A Latent Variable Model for Generative Dependency Parsing

Ivan Titov, James Henderson

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract / Description of output

Dependency parsing has been a topic of active research in natural language processing during the last several years. The CoNLL-2006 shared task (Buchholz and Marsi, 2006) made a wide selection of standardized treebanks for different languages available for the research community and allowed for easy comparison between various statistical methods on a standardized benchmark. One of the surprising things discovered by this evaluation is that the best results are achieved by methods which are quite different from state-of-the-art models for constituent parsing, e.g. the deterministic parsing method of Nivre et al. (2006) and the minimum spanning tree parser of McDonald et al.
Original languageEnglish
Title of host publicationTrends in Parsing Technology
Subtitle of host publicationDependency Parsing, Domain Adaptation, and Deep Parsing
PublisherSpringer
Pages35-55
Number of pages21
ISBN (Electronic)978-90-481-9352-3
ISBN (Print)978-90-481-9351-6
DOIs
Publication statusPublished - 29 Sept 2010

Publication series

NameText, Speech and Language Technology
PublisherSpringer Netherlands
Volume43
ISSN (Print)1386-291X

Fingerprint

Dive into the research topics of 'A Latent Variable Model for Generative Dependency Parsing'. Together they form a unique fingerprint.

Cite this