Incorporating External Knowledge to Enhance Tabular Reasoning

TL;DR

This paper explores how incorporating external knowledge and presentation strategies can significantly improve the performance of NLP models on tabular reasoning tasks, specifically in natural language inference.

Contribution

The paper introduces simple yet effective modifications to data presentation that enhance model reasoning capabilities on tabular data.

Findings

Modified data presentation strategies improve inference accuracy

Systematic experiments demonstrate substantial performance gains

Approach is easy to implement and generalizes across models

Abstract

Reasoning about tabular information presents unique challenges to modern NLP approaches which largely rely on pre-trained contextualized embeddings of text. In this paper, we study these challenges through the problem of tabular natural language inference. We propose easy and effective modifications to how information is presented to a model for this task. We show via systematic experiments that these strategies substantially improve tabular inference performance.