Joint memory-based learning of syntactic and semantic dependencies in multiple languages
In this paper we present a system submitted to the CoNLL Shared Task 2009 performing the identification and labeling of syntactic and semantic dependencies in multiple languages. Dependencies are truly jointly learned, i.e. as if they were a single task. The system works in two phases: a classification phase in which three classifiers predict different types of information, and a ranking phase in which the output of the classifiers is combined.