35 lines
1.3 KiB
Plaintext
35 lines
1.3 KiB
Plaintext
|
## tagger training invoked at Thu Aug 07 18:39:38 PDT 2014 with arguments:
|
||
|
model = spanish-distsim.tagger
|
||
|
arch = left3words,naacl2003unknowns,allwordshapes(-1,1),distsim(/u/nlp/data/spanish/distsim/spanish.spence512.cls,-1,1),distsimconjunction(/u/nlp/data/spanish/distsim/spanish.spence512.cls,-1,1)
|
||
|
trainFile = format=TREES,/u/nlp/data/spanish/ancora/ancora.train
|
||
|
closedClassTags =
|
||
|
closedClassTagThreshold = 40
|
||
|
curWordMinFeatureThresh = 2
|
||
|
debug = true
|
||
|
debugPrefix =
|
||
|
tagSeparator = _
|
||
|
encoding = utf-8
|
||
|
iterations = 100
|
||
|
lang = spanish
|
||
|
learnClosedClassTags = false
|
||
|
minFeatureThresh = 2
|
||
|
openClassTags =
|
||
|
rareWordMinFeatureThresh = 10
|
||
|
rareWordThresh = 5
|
||
|
search = qn
|
||
|
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 = 16
|