POS Tagging (State of the art)

From ACL Wiki
Revision as of 20:22, 20 June 2007 by Pdturney (Talk | contribs)

Jump to: navigation, search

"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 Giménez and Márquez (2004) SVMTool 97.16%
Stanford Tagger Learning with Cyclic Dependency Network Toutanova et al. (?) Stanford Tagger 97.24%
Bidirectional Perceptron Learning Shen et al. (?) POS tagger 97.33%


Jesús Giménez and Lluís Márquez. (2004). SVMTool: A general POS tagger generator based on Support Vector Machines.

Libin Shen, Giorgio Satta and Aravind K. Joshi. (?). Guided Learning for Bidirectional Sequence Classification.

Kristina Toutanova, Dan Klein, Christopher D. Manning, and Yoram Singer. (?) Feature-Rich Part-of-Speech Tagging with a Cyclic Dependency Network.