Transition-Based Left-Corner Parsing for Identifying PTB-Style Nonlocal Dependencies

Abstract

This paper proposes a left-corner parser which can identify nonlocal dependencies. Our parser integrates nonlocal dependency identification into a transition-based system. We use a structured perceptron which enables our parser to utilize global features captured by nonlocal dependencies. An experimental result demonstrates that our parser achieves a good balance between constituent parsing and nonlocal dependency identification.