Classifying the lexico-syntactic patterns of semantic relations between two nouns in Romanian language

A very important step toward the goal of human-computer dialog using natural language is the identification of semantic relations between different constituents of texts or speech. The semantic relations that can be established between the words senses are related to their part-of-speech. Because the noun is one of the most important lexical categories we focused on the semantic relations encoded by a lexico-syntactic pattern between two nouns. The identification of the syntactic dependencies established between the two nouns in Romanian language is strong correlated with the lexico-syntactic patterns that contain them. In this paper we present the results of these patterns classification using different lexico-syntactic features and three supervised learning methods (decision trees, Naïve Bayes and k-nearest neighbors).