Ensemble Learning for Low Resources Prepositional Phrase Attachment
Pavlos Nalmpantis, Romanos Kalamatianos, Konstantinos Kordas, Katia Lida Kermanidis · International Journal of Information Science · 2012
Prepositional phrase attachment is a major disambiguation problem when it’s about parsing natural language, for many languages. In this paper a low resources policy is proposed using supervised machine learning algorithms in order to resolve the disambiguation problem of prepositional phrase attachment in Modern Greek. It is a first attempt to resolve prepositional phrase attachment in Modern Greek, without using sophisticated syntactic annotation and semantic resources, but by employing sophisticated learning techniques i.e ensembles of classifiers.