The Celtic languages share a common linguistic phenomenon known as initial mutations; these consist of pronunciation and spelling changes that occur at the beginning of some words, triggered in certain semantic or syntactic contexts. Initial mutations occur quite frequently and all non-trivial NLP systems for the Celtic languages must learn to handle them properly. In this paper we describe and evaluate neural network models for predicting mutations in two of the six Celtic languages: Irish and Scottish Gaelic. We also discuss applications of these models to grammatical error detection and language modeling.

Manx Gaelic is one of the three Q-Celtic languages, along with Irish and Scottish Gaelic. We present a new dependency treebank for Manx consisting of 291 sentences and about 6000 tokens, annotated according to the Universal Dependency (UD) guidelines. To the best of our knowledge, this is the first annotated corpus of any kind for Manx. Our annotations generally follow the conventions established by the existing UD treebanks for Irish and Scottish Gaelic, although we highlight some areas where the grammar of Manx diverges, requiring new analyses. We use 10-fold cross validation to evaluate the accuracy of dependency parsers trained on the corpus, and compare these results with delexicalised models transferred from Irish and Scottish Gaelic.