Paper: Semantic Role Chunking Combining Complementary Syntactic Views

ACL ID W05-0634
Title Semantic Role Chunking Combining Complementary Syntactic Views
Venue International Conference on Computational Natural Language Learning
Session Main Conference
Year 2005

This paper describes a semantic role la- beling system that uses features derived from different syntactic views, and com- bines them within a phrase-based chunk- ing paradigm. For an input sentence, syn- tactic constituent structure parses are gen- erated by a Charniak parser and a Collins parser. Semantic role labels are assigned to the constituents of each parse using Support Vector Machine classifiers. The resulting semantic role labels are con- verted to an IOB representation. These IOB representations are used as additional features, along with flat syntactic chunks, by a chunking SVM classifier that pro- duces the final SRL output. This strategy for combining features from three differ- ent syntactic views gives a significant im- provement in performance over roles pro- duced by usi...