Robust VPE detection using automatically parsed text

Abstract

This paper describes a Verb Phrase Ellipsis (VPE) detection system, built for robustness, accuracy and domain independence. The system is corpus-based, and uses machine learning techniques on free text that has been automatically parsed. Tested on a mixed corpus comprising a range of genres, the system achieves a 70% F1-score. This system is designed as the first stage of a complete VPE resolution system that is input free text, detects VPEs, and proceeds to find the antecedents and resolve them.