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.

Keywords

TreebankComputer scienceDependency (UML)Natural language processingArtificial intelligenceWord (group theory)Feature (linguistics)Representation (politics)Dependency grammarPrior probabilitySpeech recognitionPart of speechWord error rateLinguistics

Affiliated Institutions

Related Publications

Publication Info

Year
2003
Type
article
Volume
1
Pages
173-180
Citations
2851
Access
Closed

External Links

View on DOI.org

Social Impact

Altmetric
PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

2851
OpenAlex

Cite This

Kristina Toutanova, Dan Klein, Christopher D. Manning et al. (2003). Feature-rich part-of-speech tagging with a cyclic dependency network. , 1 , 173-180. https://doi.org/10.3115/1073445.1073478

Identifiers

DOI
10.3115/1073445.1073478