TACR: A Table Alignment-based Cell Selection Method for HybridQA
Jian Wu, Yicheng Xu, Yan Gao, Jian–Guang Lou, Börje F. Karlsson, Manabu Okumura · 2023
Hybrid Question-Answering (HQA), which targets reasoning over tables and passages linked from table cells, has witnessed significant research in recent years.A common challenge in HQA and other passage-table QA datasets is that it is generally unrealistic to iterate over all table rows, columns, and linked passages to retrieve evidence.Such a challenge made it difficult for previous studies to show their reasoning ability in retrieving answers.To bridge this gap, we propose a novel Tablealignment-based Cell-selection and Reasoning model (TACR) for hybrid text and table QA, evaluated on the HybridQA and WikiTable-Questions datasets.In evidence retrieval, we design a table-question-alignment enhanced cellselection method to retrieve fine-grained evidence.In answer reasoning, we incorporate a QA module that treats the row containing selected cells as context.Experimental results over the HybridQA and WikiTableQuestions (WTQ) datasets show that TACR achieves stateof-the-art results on cell selection and outperforms fine-grained evidence retrieval baselines on HybridQA, while achieving competitive performance on WTQ.We also conducted a detailed analysis to demonstrate that being able to align questions to tables in the cell-selection stage can result in important gains from experiments of over 90% table row and column selection accuracy, meanwhile also improving output explainability.