Parsing with soft and hard constraints on dependency length

Abstract

In lexicalized phrase-structure or dependency parses, a word's modifiers tend to fall near it in the string. We show that a crude way to use dependency length as a parsing feature can substantially improve parsing speed and accuracy in English and Chinese, with more mixed results on German. We then show similar improvements by imposing hard bounds on dependency length and (additionally) modeling the resulting sequence of parse fragments. This simple “vine grammar” formalism has only finite-state power, but a context-free parameterization with some extra parameters for stringing fragments together. We exhibit a linear-time chart parsing algorithm with a low grammar constant.