Crosslingual Embeddings are Essential in UNMT for Distant Languages: An English to IndoAryan Case Study
This addresses the problem of low translation quality for distant language pairs in unsupervised machine translation, though it is incremental as it builds on existing UNMT methods.
The paper tackled poor translation quality in unsupervised neural machine translation for distant language pairs like English and Indo-Aryan languages, showing that initializing with cross-lingual embeddings improves BLEU scores by up to ten times over baselines.
Recent advances in Unsupervised Neural Machine Translation (UNMT) have minimized the gap between supervised and unsupervised machine translation performance for closely related language pairs. However, the situation is very different for distant language pairs. Lack of lexical overlap and low syntactic similarities such as between English and Indo-Aryan languages leads to poor translation quality in existing UNMT systems. In this paper, we show that initializing the embedding layer of UNMT models with cross-lingual embeddings shows significant improvements in BLEU score over existing approaches with embeddings randomly initialized. Further, static embeddings (freezing the embedding layer weights) lead to better gains compared to updating the embedding layer weights during training (non-static). We experimented using Masked Sequence to Sequence (MASS) and Denoising Autoencoder (DAE) UNMT approaches for three distant language pairs. The proposed cross-lingual embedding initialization yields BLEU score improvement of as much as ten times over the baseline for English-Hindi, English-Bengali, and English-Gujarati. Our analysis shows the importance of cross-lingual embedding, comparisons between approaches, and the scope of improvements in these systems.