Feature-Rich Part-of-Speech Tagging with a Cyclic Dependency Network (2003)
Cached
Download Links
| Venue: | IN PROCEEDINGS OF HLT-NAACL |
| Citations: | 181 - 12 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 = {}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
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.
