thesis-anne/Stanford_NER/stanford-ner-2018-02-27/classifiers/english.muc.7class.distsim....

55 lines
1.1 KiB
Plaintext

trainFileList = /u/nlp/data/ner/column_data/muc6.ptb.train,/u/nlp/data/ner/column_data/muc7.ptb.train
# testFile = /u/nlp/data/ner/column_data/muc7.ptb.devtest
serializeTo = english.muc.7class.distsim.crf.ser.gz
type=crf
wordFunction = edu.stanford.nlp.process.AmericanizeFunction
distSimLexicon = /u/nlp/data/pos_tags_are_useless/egw4-reut.512.clusters
numberEquivalenceDistSim = true
unknownWordDistSimClass = 0
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