SLUA: A Super Lightweight Unsupervised Word Alignment Model via Cross-Lingual Contrastive Learning.
Year: 2021
Type: preprint
Abstract: Word alignment is essential for the down-streaming 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 (SLUA) model, 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 SLUA. 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 will release our code to facilitate the community.
Source: arXiv (Cornell University)
Authors: Di Wu, Liang Ding, Shuo Yang, Dacheng Tao
Institution: The University of Sydney
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3126209702