Multilingual Dependency Learning: Exploiting Rich Features for Tagging Syntactic and Semantic Dependencies

Abstract

This paper describes our system about multilingual syntactic and semantic dependency parsing for our participation in the joint task of CoNLL-2009 shared tasks. Our system uses rich features and incorporates various integration technologies. The system is evaluated on in-domain and out-of-domain evaluation data of closed challenge of joint task. For in-domain evaluation, our system ranks the second for the average macro labeled F1 of all seven languages, 82.52% (only about 0.1% worse than the best system), and the first for English with macro labeled F1 87.69%. And for out-of-domain evaluation, our system also achieves the second for average score of all three languages.