Serialized Form
Package edu.stanford.nlp.classify |
serialVersionUID: 1L
labelIndex
Index<E> labelIndex
featureIndex
Index<E> featureIndex
Class edu.stanford.nlp.classify.AveragedPerceptronClassifierFactory extends Object implements Serializable |
serialVersionUID: 1L
epochs
int epochs
Class edu.stanford.nlp.classify.BaggingRegressor extends Object implements Serializable |
serialVersionUID: 8367022834638633057L
bagOfRegressors
List<E> bagOfRegressors
Class edu.stanford.nlp.classify.ClassifiedDatum extends BasicDatum<L,F> implements Serializable |
serialVersionUID: -9065823265750491154L
predictedLabel
Object predictedLabel
serialVersionUID: -3883164942879961091L
serialVersionUID: 19157757130054829L
labelIndex
Index<E> labelIndex
featureIndex
Index<E> featureIndex
labels
int[] labels
data
int[][] data
size
int size
Class edu.stanford.nlp.classify.GradientDiscountedLogLinearClassifier extends Object implements Serializable |
serialVersionUID: 1546827958928525578L
inner
LinearClassifier<L,F> inner
alpha
double alpha
classification
boolean classification
Class edu.stanford.nlp.classify.HandWeightedRVFClassifier extends Object implements Serializable |
serialVersionUID: -8634473005977866255L
weights
Counter<E> weights
threshold
double threshold
Class edu.stanford.nlp.classify.HierarchicalBayesianLogisticClassifier extends Object implements Serializable |
serialVersionUID: 6672245467246897192L
weights
double[] weights
featureIndex
Index<E> featureIndex
classes
Object[] classes
Class edu.stanford.nlp.classify.KNNClassifier extends Object implements Serializable |
serialVersionUID: 7115357548209007944L
weightedVotes
boolean weightedVotes
instances
CollectionValuedMap<K,V> instances
classLookup
Map<K,V> classLookup
l2Normalize
boolean l2Normalize
k
int k
Class edu.stanford.nlp.classify.KNNRegressor extends Object implements Serializable |
serialVersionUID: 8367022834638633057L
dataset
GeneralDataset<L,F> dataset
docsList
List<E> docsList
numNeighbors
int numNeighbors
simType
edu.stanford.nlp.classify.KNNRegressionFactory.SimilarityType simType
Class edu.stanford.nlp.classify.LibSVMClassifier extends Object implements Serializable |
serialVersionUID: 1L
labelIndex
Index<E> labelIndex
featureIndex
Index<E> featureIndex
model
libsvm.svm_model model
serialVersionUID: 8499574525453275255L
weights
double[][] weights
- Classifier weights. First index is the featureIndex value and second
index is the labelIndex value.
labelIndex
Index<E> labelIndex
featureIndex
Index<E> featureIndex
intern
boolean intern
thresholds
double[] thresholds
serialVersionUID: 7893768984379107397L
TOL
double TOL
mem
int mem
verbose
boolean verbose
logPrior
LogPrior logPrior
minimizer
Minimizer<T extends Function> minimizer
tuneSigmaHeldOut
boolean tuneSigmaHeldOut
tuneSigmaCV
boolean tuneSigmaCV
folds
int folds
min
double min
max
double max
retrainFromScratchAfterSigmaTuning
boolean retrainFromScratchAfterSigmaTuning
heldOutSearcher
LineSearcher heldOutSearcher
Class edu.stanford.nlp.classify.LinearRegressor extends Object implements Serializable |
serialVersionUID: 8367022834638633057L
weights
double[] weights
featureIndex
Index<E> featureIndex
Class edu.stanford.nlp.classify.LogisticClassifier extends Object implements Serializable |
serialVersionUID: 6672245467246897192L
weights
double[] weights
featureIndex
Index<E> featureIndex
classes
Object[] classes
prior
LogPrior prior
- Deprecated.
biased
boolean biased
- Deprecated.
Class edu.stanford.nlp.classify.LogisticClassifierFactory extends Object implements Serializable |
serialVersionUID: 1L
weights
double[] weights
featureIndex
Index<E> featureIndex
classes
Object[] classes
serialVersionUID: 7826853908892790965L
means
double[] means
otherPrior
LogPrior otherPrior
type
LogPrior.LogPriorType type
sigmaSqM
double[] sigmaSqM
sigmaQuM
double[] sigmaQuM
sigmaSq
double sigmaSq
sigmaQu
double sigmaQu
epsilon
double epsilon
Class edu.stanford.nlp.classify.MIRAClassifierFactory extends Object implements Serializable |
serialVersionUID: 1L
epochs
int epochs
C
double C
averageWeights
boolean averageWeights
Class edu.stanford.nlp.classify.NaiveBayesClassifier extends Object implements Serializable |
serialVersionUID: 1544820342684024068L
weights
Counter<E> weights
priors
Counter<E> priors
features
Set<E> features
addZeroValued
boolean addZeroValued
priorZero
Counter<E> priorZero
labels
Set<E> labels
zero
Integer zero
Class edu.stanford.nlp.classify.NaiveBayesClassifierFactory extends Object implements Serializable |
serialVersionUID: -8164165428834534041L
kind
int kind
alphaClass
double alphaClass
alphaFeature
double alphaFeature
sigma
double sigma
prior
int prior
labelIndex
Index<E> labelIndex
featureIndex
Index<E> featureIndex
sigma
double sigma
interpretAlwaysOnFeatureAsPrior
boolean interpretAlwaysOnFeatureAsPrior
tuneSigma
boolean tuneSigma
folds
int folds
Class edu.stanford.nlp.classify.OneVsAllClassifier extends Object implements Serializable |
serialVersionUID: -743792054415242776L
featureIndex
Index<E> featureIndex
labelIndex
Index<E> labelIndex
binaryClassifiers
Map<K,V> binaryClassifiers
defaultLabel
Object defaultLabel
serialVersionUID: -3841757837680266182L
values
double[][] values
minValues
double[] minValues
maxValues
double[] maxValues
means
double[] means
stdevs
double[] stdevs
sourcesAndIds
ArrayList<E> sourcesAndIds
Class edu.stanford.nlp.classify.SVMLightClassifier extends LinearClassifier<L,F> implements Serializable |
serialVersionUID: 1L
platt
LinearClassifier<L,F> platt
Class edu.stanford.nlp.classify.SVMLightClassifierFactory extends Object implements Serializable |
serialVersionUID: 1L
C
double C
useSigmoid
boolean useSigmoid
verbose
boolean verbose
svmLightLearn
String svmLightLearn
svmStructLearn
String svmStructLearn
svmLightClassify
String svmLightClassify
svmStructClassify
String svmStructClassify
useAlphaFile
boolean useAlphaFile
alphaFile
File alphaFile
deleteTempFilesOnExit
boolean deleteTempFilesOnExit
svmLightVerbosity
int svmLightVerbosity
doEval
boolean doEval
tuneHeldOut
boolean tuneHeldOut
tuneCV
boolean tuneCV
scorer
Scorer<L> scorer
tuneMinimizer
LineSearcher tuneMinimizer
folds
int folds
heldOutPercent
double heldOutPercent
whitespacePattern
Pattern whitespacePattern
Class edu.stanford.nlp.classify.SVMLightRegression extends Object implements Serializable |
serialVersionUID: -8654429697969292128L
modelFile
File modelFile
featureIndex
Index<E> featureIndex
classifyCommand
String classifyCommand
serialVersionUID: -5435125789127705430L
weights
float[] weights
Class edu.stanford.nlp.classify.WekaClassifier extends Object implements Serializable |
serialVersionUID: 4079231667079259223L
wekaClassifier
weka.classifiers.Classifier wekaClassifier
classAttribute
weka.core.Attribute classAttribute
instances
weka.core.Instances instances
attIndex
Map<K,V> attIndex
classifierType
int classifierType
Class edu.stanford.nlp.classify.WekaDatumClassifier extends Object implements Serializable |
serialVersionUID: 1L
readObject
private void readObject(ObjectInputStream arg0)
throws IOException,
ClassNotFoundException
- Throws:
IOException
ClassNotFoundException
writeObject
private void writeObject(ObjectOutputStream arg0)
throws IOException
- Throws:
IOException
classifier
weka.classifiers.Classifier classifier
featureIndex
Index<E> featureIndex
labelIndex
Index<E> labelIndex
Class edu.stanford.nlp.classify.WekaDatumClassifierFactory extends Object implements Serializable |
classifierType
String classifierType
classifierOptions
String[] classifierOptions
Package edu.stanford.nlp.ie |
Class edu.stanford.nlp.ie.AbstractFieldExtractor extends Object implements Serializable |
serialVersionUID: -78232374030794537L
name
String name
description
String description
Class edu.stanford.nlp.ie.ChineseFeatureFactory extends FeatureFactory<IN extends CoreLabel> implements Serializable |
serialVersionUID: 4559182480629798157L
cmfs
edu.stanford.nlp.ie.ChineseMorphFeatureSets cmfs
Class edu.stanford.nlp.ie.ChineseMorphFeatureSets extends Object implements Serializable |
serialVersionUID: -1055526945031459198L
featIndex
Index<E> featIndex
singletonFeatures
Map<K,V> singletonFeatures
affixFeatures
Map<K,V> affixFeatures
Class edu.stanford.nlp.ie.ClassifierFieldExtractor extends edu.stanford.nlp.ie.AbstractFieldExtractor implements Serializable |
serialVersionUID: 8441980740688320766L
classifier
Classifier<L,F> classifier
Class edu.stanford.nlp.ie.Corpus extends edu.stanford.nlp.ling.BasicDataCollection<L,F extends HasWord> implements Serializable |
serialVersionUID: 7837079430197487945L
targetFields
String[] targetFields
Class edu.stanford.nlp.ie.ExtractDemo extends JFrame implements Serializable |
serialVersionUID: 5675421464216140787L
conceptValues
JPanel conceptValues
topPanel
JPanel topPanel
ontologyLabel
JTextField ontologyLabel
directoryLabel
JTextField directoryLabel
searchField
JTextField searchField
urlField
JTextField urlField
classChooser
JComboBox classChooser
slotNames
List<E> slotNames
relationFields
JTextField[] relationFields
fromURLField
JLabel fromURLField
mergerLabel
JTextField mergerLabel
merger
edu.stanford.nlp.ie.merge.InstanceMerger merger
extractors
edu.stanford.nlp.ie.FieldExtractor[] extractors
searcher
edu.stanford.nlp.web.WebSearch searcher
confidences
edu.stanford.nlp.ie.Confidence[] confidences
searchURLs
String[] searchURLs
next
JButton next
prev
JButton prev
fc
JFileChooser fc
instances
edu.stanford.smi.protege.model.Instance[] instances
currInstance
int currInstance
ontology
edu.stanford.smi.protege.model.KnowledgeBase ontology
concept
edu.stanford.smi.protege.model.Cls concept
pom
edu.stanford.nlp.ie.protege.ProtegeOntologyMediator pom
finishSem
int finishSem
serialVersionUID: -7218433234372062158L
fec
edu.stanford.nlp.ie.FieldExtractorCreator fec
description
String description
key
String key
value
String value
serialVersionUID: -2329726064739185544L
lexicon
Map<K,V> lexicon
wordToSubstrings
Map<K,V> wordToSubstrings
wordToGazetteEntries
Map<K,V> wordToGazetteEntries
wordToGazetteInfos
Map<K,V> wordToGazetteInfos
genericAnnotationKeys
HashSet<E> genericAnnotationKeys
lastNames
HashSet<E> lastNames
maleNames
HashSet<E> maleNames
femaleNames
HashSet<E> femaleNames
titlePattern
Pattern titlePattern
Class edu.stanford.nlp.ie.SingleFieldExtractor extends edu.stanford.nlp.ie.AbstractFieldExtractor implements Serializable |
serialVersionUID: 5697076532695454354L
Class edu.stanford.nlp.ie.TypedTaggedDocument extends edu.stanford.nlp.ling.BasicDocument<L> implements Serializable |
serialVersionUID: -1223080266359464067L
targetFields
String[] targetFields
Package edu.stanford.nlp.ie.crf |
serialVersionUID: -8345554365027671190L
features
List<E> features
- Features for this Datum.
label
Object label
serialVersionUID: 7403010868396790276L
label
int[] label
hashCode
int hashCode
Package edu.stanford.nlp.ie.pascal |
Class edu.stanford.nlp.ie.pascal.DateModel.InvalidDateException extends Exception implements Serializable |
serialVersionUID: -9217048665732499960L
Class edu.stanford.nlp.ie.pascal.SimpleDateModel.InvalidDateException extends Exception implements Serializable |
serialVersionUID: 7336785414776655140L
Package edu.stanford.nlp.international.morph |
serialVersionUID: -3893316324305154940L
fSpec
Map<K,V> fSpec
altTag
String altTag
serialVersionUID: -5720683653931585664L
activeFeatures
Set<E> activeFeatures
Package edu.stanford.nlp.io |
Class edu.stanford.nlp.io.FileArrayList extends ArrayList<File> implements Serializable |
serialVersionUID: 5424659657299318194L
Class edu.stanford.nlp.io.MultiGZIPInputStream.NoGzipMagicException extends IOException implements Serializable |
serialVersionUID: 3084169624430655013L
serialVersionUID: -8572218999165094626L
Package edu.stanford.nlp.ling |
Class edu.stanford.nlp.ling.BasicDataCollection extends ArrayList<Datum<L,F>> implements Serializable |
serialVersionUID: -7836249640130378128L
features
List<E> features
name
String name
serialVersionUID: -4857004070061779966L
features
Collection<E> features
- features for this Datum
labels
List<E> labels
- labels for this Datum. Invariant: always non-null
Class edu.stanford.nlp.ling.BasicDocument extends ArrayList<Word> implements Serializable |
serialVersionUID: -24171720584352262L
title
String title
originalText
String originalText
labels
List<E> labels
tokenizerFactory
TokenizerFactory<T> tokenizerFactory
Class edu.stanford.nlp.ling.Category extends StringLabel implements Serializable |
serialVersionUID: 7162506625143996046L
serialVersionUID: -745085381666943254L
word
String word
tag
String tag
serialVersionUID: 2L
serialVersionUID: 1L
Class edu.stanford.nlp.ling.IndexedWord extends CoreLabel implements Serializable |
serialVersionUID: 3739633991145239829L
serialVersionUID: -7252006452127051085L
tag
Label tag
Class edu.stanford.nlp.ling.NullLabel extends ValueLabel implements Serializable |
serialVersionUID: -4546142182973131732L
serialVersionUID: -255312811814660438L
features
Counter<E> features
- features for this Datum
label
Object label
- labels for this Datum. Invariant: always non-null
serialVersionUID: -4153619273767524247L
str
String str
beginPosition
int beginPosition
- Start position of the word in the original input string
endPosition
int endPosition
- End position of the word in the original input string
Class edu.stanford.nlp.ling.Tag extends StringLabel implements Serializable |
serialVersionUID: 1143434026005416755L
serialVersionUID: -7252006452127051085L
tag
String tag
Class edu.stanford.nlp.ling.TypedTaggedWord extends TaggedWord implements Serializable |
serialVersionUID: -1116081900490995750L
type
int type
serialVersionUID: -1413303679077285530L
serialVersionUID: -4817252915997034058L
serialVersionUID: -5993410244163988138L
word
String word
lemma
String lemma
tag
String tag
serialVersionUID: -1859527239216813742L
word
String word
tag
String tag
Package edu.stanford.nlp.math |
serialVersionUID: -5702334375099248894L
val
double val
dot
double dot
Class edu.stanford.nlp.math.ScientificNotationDouble extends Number implements Serializable |
serialVersionUID: 3920695442203179910L
base
double base
exponent
int exponent
Package edu.stanford.nlp.maxent |
Class edu.stanford.nlp.maxent.LinearType2Classifier extends Object implements Serializable |
serialVersionUID: 3018892419663189770L
weights
ClassicCounter<E> weights
Package edu.stanford.nlp.objectbank |
serialVersionUID: 6846060575832573082L
delim
String delim
op
Function<T1,T2> op
serialVersionUID: 1L
oper
Function<T1,T2> oper
serialVersionUID: -4030295596701541770L
rif
ReaderIteratorFactory rif
ifrf
IteratorFromReaderFactory<T> ifrf
contents
List<E> contents
keepInMemory
boolean keepInMemory
Package edu.stanford.nlp.optimization |
serialVersionUID: 4290178321643529559L
serialVersionUID: 814182172645533781L
w
double[] w
d
double[] d
serialVersionUID: -7551807670291500396L
bSize
int bSize
quiet
boolean quiet
outputIterationsToFile
boolean outputIterationsToFile
gain
double gain
SGDPasses
int SGDPasses
QNPasses
int QNPasses
hessSampleSize
int hessSampleSize
QNMem
int QNMem
serialVersionUID: 1647150702529757545L
serialVersionUID: 1647150702529757545L
Package edu.stanford.nlp.parser.lexparser |
serialVersionUID: 3L
readObject
private void readObject(ObjectInputStream ois)
throws IOException,
ClassNotFoundException
- Throws:
IOException
ClassNotFoundException
tagProjection
TagProjection tagProjection
tagIndex
Index<E> tagIndex
wordIndex
Index<E> wordIndex
numTagBins
int numTagBins
tagBin
int[] tagBin
tlp
TreebankLanguagePack tlp
directional
boolean directional
useDistance
boolean useDistance
useCoarseDistance
boolean useCoarseDistance
lex
Lexicon lex
stopTW
IntTaggedWord stopTW
wildTW
IntTaggedWord wildTW
coarseDistanceBins
int[] coarseDistanceBins
regDistanceBins
int[] regDistanceBins
op
Options op
serialVersionUID: 4299501909017975915L
evalGF
boolean evalGF
- If true, then evaluation is over grammatical functions as well as the labels
If false, then grammatical functions are stripped for evaluation. This really
only makes sense if you've trained with grammatical functions but want to evaluate without them.
inputEncoding
String inputEncoding
outputEncoding
String outputEncoding
tlp
TreebankLanguagePack tlp
serialVersionUID: 1L
key
String key
annotationMark
String annotationMark
serialVersionUID: 8853426784197984653L
optionsString
StringBuilder optionsString
retainNPTmp
boolean retainNPTmp
retainNPSbj
boolean retainNPSbj
retainPRD
boolean retainPRD
retainPPClr
boolean retainPPClr
changeNoLabels
boolean changeNoLabels
collinizerRetainsPunctuation
boolean collinizerRetainsPunctuation
discardX
boolean discardX
headFinder
HeadFinder headFinder
annotationPatterns
Map<K,V> annotationPatterns
activeAnnotations
Map<K,V> activeAnnotations
morphoSpec
MorphoFeatureSpecification morphoSpec
baselineFeatures
List<E> baselineFeatures
additionalFeatures
List<E> additionalFeatures
Class edu.stanford.nlp.parser.lexparser.ArabicUnknownWordModel extends edu.stanford.nlp.parser.lexparser.BaseUnknownWordModel implements Serializable |
serialVersionUID: 4825624957364628771L
UNKNOWN_WORD
String UNKNOWN_WORD
BOUNDARY_TAG
String BOUNDARY_TAG
smartMutation
boolean smartMutation
unknownSuffixSize
int unknownSuffixSize
unknownPrefixSize
int unknownPrefixSize
serialVersionUID: 40L
readObject
private void readObject(ObjectInputStream ois)
throws IOException,
ClassNotFoundException
- Throws:
IOException
ClassNotFoundException
uwModel
UnknownWordModel uwModel
trainOptions
TrainOptions trainOptions
testOptions
TestOptions testOptions
smoothInUnknownsThreshold
int smoothInUnknownsThreshold
- If a word has been seen more than this many times, then relative
frequencies of tags are used for POS assignment; if not, they are smoothed
with tag priors.
smartMutation
boolean smartMutation
- Have tags changeable based on statistics on word types having various
taggings.
wordIndex
Index<E> wordIndex
tagIndex
Index<E> tagIndex
seenCounter
ClassicCounter<E> seenCounter
- Records the number of times word/tag pair was seen in training data.
Includes word/tag pairs where one is a wildcard not a real word/tag.
smooth
double[] smooth
flexiTag
boolean flexiTag
useSignatureForKnownSmoothing
boolean useSignatureForKnownSmoothing
tagsToBaseTags
int[] tagsToBaseTags
Class edu.stanford.nlp.parser.lexparser.BaseUnknownWordModel extends Object implements Serializable |
serialVersionUID: 6355171148751673822L
useFirst
boolean useFirst
useEnd
boolean useEnd
useGT
boolean useGT
useFirstCap
boolean useFirstCap
endLength
int endLength
unknownLevel
int unknownLevel
trainOptions
TrainOptions trainOptions
wordIndex
Index<E> wordIndex
tagIndex
Index<E> tagIndex
unSeenCounter
ClassicCounter<E> unSeenCounter
tagHash
HashMap<K,V> tagHash
seenEnd
Set<E> seenEnd
unknownGT
HashMap<K,V> unknownGT
lex
Lexicon lex
Class edu.stanford.nlp.parser.lexparser.BinaryGrammar extends Object implements Serializable |
serialVersionUID: 1L
readObject
private void readObject(ObjectInputStream arg0)
throws IOException,
ClassNotFoundException
- Throws:
IOException
ClassNotFoundException
index
Index<E> index
allRules
List<E> allRules
Class edu.stanford.nlp.parser.lexparser.BinaryRule extends Object implements Serializable |
serialVersionUID: 1L
parent
int parent
score
float score
leftChild
int leftChild
rightChild
int rightChild
hashCode
int hashCode
Class edu.stanford.nlp.parser.lexparser.ChineseCharacterBasedLexicon extends Object implements Serializable |
serialVersionUID: -5357655683145854069L
lengthPenalty
double lengthPenalty
penaltyType
int penaltyType
charDistributions
Map<K,V> charDistributions
knownChars
Set<E> knownChars
POSDistribution
Distribution<E> POSDistribution
useUnknownCharacterModel
boolean useUnknownCharacterModel
wordIndex
Index<E> wordIndex
tagIndex
Index<E> tagIndex
Class edu.stanford.nlp.parser.lexparser.ChineseLexicon extends BaseLexicon implements Serializable |
serialVersionUID: -7836464391021114960L
useCharBasedUnknownWordModel
boolean useCharBasedUnknownWordModel
useGoodTuringUnknownWordModel
boolean useGoodTuringUnknownWordModel
probRandomWalk
edu.stanford.nlp.parser.lexparser.RandomWalk probRandomWalk
Class edu.stanford.nlp.parser.lexparser.ChineseLexiconAndWordSegmenter extends Object implements Serializable |
serialVersionUID: -6554995189795187918L
readObject
private void readObject(ObjectInputStream arg0)
throws IOException,
ClassNotFoundException
- Throws:
IOException
ClassNotFoundException
chineseLexicon
edu.stanford.nlp.parser.lexparser.ChineseLexicon chineseLexicon
wordSegmenter
edu.stanford.nlp.process.WordSegmenter wordSegmenter
op
Options op
Class edu.stanford.nlp.parser.lexparser.ChineseMarkovWordSegmenter extends Object implements Serializable |
serialVersionUID: 1559606198270645508L
initialPOSDist
Distribution<E> initialPOSDist
markovPOSDists
Map<K,V> markovPOSDists
lex
edu.stanford.nlp.parser.lexparser.ChineseCharacterBasedLexicon lex
POSes
Set<E> POSes
wordIndex
Index<E> wordIndex
tagIndex
Index<E> tagIndex
Class edu.stanford.nlp.parser.lexparser.ChineseMaxentLexicon extends Object implements Serializable |
serialVersionUID: 238834703409896852L
featExtractor
edu.stanford.nlp.parser.lexparser.ChineseWordFeatureExtractor featExtractor
wordThreshold
Pair<T1,T2> wordThreshold
charThreshold
Pair<T1,T2> charThreshold
bigramThreshold
Pair<T1,T2> bigramThreshold
conjThreshold
Pair<T1,T2> conjThreshold
featureThresholds
List<E> featureThresholds
universalThreshold
int universalThreshold
scorer
LinearClassifier<L,F> scorer
functionWordTags
Map<K,V> functionWordTags
tagDist
Distribution<E> tagDist
wordIndex
Index<E> wordIndex
tagIndex
Index<E> tagIndex
iteratorCutoffFactor
double iteratorCutoffFactor
initialWeightFile
String initialWeightFile
trainFloat
boolean trainFloat
tol
double tol
sigma
double sigma
featureLevel
int featureLevel
trainOnLowCount
boolean trainOnLowCount
trainByType
boolean trainByType
tlpParams
TreebankLangParserParams tlpParams
ctlp
TreebankLanguagePack ctlp
op
Options op
tagsForWord
CollectionValuedMap<K,V> tagsForWord
Class edu.stanford.nlp.parser.lexparser.ChineseSimWordAvgDepGrammar extends MLEDependencyGrammar implements Serializable |
serialVersionUID: -1845503582705055342L
simSmooth
double simSmooth
simArgMap
Map<K,V> simArgMap
simHeadMap
Map<K,V> simHeadMap
debug
boolean debug
verbose
boolean verbose
statsCounter
ClassicCounter<E> statsCounter
serialVersionUID: 2L
ctlp
ChineseTreebankLanguagePack ctlp
charTags
boolean charTags
useCharacterBasedLexicon
boolean useCharacterBasedLexicon
useMaxentLexicon
boolean useMaxentLexicon
useMaxentDepGrammar
boolean useMaxentDepGrammar
segment
boolean segment
segmentMarkov
boolean segmentMarkov
sunJurafskyHeadFinder
boolean sunJurafskyHeadFinder
bikelHeadFinder
boolean bikelHeadFinder
discardFrags
boolean discardFrags
useSimilarWordMap
boolean useSimilarWordMap
segmenterClass
String segmenterClass
lex
Lexicon lex
segmenter
edu.stanford.nlp.process.WordSegmenter segmenter
headFinder
HeadFinder headFinder
chineseSplitDouHao
boolean chineseSplitDouHao
chineseSplitPunct
boolean chineseSplitPunct
chineseSplitPunctLR
boolean chineseSplitPunctLR
markVVsisterIP
boolean markVVsisterIP
markPsisterIP
boolean markPsisterIP
markIPsisterVVorP
boolean markIPsisterVVorP
markADgrandchildOfIP
boolean markADgrandchildOfIP
gpaAD
boolean gpaAD
chineseVerySelectiveTagPA
boolean chineseVerySelectiveTagPA
chineseSelectiveTagPA
boolean chineseSelectiveTagPA
markIPsisterBA
boolean markIPsisterBA
markVPadjunct
boolean markVPadjunct
markNPmodNP
boolean markNPmodNP
markModifiedNP
boolean markModifiedNP
markNPconj
boolean markNPconj
markMultiNtag
boolean markMultiNtag
markIPsisDEC
boolean markIPsisDEC
markIPconj
boolean markIPconj
markIPadjsubj
boolean markIPadjsubj
chineseSplitVP
int chineseSplitVP
mergeNNVV
boolean mergeNNVV
unaryIP
boolean unaryIP
unaryCP
boolean unaryCP
paRootDtr
boolean paRootDtr
markPostverbalP
boolean markPostverbalP
markPostverbalPP
boolean markPostverbalPP
splitBaseNP
boolean splitBaseNP
tagWordSize
boolean tagWordSize
markCC
boolean markCC
splitNPTMP
boolean splitNPTMP
splitPPTMP
boolean splitPPTMP
splitXPTMP
boolean splitXPTMP
dominatesV
boolean dominatesV
useGoodTuringUnknownWordModel
boolean useGoodTuringUnknownWordModel
useCharBasedUnknownWordModel
boolean useCharBasedUnknownWordModel
lengthPenalty
double lengthPenalty
useUnknownCharacterModel
boolean useUnknownCharacterModel
penaltyType
int penaltyType
depGramFeatureLevel
int depGramFeatureLevel
Class edu.stanford.nlp.parser.lexparser.ChineseUnknownWordModel extends edu.stanford.nlp.parser.lexparser.BaseUnknownWordModel implements Serializable |
serialVersionUID: 221L
useUnicodeType
boolean useUnicodeType
seenFirst
Set<E> seenFirst
Class edu.stanford.nlp.parser.lexparser.ChineseWordFeatureExtractor extends Object implements Serializable |
serialVersionUID: -4327267414095852504L
morpho
boolean morpho
chars
boolean chars
rads
boolean rads
useLength
boolean useLength
useFreq
boolean useFreq
bigrams
boolean bigrams
conjunctions
boolean conjunctions
mildConjunctions
boolean mildConjunctions
turnOffWordFeatures
boolean turnOffWordFeatures
wordCounter
IntCounter<E> wordCounter
cmfs
edu.stanford.nlp.ie.ChineseMorphFeatureSets cmfs
threshedFeatures
Collection<E> threshedFeatures
Class edu.stanford.nlp.parser.lexparser.DependencyGrammarCombination extends MLEDependencyGrammar implements Serializable |
serialVersionUID: 1421410021676721958L
grammar1
MLEDependencyGrammar grammar1
grammar2
MLEDependencyGrammar grammar2
wt2
double wt2
serialVersionUID: 4153878351331522581L
headFinder
HeadFinder headFinder
englishTrain
EnglishTreebankParserParams.EnglishTrain englishTrain
englishTest
EnglishTreebankParserParams.EnglishTest englishTest
serialVersionUID: 183157656745674521L
retainNPTMPSubcategories
boolean retainNPTMPSubcategories
retainTMPSubcategories
boolean retainTMPSubcategories
retainADVSubcategories
boolean retainADVSubcategories
makeCopulaHead
boolean makeCopulaHead
serialVersionUID: 1831576434872643L
leaveItAll
int leaveItAll
- if true, leave all PTB (functional tag) annotations (bad)
splitIN
int splitIN
- Annotate prepositions into subcategories. Values:
0 = no annotation
1 = IN with a ^S.* parent (putative subordinating
conjunctions) marked differently from others (real prepositions). OK.
2 = Annotate IN prepositions 3 ways: ^S.* parent, ^N.* parent or rest
(generally predicative ADJP, VP). Better than sIN=1. Good.
3 = Annotate prepositions 6 ways: real feature engineering. Great.
4 = Refinement of 3: allows -SC under SINV, WHADVP for -T and no -SCC
if the parent is an NP.
5 = Like 4 but maps TO to IN in a "nominal" (N*, P*, A*) context.
6 = 4, but mark V/A complement and leave noun ones unmarked instead.
splitQuotes
boolean splitQuotes
- Mark quote marks for single vs. double so don't get mismatched ones.
splitSFP
boolean splitSFP
- Separate out sentence final punct. (. ! ?). Doesn't help.
splitPercent
boolean splitPercent
- Mark the nouns that are percent signs. Slightly good.
splitNPpercent
int splitNPpercent
- Mark phrases that are headed by %.
A value of 0 = do nothing, 1 = only NP, 2 = NP and ADJP,
3 = NP, ADJP and QP, 4 = any phrase.
tagRBGPA
boolean tagRBGPA
- Grand parent annotate RB to try to distinguish sentential ones and
ones in places like NP post modifier (things like 'very' are already
distinguished as their parent is ADJP).
splitNNP
int splitNNP
- Mark NNP words as to position in phrase (single, left, right, inside)
or subcategorizes NNP(S) as initials or initial/final in NP.
joinPound
boolean joinPound
- Join pound with dollar.
joinJJ
boolean joinJJ
- Joint comparative and superlative adjective with positive.
joinNounTags
boolean joinNounTags
- Join proper nouns with common nouns. This isn't to improve
performance, but because Genia doesn't use proper noun tags in
general.
splitPPJJ
boolean splitPPJJ
- A special test for "such" mainly ("such as Fred"). A wash, so omit
splitTRJJ
boolean splitTRJJ
- Put a special tag on 'transitive adjectives' with NP complement, like
'due May 15' -- it also catches 'such' in 'such as NP', which may
be a good. Matches 658 times in 2-21 training corpus. Wash.
splitJJCOMP
boolean splitJJCOMP
- Put a special tag on 'adjectives with complements'. This acts as a
general subcat feature for adjectives.
splitMoreLess
boolean splitMoreLess
- Specially mark the comparative/superlative words: less, least,
more, most
unaryDT
boolean unaryDT
- Mark "Intransitive" DT. Good.
unaryRB
boolean unaryRB
- Mark "Intransitive" RB. Good.
unaryPRP
boolean unaryPRP
- "Intransitive" PRP. Wash -- basically a no-op really.
markReflexivePRP
boolean markReflexivePRP
- Mark reflexivie PRP words.
unaryIN
boolean unaryIN
- Mark "Intransitive" IN. Minutely negative.
splitCC
int splitCC
- Provide annotation of conjunctions. Gives modest gains (numbers
shown F1 increase with respect to goodPCFG in June 2005). A value of
1 annotates both "and" and "or" as "CC-C" (+0.29%),
2 annotates "but" and "&" separately (+0.17%),
3 annotates just "and" (equalsIgnoreCase) (+0.11%),
0 annotates nothing (+0.00%).
splitNOT
boolean splitNOT
- Annotates forms of "not" specially as tag "NOT". BAD
splitRB
boolean splitRB
- Split modifier (NP, AdjP) adverbs from others.
This does nothing if you're already doing tagPA.
splitAux
int splitAux
- Make special tags for forms of BE and HAVE (and maybe DO/HELP, etc.).
A value of 0 is do nothing.
A value of 1 is the basic form. Positive PCFG effect,
but neutral to negative in Factored, and impossible if you use gPA.
A value of 2 adds in "s" = "'s"
and delves further to disambiguate "'s" as BE or HAVE. Theoretically
good, but no practical gains.
A value of 3 adds DO.
A value of 4 adds HELP (which also takes VB form complement) as DO.
A value of 5 adds LET (which also takes VB form complement) as DO.
A value of 6 adds MAKE (which also takes VB form complement) as DO.
A value of 7 adds WATCH, SEE (which also take VB form complement) as DO.
A value of 8 adds come, go, but not inflections (which colloquially
can take a VB form complement) as DO.
A value of 9 adds GET as BE.
Differences are small. You get about 0.3 F1 by doing something; the best
appear to be 2 or 3 for sentence exact and 7 or 8 for LP/LR F1.
vpSubCat
boolean vpSubCat
- Pitiful attempt at marking V* preterms with their surface subcat
frames. Bad so far.
markDitransV
int markDitransV
- Attempt to record ditransitive verbs. The value 0 means do nothing;
1 records two or more NP or S* arguments, and 2 means to only record
two or more NP arguments (that aren't NP-TMP).
1 gave neutral to bad results.
splitVP
int splitVP
- Add (head) tags to VPs. An argument of
0 = no head-subcategorization of VPs,
1 = add head tags (anything, as given by HeadFinder),
2 = add head tags, but collapse finite verb tags (VBP, VBD, VBZ, MD)
together,
3 = only annotate verbal tags, and collapse finite verb tags
(annotation is VBF, TO, VBG, VBN, VB, or zero),
4 = only split on categories of VBF, TO, VBG, VBN, VB, and map
cases that are not headed by a verbal category to an appropriate
category based on word suffix (ing, d, t, s, to) or to VB otherwise.
We usually use a value of 3; 2 or 3 is much better than 0.
See also
splitVPNPAgr
. If it is true, its effects override
any value set for this parameter.
splitVPNPAgr
boolean splitVPNPAgr
- Put enough marking on VP and NP to permit "agreement".
splitSTag
int splitSTag
- Mark S/SINV/SQ nodes according to verbal tag. Meanings are:
0 = no subcategorization.
1 = mark with head tag
2 = mark only -VBF if VBZ/VBD/VBP/MD tag
3 = as 2 and mark -VBNF if TO/VBG/VBN/VB
4 = as 2 but only mark S not SINV/SQ
5 = as 3 but only mark S not SINV/SQ
Previously seen as bad. Option 4 might be promising now.
markContainedVP
boolean markContainedVP
splitNPPRP
boolean splitNPPRP
dominatesV
int dominatesV
- Verbal distance -- mark whether symbol dominates a verb (V*, MD).
Very good.
dominatesI
boolean dominatesI
- Verbal distance -- mark whether symbol dominates a preposition (IN)
dominatesC
boolean dominatesC
- Verbal distance -- mark whether symbol dominates a conjunction (CC)
markCC
int markCC
- Mark phrases which are conjunctions.
0 = No marking
1 = Any phrase with a CC daughter that isn't first or last. Possibly marginally positive.
2 = As 0 but also a non-marginal CONJP daughter. In principle good, but no gains.
3 = More like Charniak. Not yet implemented. Need to annotate _before_ annotate children!
np or vp with two or more np/vp children, a comma, cc or conjp, and nothing else.
splitSGapped
int splitSGapped
- Mark specially S nodes with "gapped" subject (control, raising).
1 is basic version. 2 is better mark S nodes with "gapped" subject.
3 seems best on small training set, but all of these are too similar;
4 can't be differentiated.
5 is done on tree before empty splitting. (Bad!?)
splitNumNP
boolean splitNumNP
- Mark "numeric NPs". Probably bad?
splitPoss
int splitPoss
- Give a special tag to NPs which are possessive NPs (end in 's).
A value of 0 means do nothing, 1 means tagging possessive NPs with
"-P", 2 means restructure possessive NPs so that they introduce a
POSSP node that
takes as children the POS and a regularly structured NP.
I.e., recover standard good linguistic practice circa 1985.
This seems a good idea, but is almost a no-op (modulo fine points of
markovization), since the previous NP-P phrase already uniquely
captured what is now a POSSP.
splitBaseNP
int splitBaseNP
- Mark base NPs. A value of 0 = no marking, 1 = marking
baseNP (ones which rewrite just as preterminals), and 2 = doing
Collins-style marking, where an extra NP node is inserted above a
baseNP, if it isn't
already in an NP over NP construction, as in Collins 1999.
This option shouldn't really be in EnglishTrain since it's needed
at parsing time. But we don't currently use it....
A value of 1 is good.
splitTMP
int splitTMP
- Retain NP-TMP (or maybe PP-TMP) annotation. Good.
The values for this parameter are defined in
NPTmpRetainingTreeNormalizer.
splitSbar
int splitSbar
- Split SBAR nodes.
1 = mark 'in order to' purpose clauses; this is actually a small and
inconsistent part of what is marked SBAR-PRP in the treebank, which
is mainly 'because' reason clauses.
2 = mark all infinitive SBAR.
3 = do 1 and 2.
A value of 1 seems minutely positive; 2 and 3 seem negative.
Also get 'in case Sfin', 'In order to', and on one occasion
'in order that'
splitNPADV
int splitNPADV
- Retain NP-ADV annotation. 0 means strip "-ADV" annotation. 1 means to
retain it, and to percolate it down to a head tag providing it can
do it through a path of only NP nodes.
splitNPNNP
int splitNPNNP
- Mark NP-NNP. 0 is nothing; 1 is only NNP head, 2 is NNP and NNPS
head; 3 is NNP or NNPS anywhere in local NP. All bad!
correctTags
boolean correctTags
- 'Correct' tags to produce verbs in VPs, etc. where possible
rightPhrasal
boolean rightPhrasal
- Right edge has a phrasal node. Bad?
sisterSplitLevel
int sisterSplitLevel
- Set the support * KL cutoff level (1-4) for sister splitting
-- don't use it, as far as we can tell so far
gpaRootVP
boolean gpaRootVP
- Grand-parent annotate (root mark) VP below ROOT. Seems negative.
makePPTOintoIN
int makePPTOintoIN
- Change TO inside PP to IN.
Class edu.stanford.nlp.parser.lexparser.EnglishUnknownWordModel extends edu.stanford.nlp.parser.lexparser.BaseUnknownWordModel implements Serializable |
serialVersionUID: 4825624957364628770L
smartMutation
boolean smartMutation
unknownSuffixSize
int unknownSuffixSize
unknownPrefixSize
int unknownPrefixSize
Class edu.stanford.nlp.parser.lexparser.FactoredLexicon extends BaseLexicon implements Serializable |
serialVersionUID: 8496467161563992530L
morphoSpec
MorphoFeatureSpecification morphoSpec
serialVersionUID: -6976724734594763986L
optionsString
StringBuilder optionsString
headFinder
HeadFinder headFinder
annotationPatterns
Map<K,V> annotationPatterns
activeAnnotations
Map<K,V> activeAnnotations
readPennFormat
boolean readPennFormat
collinizerRetainsPunctuation
boolean collinizerRetainsPunctuation
mwCounter
TwoDimensionalCounter<K1,K2> mwCounter
morphoSpec
MorphoFeatureSpecification morphoSpec
baselineFeatures
List<E> baselineFeatures
additionalFeatures
List<E> additionalFeatures
Class edu.stanford.nlp.parser.lexparser.FrenchUnknownWordModel extends edu.stanford.nlp.parser.lexparser.BaseUnknownWordModel implements Serializable |
serialVersionUID: -776564693549194424L
smartMutation
boolean smartMutation
unknownSuffixSize
int unknownSuffixSize
unknownPrefixSize
int unknownPrefixSize
serialVersionUID: -617650500538652513L
Class edu.stanford.nlp.parser.lexparser.GermanUnknownWordModel extends edu.stanford.nlp.parser.lexparser.BaseUnknownWordModel implements Serializable |
serialVersionUID: 221L
serialVersionUID: -3466519995341208619L
optionsString
StringBuilder optionsString
serialVersionUID: 2L
serialVersionUID: 1L
head
IntTaggedWord head
arg
IntTaggedWord arg
leftHeaded
boolean leftHeaded
distance
short distance
serialVersionUID: 1L
word
int word
tag
short tag
Class edu.stanford.nlp.parser.lexparser.Lattice extends Object implements Serializable |
serialVersionUID: 5135076134500512556L
constraints
List<E> constraints
edges
List<E> edges
nodes
Set<E> nodes
edgeStartsAt
Map<K,V> edgeStartsAt
maxNode
int maxNode
Class edu.stanford.nlp.parser.lexparser.LatticeEdge extends Object implements Serializable |
serialVersionUID: 4416189959485854286L
word
String word
label
String label
weight
double weight
start
int start
end
int end
attrs
Map<K,V> attrs
Class edu.stanford.nlp.parser.lexparser.LexicalizedParser extends Object implements Serializable |
serialVersionUID: 2L
lex
Lexicon lex
bg
edu.stanford.nlp.parser.lexparser.BinaryGrammar bg
ug
edu.stanford.nlp.parser.lexparser.UnaryGrammar ug
dg
DependencyGrammar dg
stateIndex
Index<E> stateIndex
wordIndex
Index<E> wordIndex
tagIndex
Index<E> tagIndex
op
Options op
serialVersionUID: -8751155308803440889L
readObject
private void readObject(ObjectInputStream arg0)
throws IOException,
ClassNotFoundException
- Throws:
IOException
ClassNotFoundException
stopCounter
ClassicCounter<E> stopCounter
depCounter
ClassicCounter<E> depCounter
nonDepCounter
ClassicCounter<E> nonDepCounter
wordPairCounter
ClassicCounter<E> wordPairCounter
wordCounter
ClassicCounter<E> wordCounter
largeWordFeatExtractor
edu.stanford.nlp.parser.lexparser.WordFeatureExtractor largeWordFeatExtractor
smallWordFeatExtractor
edu.stanford.nlp.parser.lexparser.WordFeatureExtractor smallWordFeatExtractor
largeWordFeatIndex
Index<E> largeWordFeatIndex
smallWordFeatIndex
Index<E> smallWordFeatIndex
depClassifier
edu.stanford.nlp.classify.LogisticClassifier<L,F> depClassifier
stopSmooth
double stopSmooth
depSmooth
double depSmooth
wordSmooth
double wordSmooth
jointThresh
int jointThresh
wordFeatThresh
int wordFeatThresh
negExamplesForSentence
List<E> negExamplesForSentence
Class edu.stanford.nlp.parser.lexparser.MaxMatchSegmenter extends Object implements Serializable |
serialVersionUID: 8260792244886911724L
words
Set<E> words
serialVersionUID: 1L
readObject
private void readObject(ObjectInputStream stream)
throws IOException,
ClassNotFoundException
- Throws:
IOException
ClassNotFoundException
writeObject
private void writeObject(ObjectOutputStream stream)
throws IOException
- Throws:
IOException
useSmoothTagProjection
boolean useSmoothTagProjection
useUnigramWordSmoothing
boolean useUnigramWordSmoothing
numWordTokens
int numWordTokens
argCounter
ClassicCounter<E> argCounter
- Stores all the counts for dependencies (with and without the word
being a wildcard) in the reduced tag space.
stopCounter
ClassicCounter<E> stopCounter
smooth_aT_hTWd
double smooth_aT_hTWd
- Bayesian m-estimate prior for aT given hTWd against base distribution
of aT given hTd.
TODO: Note that these values are overwritten in the constructor. Find what is best and then maybe remove these defaults!
smooth_aTW_hTWd
double smooth_aTW_hTWd
- Bayesian m-estimate prior for aTW given hTWd against base distribution
of aTW given hTd.
smooth_stop
double smooth_stop
interp
double interp
- Interpolation between model that directly predicts aTW and model
that predicts aT and then aW given aT. This percent of the mass
is on the model directly predicting aTW.
smooth_aTW_aT
double smooth_aTW_aT
smooth_aTW_hTd
double smooth_aTW_hTd
smooth_aT_hTd
double smooth_aT_hTd
smooth_aPTW_aPT
double smooth_aPTW_aPT
smoothTP
TagProjection smoothTP
smoothTPIndex
Index<E> smoothTPIndex
serialVersionUID: 757812264219400466L
markRC
boolean markRC
markZuVP
boolean markZuVP
markLP
boolean markLP
markColon
boolean markColon
markKonjParent
boolean markKonjParent
markHDParent
boolean markHDParent
markContainsV
boolean markContainsV
nodeCleanup
int nodeCleanup
headFinder
HeadFinder headFinder
treeNormalizerInsertNPinPP
boolean treeNormalizerInsertNPinPP
treeNormalizerLeaveGF
boolean treeNormalizerLeaveGF
treeReaderFactory
edu.stanford.nlp.trees.international.negra.NegraPennTreeReaderFactory treeReaderFactory
serialVersionUID: 4L
readObject
private void readObject(ObjectInputStream in)
throws IOException,
ClassNotFoundException
- Making the TestOptions transient means it won't even be
constructed when you deserialize an Options, so we need to
construct it on our own when deserializing
- Throws:
IOException
ClassNotFoundException
lexOptions
Options.LexOptions lexOptions
tlpParams
TreebankLangParserParams tlpParams
- The treebank-specific parser parameters to use.
forceCNF
boolean forceCNF
- Forces parsing with strictly CNF grammar -- unary chains are converted
to XP&YP symbols and back
doPCFG
boolean doPCFG
- Do a PCFG parse of the sentence. If both variables are on,
also do a combined parse of the sentence.
doDep
boolean doDep
- Do a dependency parse of the sentence.
freeDependencies
boolean freeDependencies
- if true, any child can be the head (seems rather bad!)
directional
boolean directional
- Whether dependency grammar considers left/right direction. Good.
genStop
boolean genStop
useSmoothTagProjection
boolean useSmoothTagProjection
useUnigramWordSmoothing
boolean useUnigramWordSmoothing
distance
boolean distance
- Use distance bins in the dependency calculations
coarseDistance
boolean coarseDistance
- Use coarser distance (4 bins) in dependency calculations
dcTags
boolean dcTags
- "double count" tags rewrites as word in PCFG and Dep parser. Good for
combined parsing only (it used to not kick in for PCFG parsing). This
option is only used at Test time, but it is now in Options, so the
correct choice for a grammar is recorded by a serialized parser.
You should turn this off for a vanilla PCFG parser.
nodePrune
boolean nodePrune
- If true, inside the factored parser, remove any node from the final
chosen tree which improves the PCFG score. This was added as the
dependency factor tends to encourage 'deep' trees.
trainOptions
TrainOptions trainOptions
wordFunction
Function<T1,T2> wordFunction
- A function that maps words used in training and testing to new
words. For example, it could be a function to lowercase text,
such as edu.stanford.nlp.util.LowercaseFunction (which makes the
parser case insensitive). This function is applied in
LexicalizedParserQuery.parse and in the training methods which
build a new parser.
serialVersionUID: 2805351374506855632L
useUnknownWordSignatures
int useUnknownWordSignatures
- Whether to use suffix and capitalization information for unknowns.
Within the BaseLexicon model options have the following meaning:
0 means a single unknown token. 1 uses suffix, and capitalization.
2 uses a variant (richer) form of signature. Good.
Use this one. Using the richer signatures in versions 3 or 4 seems
to have very marginal or no positive value.
3 uses a richer form of signature that mimics the NER word type
patterns. 4 is a variant of 2. 5 is another with more English
specific morphology (good for English unknowns!).
6-9 are options for Arabic. 9 codes some patterns for numbers and
derivational morphology, but also supports unknownPrefixSize and
unknownSuffixSize.
For German, 0 means a single unknown token, and non-zero means to use
capitalization of first letter and a suffix of length
unknownSuffixSize.
smoothInUnknownsThreshold
int smoothInUnknownsThreshold
- Words more common than this are tagged with MLE P(t|w). Default 100. The
smoothing is sufficiently slight that changing this has little effect.
But set this to 0 to be able to use the parser as a vanilla PCFG with
no smoothing (not as a practical parser but for exposition or debugging).
smartMutation
boolean smartMutation
- Smarter smoothing for rare words.
useUnicodeType
boolean useUnicodeType
- Make use of unicode code point types in smoothing.
unknownSuffixSize
int unknownSuffixSize
- For certain Lexicons, a certain number of word-final letters are
used to subclassify the unknown token. This gives the number of
letters.
unknownPrefixSize
int unknownPrefixSize
- For certain Lexicons, a certain number of word-initial letters are
used to subclassify the unknown token. This gives the number of
letters.
uwModel
String uwModel
- Model for unknown words that the lexicon should use
flexiTag
boolean flexiTag
useSignatureForKnownSmoothing
boolean useSignatureForKnownSmoothing
- Whether to use signature rather than just being unknown as prior in
known word smoothing. Currently only works if turned on for English.
Class edu.stanford.nlp.parser.lexparser.ParserConstraint extends Object implements Serializable |
serialVersionUID: 4955237758572202093L
start
int start
end
int end
state
Pattern state
Class edu.stanford.nlp.parser.lexparser.PetrovLexicon extends Object implements Serializable |
serialVersionUID: 5672415342334265614L
tagIndex
Index<E> tagIndex
wordIndex
Index<E> wordIndex
wordCounter
ClassicCounter<E> wordCounter
tagCounter
ClassicCounter<E> tagCounter
unseenTagCounter
ClassicCounter<E> unseenTagCounter
tagAndWordCounter
ClassicCounter<E> tagAndWordCounter
unseenTagAndSignatureCounter
ClassicCounter<E> unseenTagAndSignatureCounter
smoothInUnknownsThreshold
int smoothInUnknownsThreshold
smooth
double smooth
rulesWithWord
List<E>[] rulesWithWord
Class edu.stanford.nlp.parser.lexparser.SubcategoryStripperTreeTransformer extends Object implements Serializable |
serialVersionUID: 1L
langpack
TreebankLanguagePack langpack
serialVersionUID: 7256526346598L
noRecoveryTagging
boolean noRecoveryTagging
- If false, then failure of the PCFG parser to parse a sentence
will trigger allowing all tags for words in parse recovery mode,
with a log probability of -1000.
If true, these extra taggings are not added.
It is false by default. Use option -noRecoveryTagging to set
to true.
doRecovery
boolean doRecovery
- If true, then failure of the PCFG factor to parse a sentence
will trigger parse recovery mode.
useN5
boolean useN5
- If true, the n^4 "speed-up" is not used with the Factored Parser.
useFastFactored
boolean useFastFactored
- If true, use approximate factored algorithm, which just rescores
PCFG k best, rather than exact factored algorithm. This algorithm
requires the dependency grammar to exist for rescoring, but not for
the dependency grammar to be run. Hence the correct usage for
guarding code only required for exact A* factored parsing is now
if (op.doPCFG && op.doDep && ! Test.useFastFactored).
iterativeCKY
boolean iterativeCKY
- If true, use faster iterative deepening CKY algorithm.
maxLength
int maxLength
- The maximum sentence length (including punctuation, etc.) to parse.
MAX_ITEMS
int MAX_ITEMS
- The maximum number of edges and hooks combined that the factored parser
will build before giving up. This number should probably be relative to
the sentence length parsed. In general, though, if the parser cannot parse
a sentence after this much work then there is no good parse consistent
between the PCFG and Dependency parsers. (Normally, depending on other
flags), the parser will then just return the best PCFG parse.)
unseenSmooth
double unseenSmooth
- The amount of smoothing put in (as an m-estimate) for unknown words.
If negative, set by the code in the lexicon class.
increasingLength
boolean increasingLength
- Parse trees in test treebank in order of increasing length.
preTag
boolean preTag
- Tag the sentences first, then parse given those (coarse) tags.
forceTags
boolean forceTags
- Parse using only tags given from correct answer or the POS tagger
forceTagBeginnings
boolean forceTagBeginnings
taggerSerializedFile
String taggerSerializedFile
- POS tagger model used when preTag is enabled.
noFunctionalForcing
boolean noFunctionalForcing
- Only valid with force tags - strips away functionals when forcing
the tags, meaning tags have to start
appropriately but the parser will assign the functional part.
evalb
boolean evalb
- Write EvalB-readable output files.
verbose
boolean verbose
- Print a lot of extra output as you parse.
exhaustiveTest
boolean exhaustiveTest
pcfgThreshold
boolean pcfgThreshold
- If this variable is true, and the sum of the inside and outside score
for a constituent is worse than the best known score for a sentence by
more than
pcfgThresholdValue
, then -Inf is returned as the
outside Score by oScore()
(while otherwise the true
outside score is returned).
pcfgThresholdValue
double pcfgThresholdValue
printAllBestParses
boolean printAllBestParses
- Print out all best PCFG parses.
depWeight
double depWeight
- Weighting on dependency log probs. The dependency grammar negative log
probability scores are simply multiplied by this number.
prunePunc
boolean prunePunc
addMissingFinalPunctuation
boolean addMissingFinalPunctuation
- If a token list does not have sentence final punctuation near the
end, then automatically add the default one.
This might help parsing if the treebank is all punctuated.
Not done if reading a treebank.
outputFormat
String outputFormat
- Determines format of output trees: choose among penn, oneline
outputFormatOptions
String outputFormatOptions
writeOutputFiles
boolean writeOutputFiles
- If true, write files parsed to a new file with the same name except
for an added ".stp" extension.
outputFilesDirectory
String outputFilesDirectory
- If the writeOutputFiles option is true, then output files appear in
this directory. An unset value (
null
) means to use
the directory of the source files. Use ""
or .
for the current directory.
outputFilesExtension
String outputFilesExtension
- If the writeOutputFiles option is true, then output files appear with
this extension. Use
""
for no extension.
outputFilesPrefix
String outputFilesPrefix
- If the writeOutputFiles option is true, then output files appear with
this prefix.
outputkBestEquivocation
String outputkBestEquivocation
- If this option is not null, output the k-best equivocation. Must be specified
with printPCFGkBest.
maxSpanForTags
int maxSpanForTags
- The largest span to consider for word-hood. Used for parsing unsegmented
Chinese text and parsing lattices. Keep it at 1 unless you know what
you're doing.
lengthNormalization
boolean lengthNormalization
- Turns on normalizing scores for sentence length. Makes no difference
(except decreased efficiency) unless maxSpanForTags is greater than one.
Works only for PCFG (so far).
sample
boolean sample
- Used when you want to generate sample parses instead of finding the best
parse. (NOT YET USED.)
printPCFGkBest
int printPCFGkBest
- Printing k-best parses from PCFG, when k > 0.
printFactoredKGood
int printFactoredKGood
- Printing k-best parses from PCFG, when k > 0.
evals
Properties evals
- What evaluations to report and how to report them
(using LexicalizedParser). Known evaluations
are: pcfgLB, pcfgCB, pcfgDA, pcfgTA, pcfgLL, pcfgRUO, pcfgCUO, pcfgCatE,
depDA, depTA, depLL,
factLB, factCB, factDA, factTA, factLL.
The default is pcfgLB,depDA,factLB,factTA. You need to negate those
ones out (e.g.,
-evals "depDA=false"
) if you don't want
them.
LB = ParseEval labeled bracketing,
CB = crossing brackets and zero crossing bracket rate,
DA = dependency accuracy, TA = tagging accuracy,
LL = log likelihood score,
RUO/CUO = rules/categories under and over proposed,
CatE = evaluation by phrasal category.
Known styles are: runningAverages, summary, tsv.
The default style is summary.
You need to negate it out if you don't want it.
Invalid names in the argument to this option are not reported!
fastFactoredCandidateMultiplier
int fastFactoredCandidateMultiplier
- This variable says to find k good fast factored parses, how many times
k of the best PCFG parses should be examined.
fastFactoredCandidateAddend
int fastFactoredCandidateAddend
- This variable says to find k good factored parses, how many added on
best PCFG parses should be examined.
useLexiconToScoreDependencyPwGt
boolean useLexiconToScoreDependencyPwGt
- If this is true, the Lexicon is used to score P(w|t) in the backoff inside the
dependency grammar. (Otherwise, a MLE is used is w is seen, and a constant if
w is unseen.
useNonProjectiveDependencyParser
boolean useNonProjectiveDependencyParser
- If this is true, perform non-projective dependency parsing.
serialVersionUID: 72571349843538L
trainTreeFile
String trainTreeFile
trainLengthLimit
int trainLengthLimit
cheatPCFG
boolean cheatPCFG
- Add all test set trees to training data for PCFG.
(Currently only supported in FactoredParser main.)
markovFactor
boolean markovFactor
- Whether to do "horizontal Markovization" (as in ACL 2003 paper).
False means regular PCFG expansions.
markovOrder
int markovOrder
hSelSplit
boolean hSelSplit
HSEL_CUT
int HSEL_CUT
markFinalStates
boolean markFinalStates
- Whether or not to mark final states in binarized grammar.
This must be off to get most value out of grammar compaction.
openClassTypesThreshold
int openClassTypesThreshold
- A POS tag has to have been attributed to more than this number of word
types before it is regarded as an open-class tag. Unknown words will
only possibly be tagged as open-class tags (unless flexiTag is on).
If flexiTag is on, unknown words will be able to be tagged any POS for
which the unseenMap has nonzero count (that is, the tag was seen for
a new word after unseen signature counting was started).
fractionBeforeUnseenCounting
double fractionBeforeUnseenCounting
- Start to aggregate signature-tag pairs only for words unseen in the first
this fraction of the data.
PA
boolean PA
- This variable controls doing parent annotation of phrasal nodes. Good.
gPA
boolean gPA
- This variable controls doing 2 levels of parent annotation. Bad.
postPA
boolean postPA
postGPA
boolean postGPA
selectiveSplit
boolean selectiveSplit
- Only split the "common high KL divergence" parent categories.... Good.
selectiveSplitCutOff
double selectiveSplitCutOff
selectivePostSplit
boolean selectivePostSplit
selectivePostSplitCutOff
double selectivePostSplitCutOff
postSplitWithBaseCategory
boolean postSplitWithBaseCategory
- Whether, in post-splitting of categories, nodes are annotated with the
(grand)parent's base category or with its complete subcategorized
category.
sisterAnnotate
boolean sisterAnnotate
- Selective Sister annotation.
sisterSplitters
Set<E> sisterSplitters
markUnary
int markUnary
- Mark all unary nodes specially. Good for just PCFG. Bad for factored.
markUnary affects phrasal nodes. A value of 0 means to do nothing;
a value of 1 means to mark the parent (higher) node of a unary rewrite.
A value of 2 means to mark the child (lower) node of a unary rewrie.
Values of 1 and 2 only apply if the child (lower) node is phrasal.
(A value of 1 is better than 2 in combos.) A value of 1 corresponds
to the old boolean -unary flag.
markUnaryTags
boolean markUnaryTags
- Mark POS tags which are the sole member of their phrasal constituent.
This is like markUnary=2, applied to POS tags.
splitPrePreT
boolean splitPrePreT
- Mark all pre-preterminals (also does splitBaseNP: don't need both)
tagPA
boolean tagPA
- Parent annotation on tags. Good (for PCFG?)
tagSelectiveSplit
boolean tagSelectiveSplit
- Do parent annotation on tags selectively. Neutral, but less splits.
tagSelectiveSplitCutOff
double tagSelectiveSplitCutOff
tagSelectivePostSplit
boolean tagSelectivePostSplit
tagSelectivePostSplitCutOff
double tagSelectivePostSplitCutOff
rightRec
boolean rightRec
- Right edge is right-recursive (X << X) Bad. (NP only is good)
leftRec
boolean leftRec
- Left edge is right-recursive (X << X) Bad.
collinsPunc
boolean collinsPunc
- Promote/delete punctuation like Collins. Bad (!)
splitters
Set<E> splitters
- Set the splitter strings. These are a set of parent and/or grandparent
annotated categories which should be split off.
postSplitters
Set<E> postSplitters
deleteSplitters
Set<E> deleteSplitters
printTreeTransformations
int printTreeTransformations
- Just for debugging: check that your tree transforms work correctly. This
will print the transformations of the first printTreeTransformations trees.
printAnnotatedPW
PrintWriter printAnnotatedPW
printBinarizedPW
PrintWriter printBinarizedPW
printStates
boolean printStates
compactGrammar
int compactGrammar
- How to compact grammars as FSMs.
0 = no compaction [uses makeSyntheticLabel1],
1 = no compaction but use label names that wrap from right to left in binarization [uses makeSyntheticLabel2],
2 = wrapping labels and materialize unary at top rewriting passive to active,
3 = ExactGrammarCompactor,
4 = LossyGrammarCompactor,
5 = CategoryMergingGrammarCompactor.
(May 2007 CDM note: options 4 and 5 don't seem to be functioning sensibly. 0, 1, and 3
seem to be the 'good' options. 2 is only useful as input to 3. There seems to be
no reason not to use 0, despite the default.)
leftToRight
boolean leftToRight
noTagSplit
boolean noTagSplit
ruleSmoothing
boolean ruleSmoothing
- Enables linear rule smoothing during grammar extraction
but before grammar compaction. The alpha term is the same
as that described in Petrov et al. (2006), and has range [0,1].
ruleSmoothingAlpha
double ruleSmoothingAlpha
smoothing
boolean smoothing
- TODO wsg2011: This is the old grammar smoothing parameter that no
longer does anything in the parser. It should be removed.
ruleDiscount
double ruleDiscount
- Discounts the count of BinaryRule's (only, apparently) in training data.
printAnnotatedRuleCounts
boolean printAnnotatedRuleCounts
printAnnotatedStateCounts
boolean printAnnotatedStateCounts
basicCategoryTagsInDependencyGrammar
boolean basicCategoryTagsInDependencyGrammar
- Where to use the basic or split tags in the dependency grammar
serialVersionUID: 7303189408025355170L
hf
HeadFinder hf
nodeCleanup
int nodeCleanup
markKonjParent
boolean markKonjParent
markContainsV
boolean markContainsV
markZu
boolean markZu
markColons
boolean markColons
leftPhrasal
boolean leftPhrasal
markHDParent
boolean markHDParent
leaveGF
boolean leaveGF
Class edu.stanford.nlp.parser.lexparser.UnaryGrammar extends Object implements Serializable |
serialVersionUID: 1L
readObject
private void readObject(ObjectInputStream arg0)
throws IOException,
ClassNotFoundException
- Throws:
IOException
ClassNotFoundException
index
Index<E> index
coreRules
Map<K,V> coreRules
Class edu.stanford.nlp.parser.lexparser.UnaryRule extends Object implements Serializable |
serialVersionUID: 1L
parent
int parent
score
float score
child
int child
Package edu.stanford.nlp.pipeline |
serialVersionUID: 1L
Class edu.stanford.nlp.pipeline.CorefMentionFinder.CorefMentionFinderException extends RuntimeException implements Serializable |
serialVersionUID: -4043332236723982286L
Class edu.stanford.nlp.pipeline.PersonInfo extends Object implements Serializable |
serialVersionUID: -6528136000766288840L
gender
String gender
firstName
String firstName
lastName
String lastName
Package edu.stanford.nlp.process |
Class edu.stanford.nlp.process.BadPunctuationTokenizationFixer extends Object implements Serializable |
serialVersionUID: -6771080630746364974L
pattern
Pattern[] pattern
Class edu.stanford.nlp.process.CapitalFeature extends Object implements Serializable |
serialVersionUID: 8673609728403992572L
CAPITALIZED
edu.stanford.nlp.process.CapitalFeature.CapitalFeatureValue CAPITALIZED
ALLCAPS
edu.stanford.nlp.process.CapitalFeature.CapitalFeatureValue ALLCAPS
LOWERCASE
edu.stanford.nlp.process.CapitalFeature.CapitalFeatureValue LOWERCASE
MIXEDCASE
edu.stanford.nlp.process.CapitalFeature.CapitalFeatureValue MIXEDCASE
NONLETTERS
edu.stanford.nlp.process.CapitalFeature.CapitalFeatureValue NONLETTERS
allValues
edu.stanford.nlp.process.CapitalFeature.CapitalFeatureValue[] allValues
Class edu.stanford.nlp.process.CapitalFeature.CapitalFeatureValue extends Object implements Serializable |
serialVersionUID: -5772396359064803302L
val
int val
Class edu.stanford.nlp.process.ChineseDocumentToSentenceProcessor extends Object implements Serializable |
serialVersionUID: 4054964767812217460L
encoding
String encoding
normalizationTable
List<E> normalizationTable
serialVersionUID: 4L
addIndices
boolean addIndices
Class edu.stanford.nlp.process.DistSimClassifier extends Object implements Serializable |
serialVersionUID: 3L
lexicon
Map<K,V> lexicon
cased
boolean cased
numberEquivalence
boolean numberEquivalence
unknownWordClass
String unknownWordClass
Class edu.stanford.nlp.process.NumAndCapFeature extends Object implements Serializable |
serialVersionUID: 276346155803559010L
allValues
edu.stanford.nlp.process.NumAndCapFeatureValue[] allValues
cf
edu.stanford.nlp.process.CapitalFeature cf
nf
edu.stanford.nlp.process.NumberFeature nf
Class edu.stanford.nlp.process.NumberFeature extends Object implements Serializable |
serialVersionUID: -7214323781757946666L
CARDINAL
edu.stanford.nlp.process.NumberFeatureValue CARDINAL
NUMBER
edu.stanford.nlp.process.NumberFeatureValue NUMBER
HASNUMBER
edu.stanford.nlp.process.NumberFeatureValue HASNUMBER
NONUMBER
edu.stanford.nlp.process.NumberFeatureValue NONUMBER
allValues
edu.stanford.nlp.process.NumberFeatureValue[] allValues
Class edu.stanford.nlp.process.WNComboFilter extends Object implements Serializable |
serialVersionUID: 3858847447423637259L
filters
danbikel.wordnet.Filter[] filters
Package edu.stanford.nlp.sequences |
Class edu.stanford.nlp.sequences.BBNReaderAndWriter extends Object implements Serializable |
serialVersionUID: 2772440315252998258L
flags
SeqClassifierFlags flags
fileNum
int fileNum
serialVersionUID: -8109637472035159453L
readResolve
protected Object readResolve()
relativeIndices
int[] relativeIndices
hashCode
int hashCode
Class edu.stanford.nlp.sequences.CliqueDataset extends Object implements Serializable |
serialVersionUID: -2162643681374762273L
features
edu.stanford.nlp.sequences.CliqueDatum[] features
labels
int[] labels
possibleLabels
int[][] possibleLabels
maxCliqueLabels
edu.stanford.nlp.sequences.LabeledClique[] maxCliqueLabels
sourceDoc
List<E> sourceDoc
timitMap
Map<K,V> timitMap
a
int a
b
int b
cacheMaxCliqueLabels
boolean cacheMaxCliqueLabels
maxCliqueLabelsCache
List<E> maxCliqueLabelsCache
maxCliqueConditionalLabelsCache
Map<K,V> maxCliqueConditionalLabelsCache
Class edu.stanford.nlp.sequences.CMMFactory extends Object implements Serializable |
serialVersionUID: 7698629370427133778L
Class edu.stanford.nlp.sequences.CMUSeminarDataReaderAndWriter extends Object implements Serializable |
serialVersionUID: 755129769613443451L
flags
SeqClassifierFlags flags
predModel
edu.stanford.nlp.sequences.SequenceClassifier predModel
serialVersionUID: 3806263423697973704L
map
String[] map
factory
IteratorFromReaderFactory<T> factory
num
int num
Class edu.stanford.nlp.sequences.ColumnTabDocumentReaderWriter extends Object implements Serializable |
serialVersionUID: 1L
map
String[] map
delimiterPattern
Pattern delimiterPattern
whitespacePattern
Pattern whitespacePattern
replaceWhitespace
boolean replaceWhitespace
tokensAnnotationClassName
String tokensAnnotationClassName
tokenFactory
CoreTokenFactory<IN extends CoreMap> tokenFactory
Class edu.stanford.nlp.sequences.ComboFeatureFactory extends edu.stanford.nlp.sequences.Type2FeatureFactory<CoreLabel> implements Serializable |
serialVersionUID: -5170995585456062462L
readResolve
protected Object readResolve()
comboProps
List<E> comboProps
metaInfo
edu.stanford.nlp.sequences.DatasetMetaInfo metaInfo
serialVersionUID: 6281374154299530460L
flags
SeqClassifierFlags flags
Class edu.stanford.nlp.sequences.CRF extends edu.stanford.nlp.sequences.AbstractQueriableSequenceModel implements Serializable |
serialVersionUID: -6958556380850043338L
weights
double[] weights
factors
double[][] factors
cliqueLabels
Index<E>[] cliqueLabels
messageFromLeft
int[][] messageFromLeft
messageFromRight
int[][] messageFromRight
toPassMessagesRight
int[][][] toPassMessagesRight
toPassMessagesLeft
int[][][] toPassMessagesLeft
messageLabels
Index<E>[] messageLabels
condProbs
double[][] condProbs
weightsScale
double weightsScale
memorySave
boolean memorySave
Class edu.stanford.nlp.sequences.CRFFactory extends Object implements Serializable |
serialVersionUID: -7596221713774004331L
Class edu.stanford.nlp.sequences.DatasetMetaInfo extends Object implements Serializable |
serialVersionUID: 3837195914761840458L
labelIndex
HashIndex<E> labelIndex
featureIndex
HashIndex<E> featureIndex
backgroundIndex
int backgroundIndex
featureFactory
edu.stanford.nlp.sequences.Type2FeatureFactory<IN> featureFactory
maxClique
Clique maxClique
allowedSequences
Collection<E> allowedSequences
fm
edu.stanford.nlp.sequences.FeatureMap fm
featureIndexFile
File featureIndexFile
numFeatures
int numFeatures
locked
boolean locked
Class edu.stanford.nlp.sequences.DialogFeatureFactory extends FeatureFactory<IN extends CoreLabel> implements Serializable |
serialVersionUID: -4417769187415417226L
wordsToIgnore
Set<E> wordsToIgnore
serialVersionUID: 7249250071983091694L
flags
SeqClassifierFlags flags
Class edu.stanford.nlp.sequences.FeatureFactoryWrapper extends edu.stanford.nlp.sequences.Type2FeatureFactory<IN extends CoreLabel> implements Serializable |
serialVersionUID: -2370420062000889441L
wrapped
FeatureFactory<IN> wrapped
cache
Map<K,V> cache
position
int position
Class edu.stanford.nlp.sequences.FeatureFactoryWrapper.ImmutablePairOfImmutables extends Pair<F,S> implements Serializable |
serialVersionUID: 3145321753043003608L
readResolve
protected Object readResolve()
hashCode
int hashCode
Class edu.stanford.nlp.sequences.FeatureMap extends Object implements Serializable |
serialVersionUID: 3160710775400396861L
metaInfo
edu.stanford.nlp.sequences.DatasetMetaInfo metaInfo
slowMap
List<E> slowMap
lcIndex
HashIndex<E> lcIndex
fastMap
int[][] fastMap
keySet
Set<E> keySet
Class edu.stanford.nlp.sequences.GazFeatureFactory extends FeatureFactory<IN extends CoreLabel> implements Serializable |
serialVersionUID: -8510805196161524401L
readObject
private void readObject(ObjectInputStream arg0)
throws IOException,
ClassNotFoundException
- Throws:
IOException
ClassNotFoundException
writeObject
private void writeObject(ObjectOutputStream arg0)
throws IOException
- Throws:
IOException
gazMap
CollectionValuedMap<K,V> gazMap
gazNames
Collection<E> gazNames
Class edu.stanford.nlp.sequences.GazNERFeatureFactory extends edu.stanford.nlp.sequences.RVFFeatureFactory<IN extends CoreLabel> implements Serializable |
serialVersionUID: 9051266323822366578L
otherFeatureFactory
FeatureFactory<IN> otherFeatureFactory
Class edu.stanford.nlp.sequences.GlobalDatasetParams extends Object implements Serializable |
serialVersionUID: -5292341676650354270L
metaInfo
edu.stanford.nlp.sequences.DatasetMetaInfo metaInfo
flags
SeqClassifierFlags flags
timitFeatureMap
Map<K,V> timitFeatureMap
Ehat
double[] Ehat
Class edu.stanford.nlp.sequences.IncludeAllFeatureFactory extends edu.stanford.nlp.sequences.RVFFeatureFactory<IN extends CoreLabel> implements Serializable |
serialVersionUID: -8983718938165092707L
Class edu.stanford.nlp.sequences.IOBFeatureFactoryWrapper extends edu.stanford.nlp.sequences.Type2FeatureFactory<CoreLabel> implements Serializable |
serialVersionUID: -893284903284932084L
wrapped
FeatureFactory<IN> wrapped
cache
Map<K,V> cache
labelToString
Map<K,V> labelToString
position
int position
Class edu.stanford.nlp.sequences.IOBFeatureFactoryWrapper.ImmutablePairOfImmutables extends Pair<F,S> implements Serializable |
serialVersionUID: -9137857904295077788L
hashCode
int hashCode
Class edu.stanford.nlp.sequences.LabeledClique extends Object implements Serializable |
serialVersionUID: -311125697888954061L
readResolve
protected Object readResolve()
clique
Clique clique
labels
int[] labels
leftMessage
edu.stanford.nlp.sequences.LabeledClique leftMessage
rightMessage
edu.stanford.nlp.sequences.LabeledClique rightMessage
hashCode
int hashCode
Class edu.stanford.nlp.sequences.LibSVMReaderAndWriter extends Object implements Serializable |
serialVersionUID: -7997837004847909059L
flags
SeqClassifierFlags flags
factory
IteratorFromReaderFactory<T> factory
num
int num
Class edu.stanford.nlp.sequences.MalletFeatureFactory extends FeatureFactory<IN extends CoreLabel> implements Serializable |
serialVersionUID: -5586998916869425417L
Class edu.stanford.nlp.sequences.MalletReaderAndWriter extends Object implements Serializable |
serialVersionUID: 3806263423691913704L
flags
SeqClassifierFlags flags
map
String[] map
factory
IteratorFromReaderFactory<T> factory
num
int num
Class edu.stanford.nlp.sequences.MFCCFeatureFactory extends edu.stanford.nlp.sequences.RVFFeatureFactory<IN extends CoreLabel> implements Serializable |
serialVersionUID: 4927205169837335801L
keys
Class<T>[] keys
Class edu.stanford.nlp.sequences.MUCDocumentReaderAndWriter extends Object implements Serializable |
serialVersionUID: -8334720781758500037L
flags
SeqClassifierFlags flags
factory
IteratorFromReaderFactory<T> factory
serialVersionUID: -3838331732026362075L
flags
SeqClassifierFlags flags
wrapped
ObjectBank<E> wrapped
knownLCWords
Set<E> knownLCWords
monthDayPattern
Pattern monthDayPattern
Class edu.stanford.nlp.sequences.OCRDocumentReaderAndWriter extends Object implements Serializable |
serialVersionUID: 8481207852016988480L
fold
String fold
train
boolean train
serialVersionUID: -2420535144980273136L
wts
WordToSentenceProcessor<IN> wts
flags
SeqClassifierFlags flags
tokenizerFactory
TokenizerFactory<T> tokenizerFactory
tokenFactory
CoreTokenFactory<IN extends CoreMap> tokenFactory
Class edu.stanford.nlp.sequences.QueriableSequenceModelFactory extends Object implements Serializable |
serialVersionUID: 2218714006594152967L
provider
edu.stanford.nlp.sequences.QueriableSequenceModelFactory.QueriableSequenceModelFactoryDataProvider provider
metaInfo
edu.stanford.nlp.sequences.DatasetMetaInfo metaInfo
flags
SeqClassifierFlags flags
weights
double[] weights
hierarchicalWeights
Map<K,V> hierarchicalWeights
answersByDomain
Map<K,V> answersByDomain
Class edu.stanford.nlp.sequences.RVFFeatureFactory extends FeatureFactory<IN> implements Serializable |
serialVersionUID: -5217071654353485387L
serialVersionUID: -7076671761070232567L
stringRep
String stringRep
useNGrams
boolean useNGrams
conjoinShapeNGrams
boolean conjoinShapeNGrams
lowercaseNGrams
boolean lowercaseNGrams
dehyphenateNGrams
boolean dehyphenateNGrams
usePrev
boolean usePrev
useNext
boolean useNext
useTags
boolean useTags
useWordPairs
boolean useWordPairs
useGazettes
boolean useGazettes
useSequences
boolean useSequences
usePrevSequences
boolean usePrevSequences
useNextSequences
boolean useNextSequences
useLongSequences
boolean useLongSequences
useBoundarySequences
boolean useBoundarySequences
useTaggySequences
boolean useTaggySequences
useExtraTaggySequences
boolean useExtraTaggySequences
dontExtendTaggy
boolean dontExtendTaggy
useTaggySequencesShapeInteraction
boolean useTaggySequencesShapeInteraction
strictlyZeroethOrder
boolean strictlyZeroethOrder
strictlyFirstOrder
boolean strictlyFirstOrder
strictlySecondOrder
boolean strictlySecondOrder
strictlyThirdOrder
boolean strictlyThirdOrder
entitySubclassification
String entitySubclassification
retainEntitySubclassification
boolean retainEntitySubclassification
useGazettePhrases
boolean useGazettePhrases
makeConsistent
boolean makeConsistent
useWordLabelCounts
boolean useWordLabelCounts
useViterbi
boolean useViterbi
binnedLengths
int[] binnedLengths
verboseMode
boolean verboseMode
useSum
boolean useSum
tolerance
double tolerance
printFeatures
String printFeatures
useSymTags
boolean useSymTags
useSymWordPairs
boolean useSymWordPairs
- useSymWordPairs Has a small negative effect.
printClassifier
String printClassifier
printClassifierParam
int printClassifierParam
intern
boolean intern
intern2
boolean intern2
selfTest
boolean selfTest
sloppyGazette
boolean sloppyGazette
cleanGazette
boolean cleanGazette
noMidNGrams
boolean noMidNGrams
maxNGramLeng
int maxNGramLeng
useReverse
boolean useReverse
greekifyNGrams
boolean greekifyNGrams
useParenMatching
boolean useParenMatching
useLemmas
boolean useLemmas
usePrevNextLemmas
boolean usePrevNextLemmas
normalizeTerms
boolean normalizeTerms
normalizeTimex
boolean normalizeTimex
useNB
boolean useNB
useQN
boolean useQN
useFloat
boolean useFloat
QNsize
int QNsize
QNsize2
int QNsize2
maxIterations
int maxIterations
wordShape
int wordShape
useShapeStrings
boolean useShapeStrings
useTypeSeqs
boolean useTypeSeqs
useTypeSeqs2
boolean useTypeSeqs2
useTypeSeqs3
boolean useTypeSeqs3
useDisjunctive
boolean useDisjunctive
disjunctionWidth
int disjunctionWidth
useDisjunctiveShapeInteraction
boolean useDisjunctiveShapeInteraction
useDisjShape
boolean useDisjShape
useWord
boolean useWord
useClassFeature
boolean useClassFeature
useShapeConjunctions
boolean useShapeConjunctions
useWordTag
boolean useWordTag
useNPHead
boolean useNPHead
useNPGovernor
boolean useNPGovernor
useHeadGov
boolean useHeadGov
useLastRealWord
boolean useLastRealWord
useNextRealWord
boolean useNextRealWord
useOccurrencePatterns
boolean useOccurrencePatterns
useTypeySequences
boolean useTypeySequences
justify
boolean justify
normalize
boolean normalize
priorType
String priorType
sigma
double sigma
epsilon
double epsilon
beamSize
int beamSize
maxLeft
int maxLeft
maxRight
int maxRight
usePosition
boolean usePosition
useBeginSent
boolean useBeginSent
useGazFeatures
boolean useGazFeatures
useMoreGazFeatures
boolean useMoreGazFeatures
useAbbr
boolean useAbbr
useMinimalAbbr
boolean useMinimalAbbr
useAbbr1
boolean useAbbr1
useMinimalAbbr1
boolean useMinimalAbbr1
useMoreAbbr
boolean useMoreAbbr
deleteBlankLines
boolean deleteBlankLines
useGENIA
boolean useGENIA
useTOK
boolean useTOK
useABSTR
boolean useABSTR
useABSTRFreqDict
boolean useABSTRFreqDict
useABSTRFreq
boolean useABSTRFreq
useFREQ
boolean useFREQ
useABGENE
boolean useABGENE
useWEB
boolean useWEB
useWEBFreqDict
boolean useWEBFreqDict
useIsURL
boolean useIsURL
useURLSequences
boolean useURLSequences
useIsDateRange
boolean useIsDateRange
useEntityTypes
boolean useEntityTypes
useEntityTypeSequences
boolean useEntityTypeSequences
useEntityRule
boolean useEntityRule
useOrdinal
boolean useOrdinal
useACR
boolean useACR
useANTE
boolean useANTE
useMoreTags
boolean useMoreTags
useChunks
boolean useChunks
useChunkySequences
boolean useChunkySequences
usePrevVB
boolean usePrevVB
useNextVB
boolean useNextVB
useVB
boolean useVB
subCWGaz
boolean subCWGaz
documentReader
String documentReader
map
String map
useWideDisjunctive
boolean useWideDisjunctive
wideDisjunctionWidth
int wideDisjunctionWidth
useRadical
boolean useRadical
useBigramInTwoClique
boolean useBigramInTwoClique
morphFeatureFile
String morphFeatureFile
useReverseAffix
boolean useReverseAffix
charHalfWindow
int charHalfWindow
useWord1
boolean useWord1
useWord2
boolean useWord2
useWord3
boolean useWord3
useWord4
boolean useWord4
useRad1
boolean useRad1
useRad2
boolean useRad2
useWordn
boolean useWordn
useCTBPre1
boolean useCTBPre1
useCTBSuf1
boolean useCTBSuf1
useASBCPre1
boolean useASBCPre1
useASBCSuf1
boolean useASBCSuf1
usePKPre1
boolean usePKPre1
usePKSuf1
boolean usePKSuf1
useHKPre1
boolean useHKPre1
useHKSuf1
boolean useHKSuf1
useCTBChar2
boolean useCTBChar2
useASBCChar2
boolean useASBCChar2
useHKChar2
boolean useHKChar2
usePKChar2
boolean usePKChar2
useRule2
boolean useRule2
useDict2
boolean useDict2
useOutDict2
boolean useOutDict2
outDict2
String outDict2
useDictleng
boolean useDictleng
useDictCTB2
boolean useDictCTB2
useDictASBC2
boolean useDictASBC2
useDictPK2
boolean useDictPK2
useDictHK2
boolean useDictHK2
useBig5
boolean useBig5
useNegDict2
boolean useNegDict2
useNegDict3
boolean useNegDict3
useNegDict4
boolean useNegDict4
useNegCTBDict2
boolean useNegCTBDict2
useNegCTBDict3
boolean useNegCTBDict3
useNegCTBDict4
boolean useNegCTBDict4
useNegASBCDict2
boolean useNegASBCDict2
useNegASBCDict3
boolean useNegASBCDict3
useNegASBCDict4
boolean useNegASBCDict4
useNegHKDict2
boolean useNegHKDict2
useNegHKDict3
boolean useNegHKDict3
useNegHKDict4
boolean useNegHKDict4
useNegPKDict2
boolean useNegPKDict2
useNegPKDict3
boolean useNegPKDict3
useNegPKDict4
boolean useNegPKDict4
usePre
boolean usePre
useSuf
boolean useSuf
useRule
boolean useRule
useHk
boolean useHk
useMsr
boolean useMsr
useMSRChar2
boolean useMSRChar2
usePk
boolean usePk
useAs
boolean useAs
useFilter
boolean useFilter
largeChSegFile
boolean largeChSegFile
useRad2b
boolean useRad2b
keepEnglishWhitespaces
boolean keepEnglishWhitespaces
- Keep the whitespace between English words in testFile when printing out
answers. Doesn't really change the content of the CoreLabels. (For Chinese
segmentation.)
keepAllWhitespaces
boolean keepAllWhitespaces
- Keep all the whitespace words in testFile when printing out answers.
Doesn't really change the content of the CoreLabels. (For Chinese
segmentation.)
sighanPostProcessing
boolean sighanPostProcessing
useChPos
boolean useChPos
- use POS information (an "open" feature for Chinese segmentation)
normalizationTable
String normalizationTable
dictionary
String dictionary
serializedDictionary
String serializedDictionary
dictionary2
String dictionary2
normTableEncoding
String normTableEncoding
sighanCorporaDict
String sighanCorporaDict
- for Sighan bakeoff 2005, the path to the dictionary of bigrams appeared in
corpus
useWordShapeGaz
boolean useWordShapeGaz
wordShapeGaz
String wordShapeGaz
splitDocuments
boolean splitDocuments
printXML
boolean printXML
useSeenFeaturesOnly
boolean useSeenFeaturesOnly
lastNameList
String lastNameList
maleNameList
String maleNameList
femaleNameList
String femaleNameList
inputEncoding
String inputEncoding
bioSubmitOutput
boolean bioSubmitOutput
numRuns
int numRuns
answerFile
String answerFile
altAnswerFile
String altAnswerFile
dropGaz
String dropGaz
printGazFeatures
String printGazFeatures
numStartLayers
int numStartLayers
dump
boolean dump
mergeTags
boolean mergeTags
splitOnHead
boolean splitOnHead
featureCountThreshold
int featureCountThreshold
featureWeightThreshold
double featureWeightThreshold
featureFactory
String featureFactory
backgroundSymbol
String backgroundSymbol
useObservedSequencesOnly
boolean useObservedSequencesOnly
maxDocSize
int maxDocSize
printProbs
boolean printProbs
printFirstOrderProbs
boolean printFirstOrderProbs
saveFeatureIndexToDisk
boolean saveFeatureIndexToDisk
removeBackgroundSingletonFeatures
boolean removeBackgroundSingletonFeatures
doGibbs
boolean doGibbs
numSamples
int numSamples
useNERPrior
boolean useNERPrior
useAcqPrior
boolean useAcqPrior
useUniformPrior
boolean useUniformPrior
- If true and doGibbs also true, will do generic Gibbs inference without any
priors
useMUCFeatures
boolean useMUCFeatures
annealingRate
double annealingRate
annealingType
String annealingType
loadProcessedData
String loadProcessedData
initViterbi
boolean initViterbi
useUnknown
boolean useUnknown
checkNameList
boolean checkNameList
useSemPrior
boolean useSemPrior
useFirstWord
boolean useFirstWord
useNumberFeature
boolean useNumberFeature
ocrFold
int ocrFold
classifierType
String classifierType
svmModelFile
String svmModelFile
inferenceType
String inferenceType
useLemmaAsWord
boolean useLemmaAsWord
type
String type
readerAndWriter
String readerAndWriter
comboProps
List<E> comboProps
usePrediction
boolean usePrediction
useAltGazFeatures
boolean useAltGazFeatures
gazFilesFile
String gazFilesFile
usePrediction2
boolean usePrediction2
baseTrainDir
String baseTrainDir
baseTestDir
String baseTestDir
trainFiles
String trainFiles
trainFileList
String trainFileList
testFiles
String testFiles
trainDirs
String trainDirs
testDirs
String testDirs
useOnlySeenWeights
boolean useOnlySeenWeights
predProp
String predProp
pad
CoreLabel pad
useObservedFeaturesOnly
boolean useObservedFeaturesOnly
distSimLexicon
String distSimLexicon
useDistSim
boolean useDistSim
removeTopN
int removeTopN
numTimesRemoveTopN
int numTimesRemoveTopN
randomizedRatio
double randomizedRatio
removeTopNPercent
double removeTopNPercent
purgeFeatures
int purgeFeatures
booleanFeatures
boolean booleanFeatures
iobWrapper
boolean iobWrapper
iobTags
boolean iobTags
useSegmentation
boolean useSegmentation
memoryThrift
boolean memoryThrift
timitDatum
boolean timitDatum
serializeDatasetsDir
String serializeDatasetsDir
loadDatasetsDir
String loadDatasetsDir
pushDir
String pushDir
purgeDatasets
boolean purgeDatasets
keepOBInMemory
boolean keepOBInMemory
fakeDataset
boolean fakeDataset
restrictTransitionsTimit
boolean restrictTransitionsTimit
numDatasetsPerFile
int numDatasetsPerFile
useTitle
boolean useTitle
lowerNewgeneThreshold
boolean lowerNewgeneThreshold
useEitherSideWord
boolean useEitherSideWord
useEitherSideDisjunctive
boolean useEitherSideDisjunctive
twoStage
boolean twoStage
crfType
String crfType
featureThreshold
int featureThreshold
featThreshFile
String featThreshFile
featureDiffThresh
double featureDiffThresh
numTimesPruneFeatures
int numTimesPruneFeatures
newgeneThreshold
double newgeneThreshold
doAdaptation
boolean doAdaptation
useInternal
boolean useInternal
useExternal
boolean useExternal
selfTrainConfidenceThreshold
double selfTrainConfidenceThreshold
selfTrainIterations
int selfTrainIterations
selfTrainWindowSize
int selfTrainWindowSize
useHuber
boolean useHuber
useQuartic
boolean useQuartic
adaptSigma
double adaptSigma
numFolds
int numFolds
startFold
int startFold
endFold
int endFold
cacheNGrams
boolean cacheNGrams
outputFormat
String outputFormat
useSMD
boolean useSMD
useSGDtoQN
boolean useSGDtoQN
useStochasticQN
boolean useStochasticQN
useScaledSGD
boolean useScaledSGD
scaledSGDMethod
int scaledSGDMethod
SGDPasses
int SGDPasses
QNPasses
int QNPasses
tuneSGD
boolean tuneSGD
stochasticMethod
StochasticCalculateMethods stochasticMethod
initialGain
double initialGain
stochasticBatchSize
int stochasticBatchSize
useSGD
boolean useSGD
gainSGD
double gainSGD
useHybrid
boolean useHybrid
hybridCutoffIteration
int hybridCutoffIteration
outputIterationsToFile
boolean outputIterationsToFile
testObjFunction
boolean testObjFunction
testVariance
boolean testVariance
SGD2QNhessSamples
int SGD2QNhessSamples
testHessSamples
boolean testHessSamples
CRForder
int CRForder
CRFwindow
int CRFwindow
estimateInitial
boolean estimateInitial
outputEncoding
String outputEncoding
useKBest
boolean useKBest
searchGraphPrefix
String searchGraphPrefix
searchGraphPrune
double searchGraphPrune
kBest
int kBest
useFeaturesC4gram
boolean useFeaturesC4gram
useFeaturesC5gram
boolean useFeaturesC5gram
useFeaturesC6gram
boolean useFeaturesC6gram
useFeaturesCpC4gram
boolean useFeaturesCpC4gram
useFeaturesCpC5gram
boolean useFeaturesCpC5gram
useFeaturesCpC6gram
boolean useFeaturesCpC6gram
useUnicodeType
boolean useUnicodeType
useUnicodeType4gram
boolean useUnicodeType4gram
useUnicodeType5gram
boolean useUnicodeType5gram
use4Clique
boolean use4Clique
useUnicodeBlock
boolean useUnicodeBlock
useShapeStrings1
boolean useShapeStrings1
useShapeStrings3
boolean useShapeStrings3
useShapeStrings4
boolean useShapeStrings4
useShapeStrings5
boolean useShapeStrings5
useGoodForNamesCpC
boolean useGoodForNamesCpC
useDictionaryConjunctions
boolean useDictionaryConjunctions
expandMidDot
boolean expandMidDot
printFeaturesUpto
int printFeaturesUpto
useDictionaryConjunctions3
boolean useDictionaryConjunctions3
useWordUTypeConjunctions2
boolean useWordUTypeConjunctions2
useWordUTypeConjunctions3
boolean useWordUTypeConjunctions3
useWordShapeConjunctions2
boolean useWordShapeConjunctions2
useWordShapeConjunctions3
boolean useWordShapeConjunctions3
useMidDotShape
boolean useMidDotShape
augmentedDateChars
boolean augmentedDateChars
suppressMidDotPostprocessing
boolean suppressMidDotPostprocessing
printNR
boolean printNR
classBias
String classBias
printLabelValue
boolean printLabelValue
useRobustQN
boolean useRobustQN
combo
boolean combo
useGenericFeatures
boolean useGenericFeatures
verboseForTrueCasing
boolean verboseForTrueCasing
trainHierarchical
String trainHierarchical
domain
String domain
baseline
boolean baseline
transferSigmas
String transferSigmas
doFE
boolean doFE
restrictLabels
boolean restrictLabels
announceObjectBankEntries
boolean announceObjectBankEntries
usePos
boolean usePos
useAgreement
boolean useAgreement
useAccCase
boolean useAccCase
useInna
boolean useInna
useConcord
boolean useConcord
useFirstNgram
boolean useFirstNgram
useLastNgram
boolean useLastNgram
collapseNN
boolean collapseNN
useConjBreak
boolean useConjBreak
useAuxPairs
boolean useAuxPairs
usePPVBPairs
boolean usePPVBPairs
useAnnexing
boolean useAnnexing
useTemporalNN
boolean useTemporalNN
usePath
boolean usePath
innaPPAttach
boolean innaPPAttach
markProperNN
boolean markProperNN
markMasdar
boolean markMasdar
useSVO
boolean useSVO
numTags
int numTags
useTagsCpC
boolean useTagsCpC
useTagsCpCp2C
boolean useTagsCpCp2C
useTagsCpCp2Cp3C
boolean useTagsCpCp2Cp3C
useTagsCpCp2Cp3Cp4C
boolean useTagsCpCp2Cp3Cp4C
l1reg
double l1reg
mixedCaseMapFile
String mixedCaseMapFile
auxTrueCaseModels
String auxTrueCaseModels
use2W
boolean use2W
useLC
boolean useLC
useYetMoreCpCShapes
boolean useYetMoreCpCShapes
useIfInteger
boolean useIfInteger
exportFeatures
String exportFeatures
useInPlaceSGD
boolean useInPlaceSGD
useTopics
boolean useTopics
evaluateIters
int evaluateIters
evalCmd
String evalCmd
evaluateTrain
boolean evaluateTrain
tuneSampleSize
int tuneSampleSize
usePhraseFeatures
boolean usePhraseFeatures
usePhraseWords
boolean usePhraseWords
usePhraseWordTags
boolean usePhraseWordTags
usePhraseWordSpecialTags
boolean usePhraseWordSpecialTags
useCommonWordsFeature
boolean useCommonWordsFeature
useProtoFeatures
boolean useProtoFeatures
useWordnetFeatures
boolean useWordnetFeatures
tokenFactory
String tokenFactory
tokensAnnotationClassName
String tokensAnnotationClassName
useCorefFeatures
boolean useCorefFeatures
wikiFeatureDbFile
String wikiFeatureDbFile
useNoisyNonNoisyFeature
boolean useNoisyNonNoisyFeature
useYear
boolean useYear
useSentenceNumber
boolean useSentenceNumber
useLabelSource
boolean useLabelSource
casedDistSim
boolean casedDistSim
- Whether to (not) lowercase tokens before looking them up in distsim
lexicon. By default lowercasing was done, but now it doesn't have to be
true :-).
distSimFileFormat
String distSimFileFormat
- The format of the distsim file. Known values are: alexClark = TSV file.
word TAB clusterNumber [optional other content] terryKoo = TSV file.
clusterBitString TAB word TAB frequency
distSimMaxBits
int distSimMaxBits
- If this number is greater than 0, the distSim class is assume to be a bit
string and is truncated at this many characters. Normal distSim features
will then use this amount of resolution. Extra, special distsim features
may work at a coarser level of resolution. Since the lexicon only stores
this length of bit string, there is then no way to have finer-grained
clusters.
numberEquivalenceDistSim
boolean numberEquivalenceDistSim
- If this is set to true, all digit characters get mapped to '9' in a distsim
lexicon and for lookup. This is a simple word shaping that can shrink
distsim lexicons and improve their performance.
unknownWordDistSimClass
String unknownWordDistSimClass
- What class to assign to words not found in the dist sim lexicon. You might
want to make it a known class, if one is the "default class.
useNeighborNGrams
boolean useNeighborNGrams
- Use prefixes and suffixes from the previous and next word.
wordFunction
Function<T1,T2> wordFunction
- This function maps words in the training or test data to new
words. They are used at the feature extractor level, ie in the
FeatureFactory. For now, only the NERFeatureFactory uses this.
Class edu.stanford.nlp.sequences.SimpleComboFeatureFactory extends edu.stanford.nlp.sequences.ComboFeatureFactory implements Serializable |
serialVersionUID: 6124131315339969687L
Class edu.stanford.nlp.sequences.SuperSimpleFeatureFactory extends FeatureFactory<IN extends CoreLabel> implements Serializable |
serialVersionUID: 8482882637052066375L
Class edu.stanford.nlp.sequences.TIMITCliqueDatum extends Object implements Serializable |
serialVersionUID: 1948440233285748714L
keySet
Set<E> keySet
values
float[] values
Class edu.stanford.nlp.sequences.TrueCaserFeatureFactory extends FeatureFactory<IN extends CoreLabel> implements Serializable |
serialVersionUID: -8983718938165092704L
Class edu.stanford.nlp.sequences.TrueCasingForNIST09DocumentReaderAndWriter extends Object implements Serializable |
serialVersionUID: -3000389291781534479L
factory
IteratorFromReaderFactory<T> factory
mixedCaseMap
Map<K,V> mixedCaseMap
Class edu.stanford.nlp.sequences.Type2FeatureFactory extends Object implements Serializable |
serialVersionUID: -1659118594329526572L
flags
SeqClassifierFlags flags
metaInfo
edu.stanford.nlp.sequences.DatasetMetaInfo metaInfo
maxClique
Clique maxClique
Package edu.stanford.nlp.stats |
serialVersionUID: 4L
map
Map<K,V> map
mapFactory
MapFactory<K,V> mapFactory
totalCount
double totalCount
defaultValue
double defaultValue
Class edu.stanford.nlp.stats.DeltaCounter extends ClassicCounter<E> implements Serializable |
serialVersionUID: 2417145091311373088L
Class edu.stanford.nlp.stats.Dirichlet extends Object implements Serializable |
serialVersionUID: 1L
parameters
Counter<E> parameters
Class edu.stanford.nlp.stats.DirichletProcess extends Object implements Serializable |
serialVersionUID: -8653536087199951278L
baseMeasure
ProbabilityDistribution<E> baseMeasure
alpha
double alpha
sampled
ClassicCounter<E> sampled
serialVersionUID: 6707148234288637809L
numberOfKeys
int numberOfKeys
reservedMass
double reservedMass
counter
Counter<E> counter
Class edu.stanford.nlp.stats.Gamma extends Object implements Serializable |
serialVersionUID: -2992079318379176178L
alpha
double alpha
Class edu.stanford.nlp.stats.Gaussian extends Object implements Serializable |
serialVersionUID: 1960411222642524273L
mean
no.uib.cipr.matrix.Vector mean
var
no.uib.cipr.matrix.Matrix var
prec
no.uib.cipr.matrix.Matrix prec
chol
no.uib.cipr.matrix.Matrix chol
Class edu.stanford.nlp.stats.GaussianCovariancePrior extends Object implements Serializable |
serialVersionUID: -3832920718403518986L
var
no.uib.cipr.matrix.Matrix var
df
double df
inner
edu.stanford.nlp.stats.InverseWishart inner
likelihoodMean
no.uib.cipr.matrix.Vector likelihoodMean
Class edu.stanford.nlp.stats.GaussianMeanPrior extends Object implements Serializable |
serialVersionUID: -8056200031494870713L
mean
no.uib.cipr.matrix.Vector mean
var
no.uib.cipr.matrix.Matrix var
precision
no.uib.cipr.matrix.Matrix precision
likelihoodVar
no.uib.cipr.matrix.Matrix likelihoodVar
likePrecision
no.uib.cipr.matrix.Matrix likePrecision
serialVersionUID: 1L
map
Map<K,V> map
depth
int depth
total
double total
serialVersionUID: 4L
map
Map<K,V> map
mapFactory
MapFactory<K,V> mapFactory
totalCount
int totalCount
defaultValue
int defaultValue
Class edu.stanford.nlp.stats.InverseWishart extends Object implements Serializable |
serialVersionUID: -1000464962771645475L
w
edu.stanford.nlp.stats.Wishart w
v
no.uib.cipr.matrix.Matrix v
Class edu.stanford.nlp.stats.Multinomial extends Object implements Serializable |
serialVersionUID: -697457414113362926L
parameters
Counter<E> parameters
hashCode
int hashCode
Class edu.stanford.nlp.stats.OpenAddressCounter extends AbstractCounter<E> implements Serializable |
serialVersionUID: 1L
map
edu.stanford.nlp.stats.OpenAddressCounter.AdjustableObject2DoubleOpenHashMap<F> map
total
double total
serialVersionUID: 1L
map
Map<K,V> map
total
double total
outerMF
MapFactory<K,V> outerMF
innerMF
MapFactory<K,V> innerMF
defaultValue
double defaultValue
Class edu.stanford.nlp.stats.TwoDimensionalIntCounter extends Object implements Serializable |
serialVersionUID: 1L
map
Map<K,V> map
total
int total
outerMF
MapFactory<K,V> outerMF
innerMF
MapFactory<K,V> innerMF
defaultValue
int defaultValue
Class edu.stanford.nlp.stats.Wishart extends Object implements Serializable |
serialVersionUID: -1524540511821287970L
df
double df
v
no.uib.cipr.matrix.Matrix v
l
no.uib.cipr.matrix.Matrix l
lt
no.uib.cipr.matrix.Matrix lt
Package edu.stanford.nlp.trees |
serialVersionUID: -6540278059442931087L
tlp
TreebankLanguagePack tlp
nonTerminalInfo
Map<K,V> nonTerminalInfo
defaultRule
String[] defaultRule
- Default direction if no rule is found for category.
Subclasses can turn it on if they like.
If they don't it is an error if no rule is defined for a category
(null is returned).
defaultLeftRule
String[] defaultLeftRule
- These are built automatically from categoriesToAvoid and used in a fairly
different fashion from defaultRule (above). These are used for categories
that do have defined rules but where none of them have matched. Rather
than picking the rightmost or leftmost child, we will use these to pick
the the rightmost or leftmost child which isn't in categoriesToAvoid.
defaultRightRule
String[] defaultRightRule
serialVersionUID: -6506749780512708352L
gfCharacter
char gfCharacter
- Default character for indicating that something is a grammatical fn; probably should be overridden by
lang specific ones
punctTagStringAcceptFilter
Filter<T> punctTagStringAcceptFilter
punctWordStringAcceptFilter
Filter<T> punctWordStringAcceptFilter
sFPunctTagStringAcceptFilter
Filter<T> sFPunctTagStringAcceptFilter
eIPunctTagStringAcceptFilter
Filter<T> eIPunctTagStringAcceptFilter
startSymbolAcceptFilter
Filter<T> startSymbolAcceptFilter
serialVersionUID: -1005188028979810143L
tlp
TreebankLanguagePack tlp
emptyFilter
Filter<T> emptyFilter
aOverAFilter
Filter<T> aOverAFilter
serialVersionUID: 1L
serialVersionUID: 8914098359495987617L
Class edu.stanford.nlp.trees.ChelbaHeadFinder extends Object implements Serializable |
serialVersionUID: 714845907365065609L
nonTerminalInfo
HashMap<K,V> nonTerminalInfo
LEFT
Pattern LEFT
RIGHT
Pattern RIGHT
PUNCT
Pattern PUNCT
POS_PUNCT
Pattern POS_PUNCT
Class edu.stanford.nlp.trees.CollinsDependency extends Object implements Serializable |
serialVersionUID: -4236496863919294754L
modifier
CoreLabel modifier
head
CoreLabel head
relation
edu.stanford.nlp.trees.CollinsRelation relation
serialVersionUID: -8747319554557223437L
Class edu.stanford.nlp.trees.DanBobChrisTreeNormalizer extends TreeNormalizer implements Serializable |
serialVersionUID: 2401719826865123880L
serialVersionUID: -7732189363171164852L
tagRejectFilter
Filter<T> tagRejectFilter
serialVersionUID: 1166489968248785287L
wordRejectFilter
Filter<T> wordRejectFilter
serialVersionUID: -1866362375001969402L
Class edu.stanford.nlp.trees.ExplicitHeadFinder extends Object implements Serializable |
serialVersionUID: 1L
Class edu.stanford.nlp.trees.GrammaticalFunctionTreeNormalizer extends TreeNormalizer implements Serializable |
serialVersionUID: -2270472762938163327L
nodeCleanup
int nodeCleanup
root
String root
tlp
TreebankLanguagePack tlp
serialVersionUID: 892618003417550128L
language
GrammaticalRelation.Language language
shortName
String shortName
longName
String longName
parent
GrammaticalRelation parent
children
List<E> children
sourcePattern
Pattern sourcePattern
targetPatterns
List<E> targetPatterns
specific
String specific
serialVersionUID: 2286294455343892678L
dependencies
Set<E> dependencies
typedDependencies
List<E> typedDependencies
allTypedDependencies
List<E> allTypedDependencies
serialVersionUID: -8992385140984593817L
label
Label label
- Label of the parse tree.
score
double score
- Score of
TreeNode
daughterTrees
Tree[] daughterTrees
- Daughters of the parse tree.
Class edu.stanford.nlp.trees.LeftHeadFinder extends Object implements Serializable |
serialVersionUID: 8453889846239508208L
Class edu.stanford.nlp.trees.LengthTreeFilter extends Object implements Serializable |
length
int length
serialVersionUID: 3970059472026730651L
serialVersionUID: -5870387458902637256L
Class edu.stanford.nlp.trees.NamedConcreteDependency extends NamedDependency implements Serializable |
serialVersionUID: 4694393388619235531L
headIndex
int headIndex
depIndex
int depIndex
serialVersionUID: -1635646451505721133L
name
Object name
Class edu.stanford.nlp.trees.NERModCollinsHeadFinder extends ModCollinsHeadFinder implements Serializable |
serialVersionUID: -5870387458902637256L
Class edu.stanford.nlp.trees.NoPunctTreeNormalizer extends TreeNormalizer implements Serializable |
serialVersionUID: -6097556118989005285L
tlp
TreebankLanguagePack tlp
serialVersionUID: 7548777133196579107L
temporalAnnotation
int temporalAnnotation
doSGappedStuff
boolean doSGappedStuff
leaveItAll
int leaveItAll
doAdverbialNP
boolean doAdverbialNP
headFinder
HeadFinder headFinder
Class edu.stanford.nlp.trees.OrderedCombinationTreeNormalizer extends TreeNormalizer implements Serializable |
serialVersionUID: 326L
tns
List<E> tns
Class edu.stanford.nlp.trees.ParametricTreeNormalizer extends TreeNormalizer implements Serializable |
serialVersionUID: 3334729561543903805L
internStrings
boolean internStrings
unquoteStrings
boolean unquoteStrings
Class edu.stanford.nlp.trees.ParentalTreeWrapper extends Tree implements Serializable |
tree
Tree tree
parent
Tree parent
children
Tree[] children
serialVersionUID: 9081305982861675328L
Class edu.stanford.nlp.trees.PruneNodesStripSubtagsTreeNormalizer extends TreeNormalizer implements Serializable |
serialVersionUID: -4140942599350599366L
nodeFilter
Filter<T> nodeFilter
Class edu.stanford.nlp.trees.SbjRetainingTreeNormalizer extends BobChrisTreeNormalizer implements Serializable |
serialVersionUID: 4211724108734555526L
serialVersionUID: 5721799188009249808L
verbalAuxiliaries
HashSet<E> verbalAuxiliaries
copulars
HashSet<E> copulars
passiveAuxiliaries
HashSet<E> passiveAuxiliaries
verbalTags
HashSet<E> verbalTags
serialVersionUID: -8075763706877132926L
daughterTrees
Tree[] daughterTrees
- Daughters of the parse tree.
Class edu.stanford.nlp.trees.TagMapper extends HashMap implements Serializable |
serialVersionUID: 1000854105522440099L
tagMap
HashMap<K,V> tagMap
serialVersionUID: 5441849457648722744L
score
double score
serialVersionUID: 1L
root
TreeGraphNode root
- The root node of this treegraph.
indexMap
Map<K,V> indexMap
- A map from arbitrary integer indices to nodes.
serialVersionUID: 5080098143617475328L
label
CyclicCoreLabel label
- Label for this node.
parent
TreeGraphNode parent
- Parent of this node.
children
TreeGraphNode[] children
- Children of this node.
tg
TreeGraph tg
- The
TreeGraph
of which this
node is part.
serialVersionUID: 1540681875853883387L
serialVersionUID: -7690294213151279779L
reln
GrammaticalRelation reln
gov
TreeGraphNode gov
dep
TreeGraphNode dep
extra
boolean extra
serialVersionUID: -8836949694741145222L
headIndex
int headIndex
depIndex
int depIndex
serialVersionUID: -3768440215342256085L
regentText
String regentText
dependentText
String dependentText
regent
Label regent
dependent
Label dependent
Class edu.stanford.nlp.trees.WeightedFollowedTaggedWord extends TaggedWord implements Serializable |
serialVersionUID: -7600197568995481394L
follow
String follow
weight
double weight
Package edu.stanford.nlp.trees.international.pennchinese |
Class edu.stanford.nlp.trees.international.pennchinese.BikelChineseHeadFinder extends AbstractCollinsHeadFinder implements Serializable |
serialVersionUID: -5445795668059315082L
Class edu.stanford.nlp.trees.international.pennchinese.CharacterLevelTagExtender extends BobChrisTreeNormalizer implements Serializable |
serialVersionUID: 7893996593626523700L
serialVersionUID: 7655332268578049993L
map
Map<K,V> map
normalized
boolean normalized
Class edu.stanford.nlp.trees.international.pennchinese.ChineseGrammaticalStructure extends GrammaticalStructure implements Serializable |
serialVersionUID: 8877651855167458256L
serialVersionUID: 6143632784691159283L
Class edu.stanford.nlp.trees.international.pennchinese.ChineseSemanticHeadFinder extends ChineseHeadFinder implements Serializable |
serialVersionUID: 2L
serialVersionUID: 5757403475523638802L
Class edu.stanford.nlp.trees.international.pennchinese.CTBErrorCorrectingTreeNormalizer extends BobChrisTreeNormalizer implements Serializable |
serialVersionUID: -8203853817025401845L
tagExtender
TreeTransformer tagExtender
splitNPTMP
boolean splitNPTMP
splitPPTMP
boolean splitPPTMP
splitXPTMP
boolean splitXPTMP
chineseEmptyFilter
Filter<T> chineseEmptyFilter
Class edu.stanford.nlp.trees.international.pennchinese.OldChineseHeadFinder extends Object implements Serializable |
serialVersionUID: 6397738771545467067L
tlp
TreebankLanguagePack tlp
nonTerminalInfo
HashMap<K,V> nonTerminalInfo
Class edu.stanford.nlp.trees.international.pennchinese.SunJurafskyChineseHeadFinder extends AbstractCollinsHeadFinder implements Serializable |
serialVersionUID: -7942375587642755210L
Package edu.stanford.nlp.trees.tregex |
serialVersionUID: 1L
currentToken
edu.stanford.nlp.trees.tregex.Token currentToken
- This is the last token that has been consumed successfully. If
this object has been created due to a parse error, the token
followng this token will (therefore) be the first error token.
expectedTokenSequences
int[][] expectedTokenSequences
- Each entry in this array is an array of integers. Each array
of integers represents a sequence of tokens (by their ordinal
values) that is expected at this point of the parse.
tokenImage
String[] tokenImage
- This is a reference to the "tokenImage" array of the generated
parser within which the parse error occurred. This array is
defined in the generated ...Constants interface.
eol
String eol
- The end of line string for this machine.
serialVersionUID: 5060298043763944913L
neg
boolean neg
opt
boolean opt
patternString
String patternString
Package edu.stanford.nlp.trees.tregex.tsurgeon |
serialVersionUID: 1L
currentToken
edu.stanford.nlp.trees.tregex.tsurgeon.Token currentToken
- This is the last token that has been consumed successfully. If
this object has been created due to a parse error, the token
followng this token will (therefore) be the first error token.
expectedTokenSequences
int[][] expectedTokenSequences
- Each entry in this array is an array of integers. Each array
of integers represents a sequence of tokens (by their ordinal
values) that is expected at this point of the parse.
tokenImage
String[] tokenImage
- This is a reference to the "tokenImage" array of the generated
parser within which the parse error occurred. This array is
defined in the generated ...Constants interface.
eol
String eol
- The end of line string for this machine.
Package edu.stanford.nlp.util |
serialVersionUID: 1L
writeObject
private void writeObject(ObjectOutputStream out)
throws IOException
- Overridden serialization method: compacts our map before writing.
- Throws:
IOException
- If IO error
keys
Class<T>[] keys
- Array of keys
values
Object[] values
- Array of values
size
int size
- Total number of elements actually in keys,values
serialVersionUID: 1L
entryArray
edu.stanford.nlp.util.ArrayMap.Entry<K,V>[] entryArray
capacity
int capacity
size
int size
hashCodeCache
int hashCodeCache
Class edu.stanford.nlp.util.CacheMap extends LinkedHashMap<K,V> implements Serializable |
serialVersionUID: 1L
backingFile
String backingFile
CACHE_ENTRIES
int CACHE_ENTRIES
entriesSinceLastWritten
int entriesSinceLastWritten
frequencyToWrite
int frequencyToWrite
hits
int hits
misses
int misses
puts
int puts
serialVersionUID: 3711321773145894069L
serialVersionUID: 1L
serialVersionUID: -6268401669449458602L
serialVersionUID: -4236184979948498000L
serialVersionUID: 1L
defaultSize
int defaultSize
serialVersionUID: -3451920268219478134L
serialVersionUID: -9064664153962599076L
map
Map<K,V> map
cf
CollectionFactory<T> cf
treatCollectionsAsImmutable
boolean treatCollectionsAsImmutable
mf
MapFactory<K,V> mf
emptyValue
Collection<E> emptyValue
- The empty collection to be returned when a
get
doesn't find
the key. The collection returned should be empty, such as
Collections.emptySet, for example.
Class edu.stanford.nlp.util.CompositionMap extends Object implements Serializable |
serialVersionUID: 1L
map
Map<K,V> map
serialVersionUID: 198752987264L
backingMap
ConcurrentHashMap<K,V> backingMap
Class edu.stanford.nlp.util.DefaultValuedMap extends Object implements Serializable |
serialVersionUID: -4333026121894016524L
factory
Factory<T> factory
map
Map<K,V> map
Class edu.stanford.nlp.util.DefaultValuedMap.MapFactory extends Object implements Serializable |
serialVersionUID: 1L
serialVersionUID: 1L
originalMap
CollectionValuedMap<K,V> originalMap
deltaMap
Map<K,V> deltaMap
Class edu.stanford.nlp.util.DeltaIndex extends AbstractCollection<E> implements Serializable |
serialVersionUID: -1459230891686013411L
backingIndex
Index<E> backingIndex
spilloverIndex
Index<E> spilloverIndex
backingIndexSize
int backingIndexSize
locked
boolean locked
Class edu.stanford.nlp.util.FastIndex extends AbstractCollection<E> implements Serializable |
serialVersionUID: 5398562825928375261L
objects
ArrayList<E> objects
indexes
Map<K,V> indexes
locked
boolean locked
Class edu.stanford.nlp.util.FiveDimensionalMap extends Object implements Serializable |
serialVersionUID: 1L
map
Map<K,V> map
serialVersionUID: 1L
size
int size
capacity
int capacity
elements
List<E> elements
priorities
double[] priorities
Class edu.stanford.nlp.util.FourDimensionalMap extends Object implements Serializable |
serialVersionUID: 5635664746940978837L
map
Map<K,V> map
Class edu.stanford.nlp.util.FuzzyInterval extends Interval<E extends edu.stanford.nlp.util.FuzzyInterval.FuzzyComparable<E>> implements Serializable |
serialVersionUID: 1L
immutableKeys
Set<E> immutableKeys
- Set of immutable keys
hashcode
int hashcode
- Pre-computed hashcode
serialVersionUID: 1L
serialVersionUID: 5398562825928375260L
objects
ArrayList<E> objects
indexes
HashMap<K,V> indexes
locked
boolean locked
semaphore
Semaphore semaphore
serialVersionUID: -5024744406713321676L
readObject
private void readObject(ObjectInputStream s)
throws IOException,
ClassNotFoundException
- Deserialize this Object in a manner which is binary-compatible with
the JDK.
- Throws:
IOException
ClassNotFoundException
writeObject
private void writeObject(ObjectOutputStream s)
throws IOException
- Serialize this Object in a manner which is binary-compatible with the
JDK.
- Throws:
IOException
flags
int flags
serialVersionUID: 1L
serialVersionUID: 7154973101012473479L
serialVersionUID: -3744404627253652799L
serialVersionUID: 7266305463893511982L
elements
int[] elements
serialVersionUID: -7182556672628741200L
serialVersionUID: 1L
serialVersionUID: 4529666940763477360L
serialVersionUID: -5980065992461870357L
serialVersionUID: -5980065992461870357L
serialVersionUID: 624465615824626762L
d
double d
serialVersionUID: 624465615824626762L
i
int i
Class edu.stanford.nlp.util.OAIndex extends Object implements Serializable |
serialVersionUID: 127L
identityHash
boolean identityHash
keys
Object[] keys
values
int[] values
mask
int mask
hashCodes
int[] hashCodes
reverseIndex
int[] reverseIndex
maxIndex
int maxIndex
load
int load
serialVersionUID: 2064775966439971729L
l
List<E> l
padding
Object padding
serialVersionUID: 1360822168806852921L
first
Object first
- Direct access is deprecated. Use first().
-
second
Object second
- Direct access is deprecated. Use second().
-
Class edu.stanford.nlp.util.Quadruple extends Object implements Serializable |
serialVersionUID: 6295043666955910662L
first
Object first
second
Object second
third
Object third
fourth
Object fourth
Class edu.stanford.nlp.util.ReversedList extends AbstractList<E> implements Serializable |
serialVersionUID: 206477596643954354L
l
List<E> l
serialVersionUID: 1L
ascending
boolean ascending
Class edu.stanford.nlp.util.ScoredPair extends Pair<T1 extends Comparable<T1>,T2 extends Comparable<T2>> implements Serializable |
serialVersionUID: 1472506164021859706L
score
double score
Class edu.stanford.nlp.util.StringParsingTask.ParserException extends RuntimeException implements Serializable |
serialVersionUID: 1L
serialVersionUID: 1L
Class edu.stanford.nlp.util.ThreeDimensionalCollectionValuedMap extends Object implements Serializable |
serialVersionUID: 1L
map
Map<K,V> map
Class edu.stanford.nlp.util.ThreeDimensionalMap extends Object implements Serializable |
serialVersionUID: 1L
map
Map<K,V> map
serialVersionUID: -4182871682751645440L
first
Object first
second
Object second
third
Object third
Class edu.stanford.nlp.util.TwoDimensionalCollectionValuedMap extends Object implements Serializable |
serialVersionUID: 1L
map
Map<K,V> map
mf
MapFactory<K,V> mf
cf
CollectionFactory<T> cf
treatCollectionsAsImmutable
boolean treatCollectionsAsImmutable
Class edu.stanford.nlp.util.TwoDimensionalMap extends Object implements Serializable |
serialVersionUID: 1L
map
Map<K,V> map
Class edu.stanford.nlp.util.UnorderedPair extends Pair<T1,T2> implements Serializable |
serialVersionUID: 1L
Stanford NLP Group