Machine Translation of Low-Resource Indo-European Languages
This work addresses translation challenges for low-resource language communities, but it is incremental as it builds on existing transfer learning methods.
The paper tackled machine translation for low-resource Indo-European languages by comparing transfer learning from related versus unrelated language pairs, finding that relatedness improves performance but is not essential.
In this work, we investigate methods for the challenging task of translating between low-resource language pairs that exhibit some level of similarity. In particular, we consider the utility of transfer learning for translating between several Indo-European low-resource languages from the Germanic and Romance language families. In particular, we build two main classes of transfer-based systems to study how relatedness can benefit the translation performance. The primary system fine-tunes a model pre-trained on a related language pair and the contrastive system fine-tunes one pre-trained on an unrelated language pair. Our experiments show that although relatedness is not necessary for transfer learning to work, it does benefit model performance.