2021-01-14 08:07:24 +01:00
|
|
|
## tagger training invoked at Fri Feb 14 01:24:56 PST 2014 with arguments:
|
|
|
|
model = wsj-0-18-bidirectional-nodistsim.tagger
|
|
|
|
arch = bidirectional5words,naacl2003unknowns,wordshapes(-1,1)
|
|
|
|
wordFunction =
|
|
|
|
trainFile = /u/nlp/data/pos-tagger/english/train-wsj-0-18
|
|
|
|
closedClassTags =
|
|
|
|
closedClassTagThreshold = 40
|
|
|
|
curWordMinFeatureThresh = 2
|
|
|
|
debug = false
|
|
|
|
debugPrefix =
|
|
|
|
tagSeparator = _
|
|
|
|
encoding = UTF-8
|
|
|
|
iterations = 100
|
|
|
|
lang = english
|
|
|
|
learnClosedClassTags = false
|
|
|
|
minFeatureThresh = 2
|
|
|
|
openClassTags =
|
|
|
|
rareWordMinFeatureThresh = 5
|
|
|
|
rareWordThresh = 5
|
|
|
|
search = owlqn
|
|
|
|
sgml = false
|
|
|
|
sigmaSquared = 0.5
|
|
|
|
regL1 = 0.75
|
|
|
|
tagInside =
|
|
|
|
tokenize = true
|
|
|
|
tokenizerFactory =
|
|
|
|
tokenizerOptions =
|
|
|
|
verbose = false
|
|
|
|
verboseResults = true
|
|
|
|
veryCommonWordThresh = 250
|
|
|
|
xmlInput =
|
|
|
|
outputFile =
|
|
|
|
outputFormat = slashTags
|
|
|
|
outputFormatOptions =
|
|
|
|
nthreads = 1
|