Tailored Feature Extraction for Lexical Disambiguation of English Verbs Based on Corpus Pattern Analysis
Abstract
We give a report on a detailed study of automatic lexical disambiguation of 30 sample English verbs. We have trained and evaluate several statistical classifiers that use both morphosyntactic and semantic features to assign semantic patterns according to a pattern lexicon.
Our system of semantic classification draws on the Corpus Pattern Analysis (CPA) - a novel lexicographic method that seeks to cluster verb uses according to the morpho-syntactic, lexical and semantic/pragmatic similarity of their contexts rather than their grouping according to abstract semantic definitions. In this paper we mainly concentrate on the procedures for feature extraction and feature selection.
We show that features tailored to particular verbs using contextual clues given by the CPA method and explicitly described in the pattern lexicon have potential to significantly improve accuracy of supervised statistical classifiers.