SynTQA: Synergistic Table-based Question Answering via Mixture of Text-to-SQL and E2E TQA
This work addresses table-based question answering for users needing accurate data retrieval, but it is incremental as it combines existing methods rather than introducing a new paradigm.
The paper tackled the problem of table-based question answering by comparing text-to-SQL and end-to-end approaches, finding that text-to-SQL excels with arithmetic and long tables while end-to-end methods handle ambiguity and complex schemas better, and proposed a synergistic approach that improved performance through answer selection.
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.