Morphosyntactic disambiguation and shallow parsing in computational processing of Basque

Abstract

Our goal in this article is to show the improvements in the computational treatment of Basque, and more specifically, in the areas of morphosyntactic disambiguation and shallow parsing. The improvements presented in this paper include the following: analyses of previously identified ambiguities in morphosyntax and in syntactic functions, their disambiguation, and finally, an outline of possible steps in terms ofshallow parsing based on the results provided by the disambiguation process. The work is part of the current research within the field of Natural Language Processing (NLP) in Basque, and more specifically, part of the work that is being done within the IXA group.