A corpus-based study of Verb Phrase Ellipsis

Although considerable work exists on the subject of ellipsis resolution, there has been very little empirical, corpus-based work on it. We propose a system which will take free text and (i) detect instances of Verb Phrase ellipsis, (ii) identify their antecedents and (iii) resolve them, providing an end-to-end solution. For each of the steps, manually developed methods and machine learning techniques will be compared. The goal of the system is to be robust, accurate and domain-independent.