Parsing Heterogeneous Corpora with a Rich Dependency Grammar

Grammar models conceived for parsing purposes are often poorer than models that are linguistically motivated. We present a rich grammar model which is linguistically satisfactory and based on the principles of dependency grammar. We show how a state-of-the-art dependency parser (mate tools) performs with this model, trained on the Syntactic Reference Corpus of Medieval French (SRCMF), a manually annotated corpus of medieval (Old French) texts. We focus on the problems caused by small and heterogeneous training sets typical for corpora of older periods. The result is the first publicly available dependency parser for Old French.