Paper: Linguistic features in data-driven dependency parsing

ACL ID W08-2104
Title Linguistic features in data-driven dependency parsing
Venue International Conference on Computational Natural Language Learning
Session Main Conference
Year 2008
Authors

This article investigates the effect of a set of linguistically motivated features on ar- gument disambiguation in data-driven de- pendency parsing of Swedish. We present results from experiments with gold stan- dard features, such as animacy, definite- ness and finiteness, as well as correspond- ing experiments where these features have been acquired automatically and show significant improvements both in overall parse results and in the analysis of specific argument relations, such as subjects, ob- jects and predicatives.