Difference between revisions of "POS Tagging (State of the art)"
Jump to navigation
Jump to search
m (Wikipedia capitalization) |
(Add (Shen, Satta and Joshi, 2007)) |
||
| Line 12: | Line 12: | ||
| 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 [http://nlp.stanford.edu/kristina/papers/tagging.pdf] || [http://nlp.stanford.edu/software/tagger.shtml tagger] || 97.24% || | | 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 [http://nlp.stanford.edu/kristina/papers/tagging.pdf] || [http://nlp.stanford.edu/software/tagger.shtml tagger] || 97.24% || | ||
| + | |- | ||
| + | |||
| + | | || Bidirectional Perceptron Learning || Libin Shen, Giorgio Satta and Aravind K. Joshi. Guided Learning for Bidirectional Sequence Classification [http://acl.ldc.upenn.edu/P/P07/P07-1096.pdf] || [http://www.cis.upenn.edu/~xtag/spinal/ POS tagger] || 97.33% || | ||
|- | |- | ||
Revision as of 08:21, 20 June 2007
"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] | 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] | tagger | 97.24% | |
| Bidirectional Perceptron Learning | Libin Shen, Giorgio Satta and Aravind K. Joshi. Guided Learning for Bidirectional Sequence Classification [3] | POS tagger | 97.33% |