The Effect of Higher-Order Dependency Features in Discriminative Phrase-Structure Parsing

Greg Coppola, Mark Steedman

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Higher-order dependency features are known to improve dependency parser
accuracy. We investigate the incorporation of such features into a cube decoding phrase-structure parser. We find considerable gains in accuracy on the range of standard metrics. What is especially interesting is that we find strong, statistically significant gains on dependency recovery on out-of-domain tests (Brown vs. WSJ). This suggests that higher-order dependency features are not simply over-fitting the training material.
Original languageEnglish
Title of host publicationProceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Place of PublicationSofia, Bulgaria
PublisherAssociation for Computational Linguistics
Pages610-616
Number of pages7
Publication statusPublished - 1 Aug 2013

Fingerprint Dive into the research topics of 'The Effect of Higher-Order Dependency Features in Discriminative Phrase-Structure Parsing'. Together they form a unique fingerprint.

Cite this