Serialized Form
Package edu.stanford.nlp.io |
Package edu.stanford.nlp.ling |
title
String title
- title of this document (never null).
originalText
String originalText
- original text of this document (may be null).
labels
List<E> labels
- Label(s) for this document.
tokenizerFactory
TokenizerFactory<T> tokenizerFactory
- TokenizerFactory used to convert the text into words inside
BasicDocument.parse(String)
.
serialVersionUID: -745085381666943254L
word
String word
tag
String tag
serialVersionUID: 2L
serialVersionUID: 1L
serialVersionUID: -7252006452127051085L
tag
Label tag
serialVersionUID: 4659879214203680767L
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
serialVersionUID: -7252006452127051085L
tag
String tag
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.objectbank |
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 |
Package edu.stanford.nlp.parser.lexparser |
serialVersionUID: 2L
readObject
private void readObject(ObjectInputStream ois)
throws IOException,
ClassNotFoundException
- Throws:
IOException
ClassNotFoundException
tagProjection
TagProjection tagProjection
numTagBins
int numTagBins
tagBin
int[] tagBin
tlp
TreebankLanguagePack tlp
directional
boolean directional
useDistance
boolean useDistance
useCoarseDistance
boolean useCoarseDistance
serialVersionUID: 4299501909017975915L
nodeCleanup
int nodeCleanup
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: 40L
uwModel
UnknownWordModel uwModel
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.
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.
unSeenCounter
ClassicCounter<E> unSeenCounter
- Has counts for taggings in terms of unseen signatures. The IntTagWords are
for (tag,sig), (tag,null), (null,sig), (null,null). (None for basic UNK if
there are signatures.)
smooth
double[] smooth
flexiTag
boolean flexiTag
tagsToBaseTags
int[] tagsToBaseTags
serialVersionUID: 6355171148751673822L
tagHash
Map<K,V> tagHash
seenEnd
Set<E> seenEnd
unknownGT
Map<K,V> unknownGT
l
Lexicon l
smooth
double[] smooth
serialVersionUID: 1L
readObject
private void readObject(ObjectInputStream stream)
throws IOException,
ClassNotFoundException
- Throws:
IOException
ClassNotFoundException
stateSpace
String stateSpace
numStates
int numStates
allRules
List<E> allRules
serialVersionUID: 1L
leftChild
int leftChild
rightChild
int rightChild
hashCode
int hashCode
serialVersionUID: 4153878351331522581L
headFinder
HeadFinder headFinder
serialVersionUID: 4825624957364628770L
smartMutation
boolean smartMutation
smooth
double[] smooth
unknownLevel
int unknownLevel
- What type of equivalence classing is done in getSignature
unknownSuffixSize
int unknownSuffixSize
unknownPrefixSize
int unknownPrefixSize
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.
unSeenCounter
ClassicCounter<E> unSeenCounter
- Has counts for taggings in terms of unseen signatures. The IntTagWords are
for (tag,sig), (tag,null), (null,sig), (null,null). (None for basic UNK if
there are signatures.)
serialVersionUID: 1L
head
IntTaggedWord head
arg
IntTaggedWord arg
leftHeaded
boolean leftHeaded
distance
short distance
serialVersionUID: 1L
word
int word
tag
short tag
serialVersionUID: 1L
readObject
private void readObject(ObjectInputStream stream)
throws IOException,
ClassNotFoundException
- Throws:
IOException
ClassNotFoundException
writeObject
private void writeObject(ObjectOutputStream stream)
throws IOException
- Throws:
IOException
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 cosntructor. 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
smoothTPNumberer
Numberer smoothTPNumberer
serialVersionUID: 4L
numStates
int numStates
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
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.
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.
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 morophology, 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.
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
UnknownWordModel uwModel
- Model for unknown words that the lexicon should use
flexiTag
boolean flexiTag
serialVersionUID: 1L
lex
Lexicon lex
bg
BinaryGrammar bg
ug
UnaryGrammar ug
dg
DependencyGrammar dg
numbs
Map<K,V> numbs
pt
Options pt
tagNumberer
Numberer tagNumberer
wordNumberer
Numberer wordNumberer
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
lastWord
int lastWord
lastSignature
int lastSignature
serialVersionUID: 2L
parent
int parent
score
float score
serialVersionUID: 1L
readObject
private void readObject(ObjectInputStream stream)
throws IOException,
ClassNotFoundException
- Throws:
IOException
ClassNotFoundException
numStates
int numStates
- The number of "states" (nonterms) in the grammar, used to index rules.
stateSpace
String stateSpace
- The name of the Numberer state space for unary rules. Usually "states"
coreRules
Map<K,V> coreRules
- The basic list of UnaryRules. Really this is treated as a set
serialVersionUID: 1L
child
int child
Package edu.stanford.nlp.process |
Package edu.stanford.nlp.sequences |
flags
SeqClassifierFlags flags
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
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 whitespaces 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 whitespaces 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
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
printErrorStuff
boolean printErrorStuff
useRobustQN
boolean useRobustQN
combo
boolean combo
useGenericFeatures
boolean useGenericFeatures
verboseForTrueCasing
boolean verboseForTrueCasing
Package edu.stanford.nlp.stats |
serialVersionUID: 4L
map
Map<K,V> map
mapFactory
MapFactory<K,V> mapFactory
totalCount
double totalCount
defaultValue
double defaultValue
serialVersionUID: 6707148234288637809L
numberOfKeys
int numberOfKeys
reservedMass
double reservedMass
counter
Counter<E> counter
serialVersionUID: 4L
map
Map<K,V> map
mapFactory
MapFactory<K,V> mapFactory
totalCount
int totalCount
serialVersionUID: 1L
map
Map<K,V> map
total
double total
outerMF
MapFactory<K,V> outerMF
innerMF
MapFactory<K,V> innerMF
defaultValue
double defaultValue
Package edu.stanford.nlp.tagger.maxent |
serialVersionUID: -4694133872973560083L
position
int position
isTag
boolean isTag
serialVersionUID: 1L
lexicon
Map<K,V> lexicon
nextXWord
Extractor nextXWord
num
int num
serialVersionUID: -16619310062224383L
bound
int bound
num
int num
position
int position
serialVersionUID: 2631506606864457451L
bound
int bound
s
HashSet<E> s
forms
HashMap<K,V> forms
serialVersionUID: -4777107742414749890L
v
Extractor[] v
inputBox
JTextArea inputBox
outputBox
JTextArea outputBox
tagButton
JButton tagButton
serialVersionUID: -4136407850147157497L
openClassTags
String[] openClassTags
closedClassTags
String[] closedClassTags
xmlInput
String[] xmlInput
mode
TaggerConfig.Mode mode
Package edu.stanford.nlp.trees |
serialVersionUID: -6540278059442931087L
tlp
TreebankLanguagePack tlp
nonTerminalInfo
HashMap<K,V> nonTerminalInfo
defaultRule
String[] defaultRule
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: -8747319554557223437L
tagRejectFilter
Filter<T> tagRejectFilter
wordRejectFilter
Filter<T> wordRejectFilter
serialVersionUID: 2286294455343892678L
dependencies
Set<E> dependencies
typedDependencies
Collection<E> typedDependencies
allTypedDependencies
Collection<E> allTypedDependencies
label
Label label
- The string representing the word that is the yield of the parse tree.
score
double score
- The score for the leaf
label
Label label
- Label of the parse tree.
score
double score
- Score of
TreeNode
daughterTrees
Tree[] daughterTrees
- Daughters of the parse tree.
serialVersionUID: -5870387458902637256L
temporalAnnotation
int temporalAnnotation
doSGappedStuff
boolean doSGappedStuff
leaveItAll
int leaveItAll
doAdverbialNP
boolean doAdverbialNP
headFinder
HeadFinder headFinder
serialVersionUID: 9081305982861675328L
serialVersionUID: 5721799188009249808L
verbalAuxiliaries
HashSet<E> verbalAuxiliaries
copulars
HashSet<E> copulars
verbalTags
HashSet<E> verbalTags
daughterTrees
Tree[] daughterTrees
- Daughters of the parse tree.
serialVersionUID: 5441849457648722744L
serialVersionUID: 1L
root
TreeGraphNode root
- The root node of this treegraph.
indexMap
Map<K,V> indexMap
- A map from arbitrary integer indices to nodes.
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: 5L
regent
Label regent
dependent
Label dependent
Package edu.stanford.nlp.trees.international.arabic |
serialVersionUID: 9081305982861675328L
detPlusNounIsBasicCategory
boolean detPlusNounIsBasicCategory
Package edu.stanford.nlp.trees.international.pennchinese |
map
Map<K,V> map
normalized
boolean normalized
serialVersionUID: 5757403475523638802L
Package edu.stanford.nlp.trees.tregex |
specialConstructor
boolean specialConstructor
- This variable determines which constructor was used to create
this object and thereby affects the semantics of the
"getMessage" method (see below).
currentToken
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.
errorCode
int errorCode
- Indicates the reason why the exception is thrown. It will have
one of the above 4 values.
serialVersionUID: 5060298043763944913L
neg
boolean neg
opt
boolean opt
patternString
String patternString
Package edu.stanford.nlp.trees.tregex.tsurgeon |
specialConstructor
boolean specialConstructor
- This variable determines which constructor was used to create
this object and thereby affects the semantics of the
"getMessage" method (see below).
currentToken
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.
errorCode
int errorCode
- Indicates the reason why the exception is thrown. It will have
one of the above 4 values.
Package edu.stanford.nlp.util |
serialVersionUID: 1L
writeObject
private void writeObject(ObjectOutputStream out)
throws IOException
- Overriden 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
map
Map<K,V> map
cf
CollectionFactory<T> cf
treatCollectionsAsImmutable
boolean treatCollectionsAsImmutable
mf
MapFactory<K,V> mf
emptySet
Set<E> emptySet
originalMap
CollectionValuedMap<K,V> originalMap
deltaMap
Map<K,V> deltaMap
cf
CollectionFactory<T> cf
size
int size
capacity
int capacity
elements
List<E> elements
priorities
double[] priorities
serialVersionUID: 1L
immutableKeys
Set<E> immutableKeys
- Set of immutable keys
hashcode
int hashcode
- Pre-computed hashcode
serialVersionUID: 1L
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
serialVersionUID: 5398562825928375260L
objects
ArrayList<E> objects
indexes
HashMap<K,V> indexes
locked
boolean locked
serialVersionUID: 7154973101012473479L
serialVersionUID: 7266305463893511982L
elements
int[] elements
serialVersionUID: 4529666940763477360L
serialVersionUID: 624465615824626762L
d
double d
serialVersionUID: 624465615824626762L
i
int i
serialVersionUID: 1L
total
int total
intToObject
Map<K,V> intToObject
objectToInt
Map<K,V> objectToInt
tempInt
MutableInteger tempInt
locked
boolean locked
serialVersionUID: 1360822168806852921L
first
Object first
- Direct access is deprecated. Use first().
-
second
Object second
- Direct access is deprecated. Use second().
-
serialVersionUID: 1L
ascending
boolean ascending
first
Object first
second
Object second
third
Object third
Stanford NLP Group