TACR: A Table Alignment-based Cell Selection Method for HybridQA
Jian Wu, Yicheng Xu, Yan Gao, Jian-Guang Lou, Börje Karlsson, Manabu Okumura
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.- Anthology ID:
- 2023.findings-acl.409
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2023
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6535–6549
- Language:
- URL:
- https://aclanthology.org/2023.findings-acl.409
- DOI:
- 10.18653/v1/2023.findings-acl.409
- Cite (ACL):
- Jian Wu, Yicheng Xu, Yan Gao, Jian-Guang Lou, Börje Karlsson, and Manabu Okumura. 2023. TACR: A Table Alignment-based Cell Selection Method for HybridQA. In Findings of the Association for Computational Linguistics: ACL 2023, pages 6535–6549, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- TACR: A Table Alignment-based Cell Selection Method for HybridQA (Wu et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/corrections-2024-07/2023.findings-acl.409.pdf