Кечуа

AbstractWe show that unsupervised sequence-segmentation performance can be transferred to extremely low-resource languages by pre-training a Masked Segmental Language Model (Downey et al., 2021) multilingually. Further, we show that this …...

AbstractThis research has focused on evaluating the existing open-source morphological analyzers for two of the most widely spoken indigenous macrolanguages in South America, namely Quechua and Aymara. Firstly, we have …...