36 lines
1.3 KiB
Plaintext
36 lines
1.3 KiB
Plaintext
|
## tagger training invoked at Thu Jul 03 15:37:49 PDT 2014 with arguments:
|
||
|
model = german-hgc.tagger
|
||
|
arch = left3words,naacl2003unknowns,unicodeshapes(-2,2),distsim(/u/nlp/data/german/ner/hgc_175m_600,-1,1),distsimconjunction(/u/nlp/data/german/ner/hgc_175m_600,-1,1),unicodeshapeconjunction(-1,1)
|
||
|
wordFunction =
|
||
|
trainFile = /u/nlp/data/GermanACL08/negra/negra-corpus.train.utf8
|
||
|
closedClassTags =
|
||
|
closedClassTagThreshold = 40
|
||
|
curWordMinFeatureThresh = 2
|
||
|
debug = false
|
||
|
debugPrefix =
|
||
|
tagSeparator = _
|
||
|
encoding = utf-8
|
||
|
iterations = 100
|
||
|
lang = german
|
||
|
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
|