• Home
• com.novetta
• CLAVIN-nerd
• 3.0.0
• source code
• english.all.3class.distsim.prop

×

Project download

Many resources are needed to download a project. Please understand that we have to compensate our server costs. Thank you in advance.
Project price only 1 $

You can buy this project and download/modify it how often you want.

models.english.all.3class.distsim.prop Maven / Gradle / Ivy

trainFileList = /u/nlp/data/ner/column_data/all.3class.train.old2,/u/nlp/data/ner/column_data/english.extra.3class.train
testFile = /u/nlp/data/ner/column_data/all.3class.test
serializeTo = english.all.3class.distsim.crf.ser.gz

type = crf

wordFunction = edu.stanford.nlp.process.AmericanizeFunction

#distSimLexicon = /u/nlp/data/pos_tags_are_useless/englishGigaword.200.pruned
#distSimLexicon = /u/nlp/data/pos_tags_are_useless/egw.bnc.200
distSimLexicon = /u/nlp/data/pos_tags_are_useless/egw4-reut.512.clusters
useDistSim = true

map = word=0,answer=1

saveFeatureIndexToDisk = true

useClassFeature=true
useWord=true
#useWordPairs=true
useNGrams=true
noMidNGrams=true
maxNGramLeng=6
usePrev=true
useNext=true
#useTags=true
#useWordTag=true
useLongSequences=true
useSequences=true
usePrevSequences=true
useTypeSeqs=true
useTypeSeqs2=true
useTypeySequences=true
useOccurrencePatterns=true
useLastRealWord=true
useNextRealWord=true
#useReverse=false
normalize=true
# normalizeTimex=true
wordShape=chris2useLC
useDisjunctive=true
disjunctionWidth=5
#useDisjunctiveShapeInteraction=true

maxLeft=1
readerAndWriter=edu.stanford.nlp.sequences.ColumnDocumentReaderAndWriter

useObservedSequencesOnly=true

useQN = true
QNsize = 25

# makes it go faster
featureDiffThresh=0.05