Finetuning a Kalaallisut-English machine translation system using web-crawled data
This work addresses machine translation for speakers of Kalaallisut, an extremely low-resource language, though it is incremental as it did not achieve improvements.
The researchers tackled the problem of machine translation for the low-resource Kalaallisut language by finetuning a pretrained system using web-crawled pseudoparallel data, but the resulting dataset was too small and noisy to improve the model.
West Greenlandic, known by native speakers as Kalaallisut, is an extremely low-resource polysynthetic language spoken by around 56,000 people in Greenland. Here, we attempt to finetune a pretrained Kalaallisut-to-English neural machine translation (NMT) system using web-crawled pseudoparallel sentences from around 30 multilingual websites. We compile a corpus of over 93,000 Kalaallisut sentences and over 140,000 Danish sentences, then use cross-lingual sentence embeddings and approximate nearest-neighbors search in an attempt to mine near-translations from these corpora. Finally, we translate the Danish sentence to English to obtain a synthetic Kalaallisut-English aligned corpus. Although the resulting dataset is too small and noisy to improve the pretrained MT model, we believe that with additional resources, we could construct a better pseudoparallel corpus and achieve more promising results on MT. We also note other possible uses of the monolingual Kalaallisut data and discuss directions for future work. We make the code and data for our experiments publicly available.