CofeehousePy/services/corenlp/scripts/pos-tagger/french.tagger.props

36 lines
1.2 KiB
XML

## tagger training invoked at Mon Jun 09 17:36:16 PDT 2014 with arguments:
model = french.tagger
arch = left3words,naacl2003unknowns,unicodeshapes(-1,1)
wordFunction =
trainFile = format=TREES,/u/nlp/data/lexparser/trees/FrenchCC/FTB-Train.utf8.txt
closedClassTags =
closedClassTagThreshold = 40
curWordMinFeatureThresh = 2
debug = false
debugPrefix =
tagSeparator = _
encoding = utf-8
iterations = 100
lang = french
learnClosedClassTags = false
minFeatureThresh = 2
openClassTags =
rareWordMinFeatureThresh = 10
rareWordThresh = 5
search = owlqn
sgml = false
sigmaSquared = 0.0
regL1 = 0.75
tagInside =
tokenize = true
tokenizerFactory =
tokenizerOptions = quotes=ascii
verbose = false
verboseResults = true
veryCommonWordThresh = 250
xmlInput = null
outputFile =
outputFormat = slashTags
outputFormatOptions =
nthreads = 1