POS Tagging (State of the art)
Revision as of 14:51, 18 June 2007 by Pdturney (talk | contribs) (POS Tagging (StateOfTheArt) moved to POS Tagging (State of the art): Wikipedia capitalization)
"Standard" measure:
- Per token accuracy
"Standard" datasets:
- Training: sections 0-18 of WSJ
- Testing: sections 22-24 of WSJ
| System Name | Short Description | Main Publications | Software (if available) | Results | Comments (i.e. extra resources used, train/test times, ...) |
|---|---|---|---|---|---|
| SVMTool | SVM Based tagger and tagger generator | Jesús Giménez and Lluís Márquez. SVMTool: A general POS tagger generator based on Support Vector Machines[1] | http://www.lsi.upc.es/~nlp/SVMTool/ | 97.16% | |
| Stanford Tagger | Learning with Cyclic Dependency Network | Kristina Toutanova, Dan Klein, Christopher D. Manning, and Yoram Singer. Feature-Rich Part-of-Speech Tagging with a Cyclic Dependency Network [2] | http://nlp.stanford.edu/software/tagger.shtml] | 97.24% |