DFKI-LT - Cross-Domain Dependency Parsing Using a Deep Linguistic Grammar
Cross-Domain Dependency Parsing Using a Deep Linguistic Grammar
2 Proceedings of ACL-IJCNLP 2009,
Pure statistical parsing systems achieves high in-domain accuracy but performs poorly out-domain. In this paper, we propose two different approaches to produce syntactic dependency structures using a large-scale hand-crafted HPSG grammar. The dependency backbone of an HPSG analysis is used to provide general linguistic insights which, when combined with state-of-the-art statistical dependency parsing models, achieves performance improvements on out-domain tests.
Files: BibTeX, P09-1043.pdf, P09-1043.pdf