Paper: Semantic Parsing for High-Precision Semantic Role Labelling

ACL ID W08-2101
Title Semantic Parsing for High-Precision Semantic Role Labelling
Venue International Conference on Computational Natural Language Learning
Session Main Conference
Year 2008
Authors

In this paper, we report experiments that explore learning of syntactic and seman- tic representations. First, we extend a state-of-the-art statistical parser to pro- duce a richly annotated tree that identi- fies and labels nodes with semantic role la- bels as well as syntactic labels. Secondly, we explore rule-based and learning tech- niques to extract predicate-argument struc- tures from this enriched output. The learn- ing method is competitive with previous single-system proposals for semantic role labelling, yields the best reported preci- sion, and produces a rich output. In com- bination with other high recall systems it yields an F-measure of 81%.