Arc-Eager Parsing with the Tree Constraint
2014 (English)In: Computational linguistics - Association for Computational Linguistics (Print), ISSN 0891-2017, E-ISSN 1530-9312, Vol. 40, no 2, 259-267 p.Article in journal (Refereed) Published
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.
Place, publisher, year, edition, pages
2014. Vol. 40, no 2, 259-267 p.
General Language Studies and Linguistics Computer and Information Science
IdentifiersURN: urn:nbn:se:uu:diva-229457DOI: 10.1162/COLI_a_00185ISI: 000338196000002OAI: oai:DiVA.org:uu-229457DiVA: diva2:736618