Mixed-modality Representation Learning and Pre-training for Joint Table-and-Text Retrieval in OpenQA

Junjie Huang, Wanjun Zhong, Qian Liu, Ming Gong, Daxin Jiang, Nan Duan


Abstract
Retrieving evidences from tabular and textual resources is essential for open-domain question answering (OpenQA), which provides more comprehensive information. However, training an effective dense table-text retriever is difficult due to the challenges of table-text discrepancy and data sparsity problem. To address the above challenges, we introduce an optimized OpenQA Table-Text Retriever (OTTeR) to jointly retrieve tabular and textual evidences. Firstly, we propose to enhance mixed-modality representation learning via two mechanisms: modality-enhanced representation and mixed-modality negative sampling strategy. Secondly, to alleviate data sparsity problem and enhance the general retrieval ability, we conduct retrieval-centric mixed-modality synthetic pre-training. Experimental results demonstrate that OTTeR substantially improves the performance of table-and-text retrieval on the OTT-QA dataset. Comprehensive analyses examine the effectiveness of all the proposed mechanisms. Besides, equipped with OTTeR, our OpenQA system achieves the state-of-the-art result on the downstream QA task, with 10.1% absolute improvement in terms of the exact match over the previous best system.
Anthology ID:
2022.findings-emnlp.303
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4117–4129
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.303
DOI:
10.18653/v1/2022.findings-emnlp.303
Bibkey:
Cite (ACL):
Junjie Huang, Wanjun Zhong, Qian Liu, Ming Gong, Daxin Jiang, and Nan Duan. 2022. Mixed-modality Representation Learning and Pre-training for Joint Table-and-Text Retrieval in OpenQA. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 4117–4129, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Mixed-modality Representation Learning and Pre-training for Joint Table-and-Text Retrieval in OpenQA (Huang et al., Findings 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-acl-2023-videos/2022.findings-emnlp.303.pdf