chinese.misc.nodistsim.prop

trainFileList = /u/nlp/data/chinese/ner/chinese.ner.misc.train,/u/nlp/data/chinese/ner/chinese.ner.misc.extra.train
testFile = /u/nlp/data/chinese/ner/chinese.ner.misc.test
serializeTo = chinese.misc.nodistsim.crf.ser.gz

map = word=0,answer=1

useKnownLCWords = false

useDistSim = false
#distSimLexicon = /u/nlp/data/german/ner/dewac_175m_600
mergeTags = true
useTitle = false
useClassFeature=true
useWord=true
useNGrams=true
useNeighborNGrams=true
noMidNGrams=true
conjoinShapeNGrams=true
useBeginSent=true
maxNGramLeng=4
#maxNGramLeng=6
usePrev=true
useNext=true
useLongSequences=true
useSequences=true
usePrevSequences=true
useTypeSeqs=true
useTypeSeqs2=true
useTypeySequences=true
useOccurrencePatterns=true
useLastRealWord=true
useNextRealWord=true
normalize=true
wordShape=chris4
useDisjunctive=true
disjunctionWidth=5
useDisjShape=true
useRadical = true

type=crf
useQN = true

# For making faster

QNsize = 10
saveFeatureIndexToDisk = true
maxLeft=1
useObservedSequencesOnly=true
featureDiffThresh=0.05

readerAndWriter=edu.stanford.nlp.sequences.ColumnDocumentReaderAndWriter