Cross-lingual Cross-modal Pretraining for Multimodal Retrieval

Hongliang Fei, Tan Yu, Ping Li


Abstract
Recent pretrained vision-language models have achieved impressive performance on cross-modal retrieval tasks in English. Their success, however, heavily depends on the availability of many annotated image-caption datasets for pretraining, where the texts are not necessarily in English. Although we can utilize machine translation (MT) tools to translate non-English text to English, the performance still largely relies on MT’s quality and may suffer from high latency problems in real-world applications. This paper proposes a new approach to learn cross-lingual cross-modal representations for matching images and their relevant captions in multiple languages. We seamlessly combine cross-lingual pretraining objectives and cross-modal pretraining objectives in a unified framework to learn image and text in a joint embedding space from available English image-caption data, monolingual and parallel corpus. We show that our approach achieves SOTA performance in retrieval tasks on two multimodal multilingual image caption benchmarks: Multi30k with German captions and MSCOCO with Japanese captions.
Anthology ID:
2021.naacl-main.285
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Editors:
Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3644–3650
Language:
URL:
https://aclanthology.org/2021.naacl-main.285
DOI:
10.18653/v1/2021.naacl-main.285
Bibkey:
Cite (ACL):
Hongliang Fei, Tan Yu, and Ping Li. 2021. Cross-lingual Cross-modal Pretraining for Multimodal Retrieval. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3644–3650, Online. Association for Computational Linguistics.
Cite (Informal):
Cross-lingual Cross-modal Pretraining for Multimodal Retrieval (Fei et al., NAACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-main.285.pdf
Video:
 https://aclanthology.org/2021.naacl-main.285.mp4
Data
MS COCO