Skip to main content

Table 1 Performance of deep learning based dependency parsers on the MiPACQ corpus (%)

From: Parsing clinical text using the state-of-the-art deep learning based parsers: a systematic comparison

Parser Corpus Word embeddings UAS LS LAS
Stanford parser Penn TreeBank Gigaword 80.62 89.09 77.59
MiPACQ Gigaword 90.49 94.95 89.00
MiPACQ MIMICIII 90.30 94.84 88.75
Bist-parser Penn TreeBank Gigaword 81.08 89.35 78.20
MiPACQ Gigaword 90.72 95.18 89.25
MiPACQ MIMICIII 90.62 95.16 89.16
Dependency-tf Penn TreeBank Gigaword 79.14   
MiPACQ Gigaword 88.65   
MiPACQ MIMICIII 88.80   
jPTDP-parser Penn TreeBank Gigaword 79.47 85.76 74.62
MiPACQ Gigaword 88.50 92.36 85.53
MiPACQ MIMICIII 88.94 92.69 86.10
  1. Highest performance in terms of each evaluation criterion is highlighted in boldface
Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us