50 lines
1.0 KiB
Plaintext
50 lines
1.0 KiB
Plaintext
|
|
||
|
serializeTo=truecasing.fast.caseless.qn.ser.gz
|
||
|
trainFileList=/home/horatio/truecase/train.4_5M.truecase.txt
|
||
|
# trainFileList=/home/john/truecase/train.orig.txt
|
||
|
testFile=/home/horatio/truecase/test.truecase.txt
|
||
|
# testFile=/scr/nlp/data/gale/AE-MT-eval-data/mt06/cased/ref0
|
||
|
|
||
|
map=word=0,answer=1
|
||
|
|
||
|
wordFunction = edu.stanford.nlp.process.LowercaseFunction
|
||
|
|
||
|
useClassFeature=true
|
||
|
useWord=true
|
||
|
useNGrams=true
|
||
|
noMidNGrams=true
|
||
|
maxNGramLeng=6
|
||
|
usePrev=true
|
||
|
useNext=true
|
||
|
useLongSequences=true
|
||
|
useSequences=true
|
||
|
usePrevSequences=true
|
||
|
useTypeSeqs=true
|
||
|
useTypeSeqs2=true
|
||
|
useTypeySequences=true
|
||
|
useOccurrencePatterns=true
|
||
|
useLastRealWord=true
|
||
|
useNextRealWord=true
|
||
|
useDisjunctive=true
|
||
|
disjunctionWidth=5
|
||
|
wordShape=chris2useLC
|
||
|
usePosition=true
|
||
|
useBeginSent=true
|
||
|
useTitle=true
|
||
|
|
||
|
useObservedSequencesOnly=true
|
||
|
saveFeatureIndexToDisk=true
|
||
|
normalize=true
|
||
|
|
||
|
useQN=false
|
||
|
QNSize=25
|
||
|
|
||
|
maxLeft=1
|
||
|
l1reg=1.0
|
||
|
|
||
|
readerAndWriter=edu.stanford.nlp.sequences.TrueCasingForNISTDocumentReaderAndWriter
|
||
|
featureFactory=edu.stanford.nlp.ie.NERFeatureFactory
|
||
|
|
||
|
featureDiffThresh=0.02
|
||
|
|