Paper: A Cascaded Syntactic and Semantic Dependency Parsing System

ACL ID W08-2134
Title A Cascaded Syntactic and Semantic Dependency Parsing System
Venue International Conference on Computational Natural Language Learning
Session Main Conference
Year 2008
Authors

We describe our CoNLL 2008 Shared Task system in this paper. The system includes two cascaded components: a syntactic and a semantic dependency parsers. A first- order projective MSTParser is used as our syntactic dependency parser. In order to overcome the shortcoming of the MST- Parser, that it cannot model more global in- formation, we add a relabeling stage after the parsing to distinguish some confusable labels, such as ADV, TMP, and LOC. Be- sides adding a predicate identification and a classification stages, our semantic de- pendency parsing simplifies the traditional four stages semantic role labeling into two: a maximum entropy based argument clas- sification and an ILP-based post inference. Finally, we gain the overall labeled macro F1 = 82.66, which ranked the second posi- tion ...