文章基本信息

标题：Arc-Eager Parsing with the Tree Constraint
本地全文：下载
作者：Joakim Nivre ; Daniel Fernández-González
期刊名称：Computational Linguistics
印刷版ISSN：0891-2017
电子版ISSN：1530-9312
出版年度：2014
卷号：40
期号：2
页码：259-267
DOI：10.1162/COLI_a_00185
语种：English
出版社：MIT Press
摘要：The arc-eager system for transition-based dependency parsing is widely used in natural language processing despite the fact that it does not guarantee that the output is a well-formed dependency tree. We propose a simple modification to the original system that enforces the tree constraint without requiring any modification to the parser training procedure. Experiments on multiple languages show that the method on average achieves 72% of the error reduction possible and consistently outperforms the standard heuristic in current use.