Can Alternations Be Learned? A Machine Learning Approach To Romanian Verb Conjugation
Liviu P. Dinu, Emil Ionescu, Vlad Niculae, Octavia-Maria Şulea · Recent Advances in Natural Language Processing · 2011
In this paper we look at the conjugation of the Romanian verb, in particular, at its irregularities, from a machine learning point of view. Our attempt is to predict the presence or absence of any alternation in the stem (apophony), using n-gram representations of the infinitive. We combine formal labelling mechanisms with learning methods in order to build a general conjugational model.