Dealing with the Grey Sheep of the Romanian Gender System, the Neuter

Romanian has been traditionally seen as bearing three lexical genders: masculine, feminine, and neuter, although it has always been known to have only two agreement patterns (for masculine and feminine). Previous machine learning classifiers which have attempted to discriminate Romanian nouns according to gender have taken as input only the singular form, either presupposing the traditional tripartite analysis, or using additional information from case inflected forms. We present here a tool based on two parallel support vector machines using n-gram features from the singular and from the plural, which distinguish the neuter.