Cross-model Back-translated Distillation for Unsupervised Machine Translation

Phi Xuan Nguyen, Shafiq Joty, Kui Wu, AiTi Aw

Keywords: unsupervised machine translation, NMT, machine translation

Abstract: Recent unsupervised machine translation (UMT) systems usually employ three main principles: initialization, language modeling and iterative back-translation, though they may apply them differently. Crucially, iterative back-translation and denoising auto-encoding for language modeling provide data diversity to train the UMT systems. However, these diversification processes may have reached their limit. We introduce a novel component to the standard UMT framework called Cross-model Back-translated Distillation (CBD), that is aimed to induce another level of data diversification that existing principles lack. CBD is applicable to all previous UMT approaches. In our experiments, it boosts the performance of the standard UMT methods by 1.5-2.0 BLEU. In particular, in WMT'14 English-French, WMT'16 German-English and English-Romanian, CBD outperforms cross-lingual masked language model (XLM) by 2.3, 2.2 and 1.6 BLEU, respectively. It also yields 1.5-3.3 BLEU improvements in IWSLT English-French and English-German tasks. Through extensive experimental analyses, we show that CBD is effective because it embraces data diversity while other similar variants do not.

One-sentence Summary: The paper introduces a method to improve unsupervised machine translation using two unsupervised agents to produce diverse data and conduct knowledge distillation.

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

Reviewed Version (pdf): https://openreview.net/references/pdf?id=XFUBx8OV4G