Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering

Alexander Hanbo Li, Patrick Ng, Peng Xu, Henghui Zhu, Zhiguo Wang, Bing Xiang


Abstract
The current state-of-the-art generative models for open-domain question answering (ODQA) have focused on generating direct answers from unstructured textual information. However, a large amount of world’s knowledge is stored in structured databases, and need to be accessed using query languages such as SQL. Furthermore, query languages can answer questions that require complex reasoning, as well as offering full explainability. In this paper, we propose a hybrid framework that takes both textual and tabular evidences as input and generates either direct answers or SQL queries depending on which form could better answer the question. The generated SQL queries can then be executed on the associated databases to obtain the final answers. To the best of our knowledge, this is the first paper that applies Text2SQL to ODQA tasks. Empirically, we demonstrate that on several ODQA datasets, the hybrid methods consistently outperforms the baseline models that only takes homogeneous input by a large margin. Specifically we achieve the state-of-the-art performance on OpenSQuAD dataset using a T5-base model. In a detailed analysis, we demonstrate that the being able to generate structural SQL queries can always bring gains, especially for those questions that requires complex reasoning.
Anthology ID:
2021.acl-long.315
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4078–4088
Language:
URL:
https://aclanthology.org/2021.acl-long.315
DOI:
10.18653/v1/2021.acl-long.315
Bibkey:
Cite (ACL):
Alexander Hanbo Li, Patrick Ng, Peng Xu, Henghui Zhu, Zhiguo Wang, and Bing Xiang. 2021. Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 4078–4088, Online. Association for Computational Linguistics.
Cite (Informal):
Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering (Li et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-acl-2023-videos/2021.acl-long.315.pdf
Optional supplementary material:
 2021.acl-long.315.OptionalSupplementaryMaterial.zip
Code
 awslabs/durepa-hybrid-qa
Data
HybridQANatural QuestionsOTT-QASQuADWikiSQL