Feature-Rich Part-of-Speech Tagging with a Cyclic Dependency Network

DMCA

Feature-Rich Part-of-Speech Tagging with a Cyclic Dependency Network (2003)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Kristina Toutanova , Dan Klein , Christopher D. Manning , Yoram Singer

Venue:	IN PROCEEDINGS OF HLT-NAACL
Citations:	657 - 23 self

BibTeX

@INPROCEEDINGS{Toutanova03feature-richpart-of-speech,
    author = {Kristina Toutanova and Dan Klein and Christopher D. Manning and Yoram Singer},
    title = {Feature-Rich Part-of-Speech Tagging with a Cyclic Dependency Network},
    booktitle = {IN PROCEEDINGS OF HLT-NAACL },
    year = {2003},
    pages = {252--259},
    publisher = {}
}

OpenURL

Abstract

We present a new part-of-speech tagger that demonstrates the following ideas: (i) explicit use of both preceding and following tag contexts via a dependency network representation, (ii) broad use of lexical features, including jointly conditioning on multiple consecutive words, (iii) effective use of priors in conditional loglinear models, and (iv) fine-grained modeling of unknown word features. Using these ideas together, the resulting tagger gives a 97.24% accuracy on the Penn Treebank WSJ, an error reduction of 4.4% on the best previous single automatically learned tagging result.

Keyphrases

cyclic dependency network feature-rich part-of-speech tagging conditional loglinear model broad use dependency network representation effective use explicit use tag context lexical feature unknown word feature penn treebank wsj fine-grained modeling following idea error reduction new part-of-speech tagger multiple consecutive word

DMCA