CofeehousePy/services/corenlp/scripts/ner/english.all.3class.caseless...

60 lines
1.8 KiB
Plaintext

# trainFileList = /u/nlp/data/ner/column_data/all.3class.train.old2,/u/nlp/data/ner/column_data/english.extra.3class.train
trainFileList = /u/nlp/data/ner/column_data/ace23.3class.train,/u/nlp/data/ner/column_data/muc6.3class.ptb.train,/u/nlp/data/ner/column_data/muc7.3class.ptb.train,/u/nlp/data/ner/column_data/conll.3class.train,/u/nlp/data/ner/column_data/wikiner.3class.train,/u/nlp/data/ner/column_data/ontonotes.3class.train,/u/nlp/data/ner/column_data/english.extra.3class.train
testFile = /u/nlp/data/ner/column_data/all.3class.test
serializeTo = english.all.3class.caseless.distsim.crf.ser.gz
type = crf
wordFunction = edu.stanford.nlp.process.LowercaseAndAmericanizeFunction
useKnownLCWords = false
#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
# right options for egw4-reut.512 (though effect of having or not is small)
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