Table 5.
Parser | Fdep |
Charniak-Lease | 77.0 |
Bikel (0.9.8) | 77.0 |
Bikel (0.9.9c) | 77.0 |
Collins (model 3) | 71.0 |
Collins (model 2) | 70.5 |
Stanford (lexicalised) | 70.5 |
Collins (model 1) | 69.5 |
Charniak (Aug 05) | 68.5 |
Stanford (unlexicalised) | 68.5 |
Parser effectiveness based on comparison of dependency graphs to the graphs generated from the GENIA treebank, summed over the sentences for which each parser returned a successful parse.