Paper: Applying Sentence Simplification to the CoNLL-2008 Shared Task

ACL ID W08-2140
Title Applying Sentence Simplification to the CoNLL-2008 Shared Task
Venue International Conference on Computational Natural Language Learning
Session Main Conference
Year 2008
Authors

Our submission to the CoNLL-2008 shared task (Surdeanu et al., 2008) focused on applying a novel method for semantic rolelabelingtothesharedtask. Oursystem first simplifies each sentence to be labeled using a set of hand-constructed rules; the weights of the system are trained on se- mantic role labeling data to generate sim- plifications which are as useful as possible for semantic role labeling. Our system is only a semantic role labeling system, and thus did not receive a score for Syntactic Dependencies (or, byextension, a score for the complete problem). Unlike most sys- tems in the shared task, our system took constituency parses as input. On the sub- task of semantic dependencies, our system obtained an F1 score of 76.17, the high- est in the open task. In this paper we give