Localize, Retrieve and Fuse: A Generalized Framework for Free-Form Question Answering over Tables

TL;DR

This paper introduces TAG-QA, a three-stage framework for free-form question answering over tables that combines cell localization, external knowledge retrieval, and answer generation, significantly improving answer quality.

Contribution

The paper presents a novel generalized approach for free-form TableQA that integrates graph neural networks, external knowledge, and fusion techniques, addressing reasoning over diverse table cells.

Findings

TAG-QA surpasses TAPAS by 17% BLEU-4 and 14% PARENT F-score.

TAG-QA outperforms T5 by 16% BLEU-4 and 12% PARENT F-score.

Experiments demonstrate TAG-QA's superior ability to generate faithful and coherent answers.

Abstract

Question answering on tabular data (a.k.a TableQA), which aims at generating answers to questions grounded on a provided table, has gained significant attention recently. Prior work primarily produces concise factual responses through information extraction from individual or limited table cells, lacking the ability to reason across diverse table cells. Yet, the realm of free-form TableQA, which demands intricate strategies for selecting relevant table cells and the sophisticated integration and inference of discrete data fragments, remains mostly unexplored. To this end, this paper proposes a generalized three-stage approach: Table-to- Graph conversion and cell localizing, external knowledge retrieval, and the fusion of table and text (called TAG-QA), to address the challenge of inferring long free-form answers in generative TableQA. In particular, TAG-QA (1) locates relevant table cells using a graph neural network to gather intersecting cells between relevant rows and columns, (2) leverages external knowledge from Wikipedia, and (3) generates answers by integrating both tabular data and natural linguistic information. Experiments showcase the superior capabilities of TAG-QA in generating sentences that are both faithful and coherent, particularly when compared to several state-of-the-art baselines. Notably, TAG-QA surpasses the robust pipeline-based baseline TAPAS by 17% and 14% in terms of BLEU-4 and PARENT F-score, respectively. Furthermore, TAG-QA outperforms the end-to-end model T5 by 16% and 12% on BLEU-4 and PARENT F-score, respectively.