Combining NLP and statistical techniques for lexical acquisition

Abstract

The growing availability of large on-line corpora encourages the study of word behaviour directly from accessible raw texts. However the methods by which lexical knowledge should be extracted from plain texts are still matter of debate and experimentation. In this paper it is presented an integrated tool for lexical acquisition from corpora, ARIOSTO, based on a hybrid methodology that combines typical NLP techniques, such as (shallow) syntax and semantic markers, with numerical processing.