POS Tagging (State of the art)

From ACLWiki
(Difference between revisions)
Jump to: navigation, search
(Table of results: LTAG-spinal again)
Line 1: Line 1:
* '''Performance measure:''' per token accuracy
+
* '''Performance measure:''' per token accuracy. (The convention is for this to be measured on all tokens, including punctuation tokens and other unambiguous tokens.)
 
* '''Training data:''' sections 0-18 of Wall Street Journal corpus
 
* '''Training data:''' sections 0-18 of Wall Street Journal corpus
 
* '''Testing data:''' sections 22-24 of Wall Street Journal corpus
 
* '''Testing data:''' sections 22-24 of Wall Street Journal corpus

Revision as of 23:09, 1 January 2010

  • Performance measure: per token accuracy. (The convention is for this to be measured on all tokens, including punctuation tokens and other unambiguous tokens.)
  • Training data: sections 0-18 of Wall Street Journal corpus
  • Testing data: sections 22-24 of Wall Street Journal corpus


Table of results

System name Short description Main publications Software Results
SVMTool SVM-based tagger and tagger generator Giménez and Márquez (2004) SVMTool 97.16%
Stanford Tagger learning with cyclic dependency network Toutanova et al. (2003) Stanford Tagger 97.24%
LTAG-spinal bidirectional perceptron learning Shen et al. (2007) LTAG-spinal 97.33%
GENiA Tagger  ? Tsuruoka, et al (2005) GENiA 96.94% on WSJ, 98.26% on biomed.

References

See also

Personal tools