Mathias Hans Erik Stenlund


2023

pdf bib
Improving Translation Quality for Low-Resource Inuktitut with Various Preprocessing Techniques
Mathias Hans Erik Stenlund | Mathilde Nanni | Micaella Bruton | Meriem Beloucif
Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing

Neural machine translation has been shown to outperform all other machine translation paradigms when trained in a high-resource setting. However, it still performs poorly when dealing with low-resource languages, for which parallel data for training is scarce. This is especially the case for morphologically complex languages such as Turkish, Tamil, Uyghur, etc. In this paper, we investigate various preprocessing methods for Inuktitut, a low-resource indigenous language from North America, without a morphological analyzer. On both the original and romanized scripts, we test various preprocessing techniques such as Byte-Pair Encoding, random stemming, and data augmentation using Hungarian for the Inuktitut-to-English translation task. We found that there are benefits to retaining the original script as it helps to achieve higher BLEU scores than the romanized models.