SynTQA: Synergistic Table-based Question Answering via Mixture of Text-to-SQL and E2E TQA

TL;DR

This paper introduces SynTQA, a hybrid approach combining Text-to-SQL and end-to-end TQA models to leverage their respective strengths, resulting in improved performance on table-based question answering benchmarks.

Contribution

The paper proposes a novel synergistic framework that integrates Text-to-SQL and E2E TQA models through answer selection, enhancing overall accuracy.

Findings

Text-to-SQL handles arithmetic and long tables better.

E2E TQA is superior for ambiguous questions and complex tables.

Ensembling models improves performance significantly.

Abstract

Text-to-SQL parsing and end-to-end question answering (E2E TQA) are two main approaches for Table-based Question Answering task. Despite success on multiple benchmarks, they have yet to be compared and their synergy remains unexplored. In this paper, we identify different strengths and weaknesses through evaluating state-of-the-art models on benchmark datasets: Text-to-SQL demonstrates superiority in handling questions involving arithmetic operations and long tables; E2E TQA excels in addressing ambiguous questions, non-standard table schema, and complex table contents. To combine both strengths, we propose a Synergistic Table-based Question Answering approach that integrate different models via answer selection, which is agnostic to any model types. Further experiments validate that ensembling models by either feature-based or LLM-based answer selector significantly improves the performance over individual models.