TableFormer: Robust Transformer Modeling for Table-Text Encoding

doi:10.48550/arXiv.2203.00274

Paper

TableFormer: Robust Transformer Modeling for Table-Text Encoding

Published Mar 1, 2022 · Jingfeng Yang, Aditya Gupta, Shyam Upadhyay

ArXiv

115

Citations

14

Influential Citations

PDF

Abstract

Understanding tables is an important aspect of natural language understanding. Existing models for table understanding require linearization of the table structure, where row or column order is encoded as an unwanted bias. Such spurious biases make the model vulnerable to row and column order perturbations. Additionally, prior work has not thoroughly modeled the table structures or table-text alignments, hindering the table-text understanding ability. In this work, we propose a robust and structurally aware table-text encoding architecture TableFormer, where tabular structural biases are incorporated completely through learnable attention biases. TableFormer is (1) strictly invariant to row and column orders, and, (2) could understand tables better due to its tabular inductive biases. Our evaluations showed that TableFormer outperforms strong baselines in all settings on SQA, WTQ and TabFact table reasoning datasets, and achieves state-of-the-art performance on SQA, especially when facing answer-invariant row and column order perturbations (6% improvement over the best baseline), because previous SOTA models’ performance drops by 4% - 6% when facing such perturbations while TableFormer is not affected.

Highly CitedPreprint

Study Snapshot

TableFormer is a robust and structurally aware table-text encoding architecture that improves table understanding by incorporating tabular structural biases through learnable attention biases.

PopulationOlder adults (50-71 years)

Sample size24

MethodsObservational

OutcomesBody Mass Index projections

ResultsSocial networks mitigate obesity in older groups.

TableFormer: Robust Transformer Modeling for Table-Text Encoding

References

Citations