Towards A Dependency Parser For Basque

We present the Dependency Parser, called Maxuxta, for the linguistic processing of Basque, which can serve as a representative of agglutinative languages that are also characterized by the free order of its constituents. The Dependency syntactic model is applied to establish the dependency-based grammatical relations between the components within the clause. Such a deep analysis is used to improve the output of the shallow parsing where syntactic structure ambiguity is not fully and explicitly resolved. Previous to the completion of the grammar for the dependency parsing, the design of the Dependency Structure-based Scheme had to be accomplished; we concentrated on issues that must be resolved by any practical system that uses such models. This scheme was used both to the manual tagging of the corpus and to develop the parser. The manually tagged corpus has been used to evaluate the accuracy of the parser. We have evaluated the application of the grammar to corpus, measuring the linking of the verb with its dependents, with satisfactory results.