Incremental predictive parsing with TurboParser

Abstract

Most approaches to incremental parsing either incur a degradation of accuracy or they have to postpone decisions, yielding underspecified intermediate output. We present an incremental predictive dependency parser that is fast, accurate, and largely language independent. By extending a state-of-the-art dependency parser, connected analyses for sentence prefixes are obtained, which even predict properties and the structural embedding of upcoming words. In contrast to other approaches, accuracy for complete sentence analyses does not decrease. © 2014 Association for Computational Linguistics.