Low-resource Neural Machine Translation with Cross-modal Alignment

Zhe Yang, Qingkai Fang, Yang Feng


Abstract
How to achieve neural machine translation with limited parallel data? Existing techniques often rely on large-scale monolingual corpus, which is impractical for some low-resource languages. In this paper, we turn to connect several low-resource languages to a particular high-resource one by additional visual modality. Specifically, we propose a cross-modal contrastive learning method to learn a shared space for all languages, where both a coarse-grained sentence-level objective and a fine-grained token-level one are introduced. Experimental results and further analysis show that our method can effectively learn the cross-modal and cross-lingual alignment with a small amount of image-text pairs, and achieves significant improvements over the text-only baseline under both zero-shot and few-shot scenarios.
Anthology ID:
2022.emnlp-main.689
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10134–10146
Language:
URL:
https://aclanthology.org/2022.emnlp-main.689
DOI:
10.18653/v1/2022.emnlp-main.689
Bibkey:
Cite (ACL):
Zhe Yang, Qingkai Fang, and Yang Feng. 2022. Low-resource Neural Machine Translation with Cross-modal Alignment. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 10134–10146, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Low-resource Neural Machine Translation with Cross-modal Alignment (Yang et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.689.pdf