When do Contrastive Word Alignments Improve Many-to-many Neural Machine Translation?
This work addresses the challenge of enhancing translation quality for many-to-many NMT without relying on high-quality bilingual dictionaries, which are often unavailable, though it is incremental in nature.
The paper tackles the problem of improving many-to-many neural machine translation by proposing a word-level contrastive objective to leverage automatically learned word alignments, resulting in 0.8 BLEU gains for several language pairs.
Word alignment has proven to benefit many-to-many neural machine translation (NMT). However, high-quality ground-truth bilingual dictionaries were used for pre-editing in previous methods, which are unavailable for most language pairs. Meanwhile, the contrastive objective can implicitly utilize automatically learned word alignment, which has not been explored in many-to-many NMT. This work proposes a word-level contrastive objective to leverage word alignments for many-to-many NMT. Empirical results show that this leads to 0.8 BLEU gains for several language pairs. Analyses reveal that in many-to-many NMT, the encoder's sentence retrieval performance highly correlates with the translation quality, which explains when the proposed method impacts translation. This motivates future exploration for many-to-many NMT to improve the encoder's sentence retrieval performance.