MirrorAlign: A Super Lightweight Unsupervised Word Alignment Model via Cross-Lingual Contrastive Learning

Di Wu, Liang Ding, Shuo Yang, Mingyang Li

Abstract
Word alignment is essential for the downstream cross-lingual language understanding and generation tasks. Recently, the performance of the neural word alignment models has exceeded that of statistical models. However, they heavily rely on sophisticated translation models. In this study, we propose a super lightweight unsupervised word alignment model named MirrorAlign, in which bidirectional symmetric attention trained with a contrastive learning objective is introduced, and an agreement loss is employed to bind the attention maps, such that the alignments follow mirror-like symmetry hypothesis. Experimental results on several public benchmarks demonstrate that our model achieves competitive, if not better, performance compared to the state of the art in word alignment while significantly reducing the training and decoding time on average. Further ablation analysis and case studies show the superiority of our proposed MirrorAlign. Notably, we recognize our model as a pioneer attempt to unify bilingual word embedding and word alignments. Encouragingly, our approach achieves 16.4X speedup against GIZA++, and 50X parameter compression compared with the Transformer-based alignment methods. We release our code to facilitate the community: https://github.com/moore3930/MirrorAlign.
Anthology ID:
2022.iwslt-1.8
Volume:
Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)
Month:
May
Year:
2022
Address:
Dublin, Ireland (in-person and online)
Editors:
Elizabeth Salesky, Marcello Federico, Marta Costa-jussà
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Association for Computational Linguistics
Note:
Pages:
83–91
Language:
URL:
https://aclanthology.org/2022.iwslt-1.8
DOI:
10.18653/v1/2022.iwslt-1.8
Bibkey:
Cite (ACL):
Di Wu, Liang Ding, Shuo Yang, and Mingyang Li. 2022. MirrorAlign: A Super Lightweight Unsupervised Word Alignment Model via Cross-Lingual Contrastive Learning. In Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022), pages 83–91, Dublin, Ireland (in-person and online). Association for Computational Linguistics.
Cite (Informal):
MirrorAlign: A Super Lightweight Unsupervised Word Alignment Model via Cross-Lingual Contrastive Learning (Wu et al., IWSLT 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp-22-attachments/2022.iwslt-1.8.pdf
PDF Search