Paper: Semantics-Driven Shallow Parsing for Chinese Semantic Role Labeling

ACL ID P10-2019
Title Semantics-Driven Shallow Parsing for Chinese Semantic Role Labeling
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2010
Authors

One deficiency of current shallow pars- ing based Semantic Role Labeling (SRL) methods is that syntactic chunks are too small to effectively group words. To par- tially resolve this problem, we propose semantics-driven shallow parsing, which takes into account both syntactic struc- tures and predicate-argument structures. We also introduce several new “path” fea- tures to improve shallow parsing based SRL method. Experiments indicate that our new method obtains a significant im- provement over the best reported Chinese SRL result.