36 lines
2.3 KiB
Plaintext
36 lines
2.3 KiB
Plaintext
|
## tagger training invoked at Sun Sep 23 19:24:37 PST 2018 with arguments:
|
||
|
model = english-left3words-distsim.tagger
|
||
|
arch = left3words,wordshapes(-1,1),distsim(/u/nlp/data/pos_tags_are_useless/egw4-reut.512.clusters,-1,1),distsimconjunction(/u/nlp/data/pos_tags_are_useless/egw4-reut.512.clusters,-1,1),rareExtractor(edu.stanford.nlp.tagger.maxent.ExtractorUCase),rareExtractor(edu.stanford.nlp.tagger.maxent.ExtractorCNumber),rareExtractor(edu.stanford.nlp.tagger.maxent.ExtractorDash),rareExtractor(edu.stanford.nlp.tagger.maxent.ExtractorLetterDigitDash),rareExtractor(edu.stanford.nlp.tagger.maxent.CompanyNameDetector),rareExtractor(edu.stanford.nlp.tagger.maxent.ExtractorAllCapitalized),rareExtractor(edu.stanford.nlp.tagger.maxent.ExtractorUpperDigitDash),rareExtractor(edu.stanford.nlp.tagger.maxent.ExtractorStartSentenceCap),rareExtractor(edu.stanford.nlp.tagger.maxent.ExtractorMidSentenceCapC),rareExtractor(edu.stanford.nlp.tagger.maxent.ExtractorMidSentenceCap),prefix(10),suffix(10),unicodeshapes(0),rareExtractor(edu.stanford.nlp.tagger.maxent.ExtractorNonAlphanumeric)
|
||
|
wordFunction = edu.stanford.nlp.process.AmericanizeFunction
|
||
|
trainFile = /u/nlp/data/pos-tagger/english/train-wsj-0-18;/u/nlp/data/pos-tagger/english/train-extra-english;/u/nlp/data/pos-tagger/english/train-tech-english;/u/nlp/data/pos-tagger/english/train-currency
|
||
|
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 = 0.0
|
||
|
regL1 = 0.75
|
||
|
tagInside =
|
||
|
tokenize = true
|
||
|
tokenizerFactory =
|
||
|
tokenizerOptions =
|
||
|
verbose = false
|
||
|
verboseResults = true
|
||
|
veryCommonWordThresh = 250
|
||
|
xmlInput =
|
||
|
outputFile =
|
||
|
outputFormat = slashTags
|
||
|
outputFormatOptions =
|
||
|
nthreads = 1
|