CoreNLP/scripts/truecase/truecasing.full.prop at master · JavaMuller/CoreNLP · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39

serializeTo=truecasing.full.qn.ser.gz
trainFileList=/scr/nlp/data/gale/NIST09/truecaser/crf/noUN.input
testFile=/scr/nlp/data/gale/AE-MT-eval-data/mt06/cased/ref0

maxLeft=1
map=word=0,answer=1

usePosition=true
usePrevSequences=true
useObservedSequencesOnly=true
useTitle=true
useLastRealWord=true
l1reg=1.0
useClassFeature=true
useTypeSeqs2=true
useSequences=true
useNextRealWord=true
disjunctionWidth=5
wordShape=chris2useLC
saveFeatureIndexToDisk=true
useTypeySequences=true
useDisjunctive=true
noMidNGrams=true
maxNGramLeng=6
useNGrams=true
normalize=true
usePrev=true
useNext=true
useLongSequences=true
useOccurrencePatterns=true
useWord=true
useTypeSeqs=true

useQN=false
QNSize=25

readerAndWriter=edu.stanford.nlp.sequences.TrueCasingForNISTDocumentReaderAndWriter
featureFactory=edu.stanford.nlp.ie.NERFeatureFactory