Cross-model Back-translated Distillation for Unsupervised Machine Translation
This addresses the problem of limited data diversity in unsupervised machine translation for researchers and practitioners, offering incremental improvements over existing methods.
The paper tackles the plateauing gains in unsupervised machine translation by introducing Cross-model Back-translated Distillation (CBD), which adds data diversification to existing frameworks, achieving state-of-the-art BLEU scores of 38.2, 30.1, and 36.3 on WMT tasks and 1.5-3.3 BLEU improvements on IWSLT tasks.
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, the gains from these diversification processes has seemed to plateau. 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, CBD achieves the state of the art in the WMT'14 English-French, WMT'16 English-German and English-Romanian bilingual unsupervised translation tasks, with 38.2, 30.1, and 36.3 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.