POS Induction (State of the art): Difference between revisions

From ACL Wiki
Jump to navigation Jump to search
No edit summary
Auser (talk | contribs)
Berg-Kirkpatrick et al. (2010)
Line 12: Line 12:
|  
|  
| 76.1%
| 76.1%
|-
|
| Logistic regression with features and LBFGS
| Berg-Kirkpatrick et al. (2010)
|
| 75.5%
|-
|-
|}
|}
Line 18: Line 24:
== References ==
== References ==


* [http://www.aclweb.org/anthology/D/D10/D10-1056.pdf Christos Christodoulopoulos, Sharon Goldwater and Mark Steedman. 2010. Two Decades of Unsupervised POS induction: How far have we come? In Proceedings of EMNLP 2010]
* [http://www.aclweb.org/anthology/D/D10/D10-1056.pdf Christos Christodoulopoulos, Sharon Goldwater and Mark Steedman. 2010. Two Decades of Unsupervised POS induction: How far have we come? In Proceedings of EMNLP 2010.]
 
* [http://www.aclweb.org/anthology/N/N10/N10-1083.pdf Taylor Berg-Kirkpatrick, Alexandre Bouchard-Cote, John DeNero, and Dan Klein. 2010. Painless Unsupervised Learning with Features. NAACL 2010.]


== See also ==
== See also ==

Revision as of 21:03, 27 January 2011

System name Short description Main publications Software Many-to-1
Prototype-based+Brown MRF initialized with Brown prototypes Christodoulopoulos, Goldwater and Steedman (2010) 76.1%
Logistic regression with features and LBFGS Berg-Kirkpatrick et al. (2010) 75.5%


References

See also