SentencePiece

AbstractMi’kmaq is an Indigenous language spoken primarily in Eastern Canada. It is polysynthetic and low-resource. In this paper we consider a range of n-gram and RNN language models for Mi’kmaq. …...

AbstractPre-trained models have achieved great success in learning unsupervised language representations by self-supervised tasks on large-scale corpora. Recent studies mainly focus on how to fine-tune different downstream tasks from a …...

AbstractThe Transformer model is the state-of-the-art in Machine Translation. However and in general and neural translation models often under perform on language pairs with insufficient training data. As a consequence …...

AbstractWe present a subword regularization method for WordPiece, which uses a maximum matching algorithm for tokenization. The proposed method, MaxMatch-Dropout, randomly drops words in a search using the maximum matching …...