Difference between revisions of "POS Tagging (State of the art)"

From ACL Wiki
Jump to: navigation, search
(References: bullit points for all refs)
(Table of results: typo)
Line 37: Line 37:
 
| Tsuruoka, et al (2005)
 
| Tsuruoka, et al (2005)
 
| [http://www-tsujii.is.s.u-tokyo.ac.jp/GENIA/tagger/ GENiA
 
| [http://www-tsujii.is.s.u-tokyo.ac.jp/GENIA/tagger/ GENiA
| 96.94% on WSJ, 98.26 on biomed.
+
| 96.94% on WSJ, 98.26% on biomed.
 
|-
 
|-
 
|}
 
|}

Revision as of 22:40, 18 November 2009

  • Performance measure: per token accuracy
  • 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%
POS tagger bidirectional perceptron learning Shen et al. (2007) POS tagger 97.33%
GENiA Tagger  ? Tsuruoka, et al (2005) [http://www-tsujii.is.s.u-tokyo.ac.jp/GENIA/tagger/ GENiA 96.94% on WSJ, 98.26% on biomed.

References

See also