Machine Translation for English–Inuktitut with Segmentation, Data Acquisition and Pre-Training
C.W.J. Roest, Lukas Edman, Gosse Minnema, Kevin Kelly, Jennifer K. Spenader, Antonio Toral · 2020
Translating to and from low-resource polysynthetic languages present numerous challenges for NMT.We present the results of our systems for the English-Inuktitut language pair for the WMT 2020 translation tasks.We investigated the importance of correct morphological segmentation, whether or not adding data from a related language (Greenlandic) helps, and whether using contextual word embeddings improves translation.While each method showed some promise, the results are mixed.