Announcements‎ > ‎

English Best Model

posted Feb 14, 2012, 3:57 AM by Giuseppe Attardi   [ updated Feb 14, 2012, 6:36 AM ]
Using feature models involving the new composite features, I was able to improve the parser accuracy on the English Penn TreeBank.
I have then used parser combination, according to the technique presented in our NAACL 2009 paper: G. Attardi, F. Dell'Orletta. Reverse Revision and Linear Tree Combination for Dependency Parsing. Proc. of NAACL HLT 2009, 2009.

The combination of three parsers, a standard MLP model and two reverse revision MLP models, achieves the following scores:

  Labeled   attachment score: 51497 / 57676 * 100 = 89.29 %
  Unlabeled attachment score: 52827 / 57676 * 100 = 91.59 %
  Label accuracy score:       53910 / 57676 * 100 = 93.47 %

which are at the very best of those reported at the ConLL 2008 Shared Task.
This is an excellent result considering that the DeSR parser combination is still a fast linear process, while the best at CoNLL 2008 was a 2rd order MST parser which adopted the expensive search procedure by Carreras (2007).
Comments