Paper: Multilingual Syntactic-Semantic Dependency Parsing with Three-Stage Approximate Max-Margin Linear Models

ACL ID W09-1218
Title Multilingual Syntactic-Semantic Dependency Parsing with Three-Stage Approximate Max-Margin Linear Models
Venue International Conference on Computational Natural Language Learning
Session shared task
Year 2009
Authors

This paper describes a system for syntactic- semantic dependency parsing for multiple lan- guages. The system consists of three parts: a state-of-the-art higher-order projective depen- dency parser for syntactic dependency pars- ing, a predicate classifier, and an argument classifier for semantic dependency parsing. For semantic dependency parsing, we ex- plore use of global features. All components are trained with an approximate max-margin learning algorithm. In the closed challenge of the CoNLL-2009 Shared Task (Hajiˇc et al., 2009), our system achieved the 3rd best performances for En- glish and Czech, and the 4th best performance for Japanese.