) model developed for question answering (Herzig et al., 2020), we find that modeling table structure improves a language model pre-trained on unstructured text. Pre-training language models on English Wikipedia table data further improves performance. Pre-training on a question answering task with column-level cell rank information achieves the best performance. With improved pre-training and cell embeddings, this approach outperforms the state-of-the-art Numerically-aware Graph Neural Network table fact verification model (GNN-TabFact), increasing statement classification accuracy from 72.2% to 73.9% even without modeling numerical information. Incorporating numerical information with cell rankings and pre-training on a question-answering task increases accuracy to 76%. We further analyze accuracy on statements implicating single rows or multiple rows and columns of tables, on different numerical reasoning subtasks, and on generalizing to detecting errors in statements derived from the ToTTo table-totext generation dataset.

show abstract

Learn to Combine Linguistic and Symbolic Information for Table-based Fact Verification

Cited by 20 publications

References 23 publications

Exploring Decomposition for Table-based Fact Verification

Exploring Decomposition for Table-based Fact Verification

AttesTable at SemEval-2021 Task 9: Extending Statement Verification with Tables for Unknown Class, and Semantic Evidence Finding

Structural Encoding and Pre-training Matter: Adapting BERT for Table-Based Fact Verification

Contact Info

Product

Resources

About