@inproceedings{wu2023tacr,
author = {Wu, Jian and Xu, Yicheng and Gao, Yan and Lou, Jian-Guang and Karlsson, Brje and Okumura, Manabu},
title = {TACR: A Table Alignment-based Cell Selection Method for HybridQA},
booktitle = {ACL 2023},
year = {2023},
month = {July},
abstract = {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 Table-alignment-based Cell-selection and Reasoning model (TACR) for hybrid text and table QA, evaluated on the HybridQA and WikiTableQuestions datasets. In evidence retrieval, we design a table-question-alignment enhanced cell-selection 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 state-of-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.},
url = {http://approjects.co.za/?big=en-us/research/publication/tacr-a-table-alignment-based-cell-selection-method-for-hybridqa/},
}