Unifying Cross-Lingual and Cross-Modal Modeling Towards Weakly Supervised Multilingual Vision-Language Pre-training

Zejun Li, Zhihao Fan, Jingjing Chen, Qi Zhang, Xuanjing Huang, Zhongyu Wei


Abstract
Multilingual Vision-Language Pre-training (VLP) is a promising but challenging topic due to the lack of large-scale multilingual image-text pairs. Existing works address the problem by translating English data into other languages, which is intuitive and the generated data is usually limited in form and scale. In this paper, we explore a more practical and scalable setting: weakly supervised multilingual VLP with only English image-text pairs and multilingual text corpora. We argue that the universal multilingual representation learned from texts allows the cross-modal interaction learned in English to be transferable to other languages. To this end, we propose a framework to effectively unify cross-lingual and cross-modal pre-training. For unified modeling on different data, we design an architecture with flexible modules to learn different interactions. Moreover, two unified tasks are introduced to efficiently guide the unified cross-lingual cross-modal learning. Extensive experiments demonstrate that our pre-trained model learns universal multilingual multimodal representations, allowing effective cross-lingual transfer on multimodal tasks. Code and models are available at https://github.com/FudanDISC/weakly-supervised-mVLP.
Anthology ID:
2023.acl-long.327
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5939–5958
Language:
URL:
https://aclanthology.org/2023.acl-long.327
DOI:
10.18653/v1/2023.acl-long.327
Bibkey:
Cite (ACL):
Zejun Li, Zhihao Fan, Jingjing Chen, Qi Zhang, Xuanjing Huang, and Zhongyu Wei. 2023. Unifying Cross-Lingual and Cross-Modal Modeling Towards Weakly Supervised Multilingual Vision-Language Pre-training. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5939–5958, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Unifying Cross-Lingual and Cross-Modal Modeling Towards Weakly Supervised Multilingual Vision-Language Pre-training (Li et al., ACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/2023.acl-long.327.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-2/2023.acl-long.327.mp4