Year: 2014
Type: article
Abstract: 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.
Source: Computational Linguistics
DOI: 10.1162/coli_a_00185
Authors: Joakim Nivre, Daniel Fernández-González
Institutions: Uppsala University, Universidade de Vigo
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W2121293489