Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding

Haoli Bai, Zhiguang Liu, Xiaojun Meng, Li Wentao, Shuang Liu, Yifeng Luo, Nian Xie, Rongfu Zheng, Liangwei Wang, Lu Hou, Jiansheng Wei, Xin Jiang, Qun Liu


Abstract
Unsupervised pre-training on millions of digital-born or scanned documents has shown promising advances in visual document understanding (VDU). While various vision-language pre-training objectives are studied in existing solutions, the document textline, as an intrinsic granularity in VDU, has seldom been explored so far. A document textline usually contains words that are spatially and semantically correlated, which can be easily obtained from OCR engines. In this paper, we propose Wukong-Reader, trained with new pre-training objectives to leverage the structural knowledge nested in document textlines. We introduce textline-region contrastive learning to achieve fine-grained alignment between the visual regions and texts of document textlines. Furthermore, masked region modeling and textline-grid matching are also designed to enhance the visual and layout representations of textlines. Experiments show that Wukong-Reader brings superior performance on various VDU tasks in both English and Chinese. The fine-grained alignment over textlines also empowers Wukong-Reader with promising localization ability.
Anthology ID:
2023.acl-long.748
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13386–13401
Language:
URL:
https://aclanthology.org/2023.acl-long.748
DOI:
10.18653/v1/2023.acl-long.748
Bibkey:
Cite (ACL):
Haoli Bai, Zhiguang Liu, Xiaojun Meng, Li Wentao, Shuang Liu, Yifeng Luo, Nian Xie, Rongfu Zheng, Liangwei Wang, Lu Hou, Jiansheng Wei, Xin Jiang, and Qun Liu. 2023. Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13386–13401, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding (Bai et al., ACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/remove-xml-comments/2023.acl-long.748.pdf