Table 1

Fconst score, all sentences

Parser

Fconst


Charniak-Lease

80.2

Bikel (0.9.8)

79.4

Bikel (0.9.9c)

79.4

Charniak (Aug 05)

78.1

Collins (model 2)

77.8

Collins (model 3)

77.2

Collins (model 1)

76.4

Stanford (unlexicalised)

72.3

Stanford (lexicalised)

71.1


Parser effectiveness based on comparison of constituent trees to the GENIA treebank, summed over entire corpus.

Clegg and Shepherd BMC Bioinformatics 2007 8:24   doi:10.1186/1471-2105-8-24

Open Data