Iterative Task-adaptive Pretraining for Unsupervised Word Alignment

Zhi Li, Gao Xing, Ji Zhang, Yin Zhang

Abstract: How to establish a closer relationship between pre-training and downstream task is a valuable question. We argue that task-adaptive pretraining should not just performed before task. For word alignment task, we propose an iterative self-supervised task-adaptive pretraining paradigm, tying together word alignment and self-supervised pretraining by code-switching data augmentation. When we get the aligned pairs predicted by the multilingual contextualized word embeddings, we employ these pairs and origin parallel sentences to synthesize code-switched sentences. Then multilingual models will be continuously finetuned on the augmented code-switched dataset. Finally, finetuned models will be used to produce new aligned pairs. This process will be executed iteratively. Our paradigm is suitable for almost all unsupervised word alignment methods based on multilingual pre-trained LMs and doesn't need gold labeled data, extra parallel data or any other external resources. Experimental results on six language pairs demonstrate that our paradigm can consistently improve baseline method. Compared to resource-rich languages, the improvements on relatively low-resource or different morphological languages are more significant. For example, the AER scores of three different alignment methods based on XLM-R are reduced by about $4 \sim 5$ percentage points on language pair En-Hi.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Applications (eg, speech processing, computer vision, NLP)