Quarterly (March, June, September, December)
160 pp. per issue
6 3/4 x 10
2014 Impact factor:

Computational Linguistics

Hwee Tou Ng, Editor
June 2014, Vol. 40, No. 2, Pages 259-267
(doi: 10.1162/COLI_a_00185)
@ 2014 Association for Computational Linguistics
Arc-Eager Parsing with the Tree Constraint
Article PDF (89.86 KB)

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.