Skip to main content

Table 1 F const score, all sentences

From: Benchmarking natural-language parsers for biological applications using dependency graphs

Parser

F const

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

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