On Romanization for Model Transfer Between Scripts in Neural Machine Translation
This addresses a specific challenge in low-resource machine translation for languages with different scripts, but the findings are incremental as it builds on existing transfer learning techniques.
The study investigated using romanization to improve neural machine translation transfer between languages with different scripts, finding it can help for related languages but causes information loss and is not always better than simpler methods.
Transfer learning is a popular strategy to improve the quality of low-resource machine translation. For an optimal transfer of the embedding layer, the child and parent model should share a substantial part of the vocabulary. This is not the case when transferring to languages with a different script. We explore the benefit of romanization in this scenario. Our results show that romanization entails information loss and is thus not always superior to simpler vocabulary transfer methods, but can improve the transfer between related languages with different scripts. We compare two romanization tools and find that they exhibit different degrees of information loss, which affects translation quality. Finally, we extend romanization to the target side, showing that this can be a successful strategy when coupled with a simple deromanization model.