Paper: A Comparison of Chinese Parsers for Stanford Dependencies

ACL ID P12-2003
Title A Comparison of Chinese Parsers for Stanford Dependencies
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2012

Stanford dependencies are widely used in nat- ural language processing as a semantically- oriented representation, commonly generated either by (i) converting the output of a con- stituent parser, or (ii) predicting dependencies directly. Previous comparisons of the two ap- proaches for English suggest that starting from constituents yields higher accuracies. In this paper, we re-evaluate both methods for Chi- nese, using more accurate dependency parsers than in previous work. Our comparison of per- formance and efficiency across seven popular open source parsers (four constituent and three dependency) shows, by contrast, that recent higher-order graph-based techniques can be more accurate, though somewhat slower, than constituent parsers. We demonstrate also that n-way jackknifing is a us...