Paper: Parsing Syntactic and Semantic Dependencies for Multiple Languages with A Pipeline Approach

ACL ID W09-1215
Title Parsing Syntactic and Semantic Dependencies for Multiple Languages with A Pipeline Approach
Venue International Conference on Computational Natural Language Learning
Session shared task
Year 2009
Authors

This paper describes a pipelined approach for CoNLL-09 shared task on joint learning of syntactic and semantic dependencies. In the system, we handle syntactic dependency pars- ing with a transition-based approach and util- ize MaltParser as the base model. For SRL, we utilize a Maximum Entropy model to iden- tify predicate senses and classify arguments. Experimental results show that the average performance of our system for all languages achieves 67.81% of macro F1 Score, 78.01% of syntactic accuracy, 56.69% of semantic la- beled F1, 71.66% of macro precision and 64.66% of micro recall.