Overview  Package  Class  Tree  Deprecated  Index  Help 
 PREV   NEXT FRAMES    NO FRAMES    

Serialized Form

Package edu.stanford.nlp.graph

Class edu.stanford.nlp.graph.DirectedMultiGraph extends java.lang.Object implements Serializable

serialVersionUID: 609823567298345145L

Serialized Fields

outgoingEdges

java.util.Map<K,V> outgoingEdges

incomingEdges

java.util.Map<K,V> incomingEdges
Package edu.stanford.nlp.international.arabic

Class edu.stanford.nlp.international.arabic.ArabicMorphoFeatureSpecification extends MorphoFeatureSpecification implements Serializable

serialVersionUID: 4448045447200922076L

Class edu.stanford.nlp.international.arabic.ArabicMorphoFeatureSpecification.ArabicMorphoFeatures extends MorphoFeatures implements Serializable

serialVersionUID: -4611776415583633186L

Class edu.stanford.nlp.international.arabic.Buckwalter extends java.lang.Object implements Serializable

serialVersionUID: 4351710914246859336L

Serialized Fields

outputUnicodeValues

boolean outputUnicodeValues
If true (include flag "-o"), outputs space separated unicode values (e.g., "ء" rather than the character version of those values. Only applicable for Buckwalter to Arabic conversion.

arabicChars

char[] arabicChars

buckChars

char[] buckChars

unicode2Buckwalter

boolean unicode2Buckwalter

u2bMap

java.util.HashMap<K,V> u2bMap

b2uMap

java.util.HashMap<K,V> b2uMap

unmappable

ClassicCounter<E> unmappable
Package edu.stanford.nlp.international.arabic.pipeline

Class edu.stanford.nlp.international.arabic.pipeline.DefaultLexicalMapper extends java.lang.Object implements Serializable

serialVersionUID: -3798804368296999785L

Serialized Fields

utf8ArabicChart

java.util.regex.Pattern utf8ArabicChart

bwAlefChar

java.lang.String bwAlefChar

bwDiacritics

java.util.regex.Pattern bwDiacritics

bwTatweel

java.util.regex.Pattern bwTatweel

bwAlef

java.util.regex.Pattern bwAlef

bwQuran

java.util.regex.Pattern bwQuran

bwNullAnaphoraMarker

java.util.regex.Pattern bwNullAnaphoraMarker

latinPunc

java.util.regex.Pattern latinPunc

arabicPunc

java.util.regex.Pattern arabicPunc

arabicDigit

java.util.regex.Pattern arabicDigit

utf8Diacritics

java.util.regex.Pattern utf8Diacritics

utf8Tatweel

java.util.regex.Pattern utf8Tatweel

utf8Alef

java.util.regex.Pattern utf8Alef

utf8Quran

java.util.regex.Pattern utf8Quran

utf8ProDrop

java.util.regex.Pattern utf8ProDrop

segmentationMarker

java.util.regex.Pattern segmentationMarker

morphemeBoundary

java.util.regex.Pattern morphemeBoundary

hasDigit

java.util.regex.Pattern hasDigit

useATBVocalizedSectionMapping

boolean useATBVocalizedSectionMapping

stripMorphemeMarkersInUTF8

boolean stripMorphemeMarkersInUTF8

stripSegmentationMarkersInUTF8

boolean stripSegmentationMarkersInUTF8

parentTagString

java.lang.String parentTagString

parentTagsToEscape

java.util.Set<E> parentTagsToEscape

utf8CliticString

java.lang.String utf8CliticString

bwClitics

java.util.Set<E> bwClitics
Package edu.stanford.nlp.international.arabic.process

Class edu.stanford.nlp.international.arabic.process.ArabicTokenizer.ArabicTokenizerFactory extends java.lang.Object implements Serializable

serialVersionUID: 946818805507187330L

Serialized Fields

factory

LexedTokenFactory<T> factory

lexerProperties

java.util.Properties lexerProperties
Package edu.stanford.nlp.international.french

Class edu.stanford.nlp.international.french.FrenchMorphoFeatureSpecification extends MorphoFeatureSpecification implements Serializable

serialVersionUID: -58379347760106784L

Package edu.stanford.nlp.international.morph

Class edu.stanford.nlp.international.morph.MorphoFeatures extends java.lang.Object implements Serializable

serialVersionUID: -3893316324305154940L

Serialized Fields

fSpec

java.util.Map<K,V> fSpec

altTag

java.lang.String altTag

Class edu.stanford.nlp.international.morph.MorphoFeatureSpecification extends java.lang.Object implements Serializable

serialVersionUID: -5720683653931585664L

Serialized Fields

activeFeatures

java.util.Set<E> activeFeatures
Package edu.stanford.nlp.io

Class edu.stanford.nlp.io.RuntimeIOException extends java.lang.RuntimeException implements Serializable

serialVersionUID: -8572218999165094626L

Package edu.stanford.nlp.io.ui

Class edu.stanford.nlp.io.ui.OpenPageDialog extends javax.swing.JDialog implements Serializable

serialVersionUID: -7987625449997527926L

Serialized Fields

jfc

javax.swing.JFileChooser jfc

status

int status

urlTextField

javax.swing.JTextField urlTextField

openButton

javax.swing.JButton openButton

jLabel1

javax.swing.JLabel jLabel1

jPanel3

javax.swing.JPanel jPanel3

jLabel2

javax.swing.JLabel jLabel2

jPanel2

javax.swing.JPanel jPanel2

cancelButton

javax.swing.JButton cancelButton

browseButton

javax.swing.JButton browseButton

jPanel1

javax.swing.JPanel jPanel1
Package edu.stanford.nlp.ling

Class edu.stanford.nlp.ling.BasicDocument extends java.util.ArrayList<Word> implements Serializable

serialVersionUID: -24171720584352262L

Serialized Fields

title

java.lang.String title
title of this document (never null).

originalText

java.lang.String originalText
original text of this document (may be null).

labels

java.util.List<E> labels
Label(s) for this document.

tokenizerFactory

TokenizerFactory<T> tokenizerFactory
TokenizerFactory used to convert the text into words inside BasicDocument.parse(String).

Class edu.stanford.nlp.ling.CategoryWordTag extends StringLabel implements Serializable

serialVersionUID: -745085381666943254L

Serialized Fields

word

java.lang.String word

tag

java.lang.String tag

Class edu.stanford.nlp.ling.CoreLabel extends ArrayCoreMap implements Serializable

serialVersionUID: 2L

Class edu.stanford.nlp.ling.CyclicCoreLabel extends CoreLabel implements Serializable

serialVersionUID: 1L

Class edu.stanford.nlp.ling.IndexedWord extends CoreLabel implements Serializable

serialVersionUID: 3739633991145239829L

Class edu.stanford.nlp.ling.LabeledWord extends Word implements Serializable

serialVersionUID: -7252006452127051085L

Serialized Fields

tag

Label tag

Class edu.stanford.nlp.ling.StringLabel extends ValueLabel implements Serializable

serialVersionUID: -4153619273767524247L

Serialized Fields

str

java.lang.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

Class edu.stanford.nlp.ling.TaggedWord extends Word implements Serializable

serialVersionUID: -7252006452127051085L

Serialized Fields

tag

java.lang.String tag

Class edu.stanford.nlp.ling.ValueLabel extends java.lang.Object implements Serializable

serialVersionUID: -1413303679077285530L

Class edu.stanford.nlp.ling.Word extends StringLabel implements Serializable

serialVersionUID: -4817252915997034058L

Class edu.stanford.nlp.ling.WordLemmaTag extends java.lang.Object implements Serializable

serialVersionUID: -5993410244163988138L

Serialized Fields

word

java.lang.String word

lemma

java.lang.String lemma

tag

java.lang.String tag

Class edu.stanford.nlp.ling.WordTag extends java.lang.Object implements Serializable

serialVersionUID: -1859527239216813742L

Serialized Fields

word

java.lang.String word

tag

java.lang.String tag
Package edu.stanford.nlp.math

Class edu.stanford.nlp.math.ArrayMath.InvalidElementException extends java.lang.RuntimeException implements Serializable

serialVersionUID: 1647150702529757545L

Package edu.stanford.nlp.objectbank

Class edu.stanford.nlp.objectbank.LineIterator.LineIteratorFactory extends java.lang.Object implements Serializable

serialVersionUID: 1L

Serialized Fields

oper

Function<T1,T2> oper

Class edu.stanford.nlp.objectbank.ObjectBank extends java.lang.Object implements Serializable

serialVersionUID: -4030295596701541770L

Serialized Fields

rif

ReaderIteratorFactory rif

ifrf

IteratorFromReaderFactory<T> ifrf

contents

java.util.List<E> contents

keepInMemory

boolean keepInMemory
Package edu.stanford.nlp.parser.lexparser

Class edu.stanford.nlp.parser.lexparser.AbstractDependencyGrammar extends java.lang.Object implements Serializable

serialVersionUID: 3L

Serialization Methods

readObject

private void readObject(java.io.ObjectInputStream ois)
                 throws java.io.IOException,
                        java.lang.ClassNotFoundException
Throws:
java.io.IOException
java.lang.ClassNotFoundException
Serialized Fields

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

Class edu.stanford.nlp.parser.lexparser.AbstractTreebankParserParams extends java.lang.Object implements Serializable

serialVersionUID: 4299501909017975915L

Serialized Fields

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

java.lang.String inputEncoding

outputEncoding

java.lang.String outputEncoding

tlp

TreebankLanguagePack tlp

Class edu.stanford.nlp.parser.lexparser.AbstractTreebankParserParams.AnnotatePunctuationFunction extends java.lang.Object implements Serializable

serialVersionUID: 1L

Serialized Fields

key

java.lang.String key

annotationMark

java.lang.String annotationMark

Class edu.stanford.nlp.parser.lexparser.ArabicTreebankParserParams extends AbstractTreebankParserParams implements Serializable

serialVersionUID: 8853426784197984653L

Serialized Fields

optionsString

java.lang.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

java.util.Map<K,V> annotationPatterns

activeAnnotations

java.util.List<E> activeAnnotations

morphoSpec

MorphoFeatureSpecification morphoSpec

baselineFeatures

java.util.List<E> baselineFeatures
These are the annotations included when the user selects the -arabicFactored option.

additionalFeatures

java.util.List<E> additionalFeatures

Class edu.stanford.nlp.parser.lexparser.ArabicUnknownWordModel extends BaseUnknownWordModel implements Serializable

serialVersionUID: 4825624957364628771L

Serialized Fields

smartMutation

boolean smartMutation

unknownSuffixSize

int unknownSuffixSize

unknownPrefixSize

int unknownPrefixSize

Class edu.stanford.nlp.parser.lexparser.BaseLexicon extends java.lang.Object implements Serializable

serialVersionUID: 40L

Serialization Methods

readObject

private void readObject(java.io.ObjectInputStream ois)
                 throws java.io.IOException,
                        java.lang.ClassNotFoundException
Throws:
java.io.IOException
java.lang.ClassNotFoundException
Serialized Fields

uwModel

UnknownWordModel uwModel

uwModelTrainerClass

java.lang.String uwModelTrainerClass

trainOptions

TrainOptions trainOptions

testOptions

TestOptions testOptions

op

Options op

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

baseTagCounts

java.util.Map<K,V> baseTagCounts
Only used when training, specifically when training on sentenes that weren't part of annotated (eg markovized, etc) data

tagsToBaseTags

int[] tagsToBaseTags

Class edu.stanford.nlp.parser.lexparser.BaseUnknownWordModel extends java.lang.Object implements Serializable

serialVersionUID: 6355171148751673822L

Serialized Fields

useFirst

boolean useFirst

useEnd

boolean useEnd

useGT

boolean useGT

useFirstCap

boolean useFirstCap

endLength

int endLength

unknownLevel

int unknownLevel
What type of equivalence classing is done in getSignature

trainOptions

TrainOptions trainOptions

wordIndex

Index<E> wordIndex

tagIndex

Index<E> tagIndex

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.)

tagHash

java.util.HashMap<K,V> tagHash
This maps from a tag (as a label) to a Counter from word signatures to their P(sig|tag), as estimated in the model. For Chinese, the word signature is just the first character or its unicode type for things that aren't Chinese characters.

seenEnd

java.util.Set<E> seenEnd
This is the set of all signatures that we have seen.

unknownGT

java.util.HashMap<K,V> unknownGT

lex

Lexicon lex
All classes that implement UnknownWordModel must call the constructor that initializes this variable.

Class edu.stanford.nlp.parser.lexparser.BinaryGrammar extends java.lang.Object implements Serializable

serialVersionUID: 1L

Serialization Methods

readObject

private void readObject(java.io.ObjectInputStream stream)
                 throws java.io.IOException,
                        java.lang.ClassNotFoundException
Throws:
java.io.IOException
java.lang.ClassNotFoundException
Serialized Fields

index

Index<E> index

allRules

java.util.List<E> allRules

Class edu.stanford.nlp.parser.lexparser.BinaryRule extends java.lang.Object implements Serializable

serialVersionUID: 1L

Serialized Fields

parent

int parent

score

float score
Score should be a log probability

leftChild

int leftChild

rightChild

int rightChild

hashCode

int hashCode

Class edu.stanford.nlp.parser.lexparser.ChineseCharacterBasedLexicon extends java.lang.Object implements Serializable

serialVersionUID: -5357655683145854069L

Serialized Fields

lengthPenalty

double lengthPenalty

penaltyType

int penaltyType

charDistributions

java.util.Map<K,V> charDistributions

knownChars

java.util.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

Serialized Fields

useCharBasedUnknownWordModel

boolean useCharBasedUnknownWordModel

useGoodTuringUnknownWordModel

boolean useGoodTuringUnknownWordModel

probRandomWalk

edu.stanford.nlp.parser.lexparser.RandomWalk probRandomWalk

Class edu.stanford.nlp.parser.lexparser.ChineseLexiconAndWordSegmenter extends java.lang.Object implements Serializable

serialVersionUID: -6554995189795187918L

Serialization Methods

readObject

private void readObject(java.io.ObjectInputStream in)
                 throws java.io.IOException,
                        java.lang.ClassNotFoundException
Throws:
java.io.IOException
java.lang.ClassNotFoundException
Serialized Fields

chineseLexicon

ChineseLexicon chineseLexicon

wordSegmenter

WordSegmenter wordSegmenter

op

Options op

Class edu.stanford.nlp.parser.lexparser.ChineseMarkovWordSegmenter extends java.lang.Object implements Serializable

serialVersionUID: 1559606198270645508L

Serialized Fields

initialPOSDist

Distribution<E> initialPOSDist

markovPOSDists

java.util.Map<K,V> markovPOSDists

lex

ChineseCharacterBasedLexicon lex

POSes

java.util.Set<E> POSes

wordIndex

Index<E> wordIndex

tagIndex

Index<E> tagIndex

Class edu.stanford.nlp.parser.lexparser.ChineseSimWordAvgDepGrammar extends MLEDependencyGrammar implements Serializable

serialVersionUID: -1845503582705055342L

Serialized Fields

simSmooth

double simSmooth

simArgMap

java.util.Map<K,V> simArgMap

simHeadMap

java.util.Map<K,V> simHeadMap

debug

boolean debug

verbose

boolean verbose

statsCounter

ClassicCounter<E> statsCounter

Class edu.stanford.nlp.parser.lexparser.ChineseTreebankParserParams extends AbstractTreebankParserParams implements Serializable

serialVersionUID: 2L

Serialized Fields

ctlp

ChineseTreebankLanguagePack ctlp
The variable ctlp stores the same thing as the tlp variable in AbstractTreebankParserParams, but pre-cast to be a ChineseTreebankLanguagePack.

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

java.lang.String segmenterClass

lex

Lexicon lex

segmenter

WordSegmenter segmenter

headFinder

HeadFinder headFinder

chineseSplitDouHao

boolean chineseSplitDouHao
Chinese: Split the dou hao (a punctuation mark separating members of a list) from other punctuation. Good but included below.

chineseSplitPunct

boolean chineseSplitPunct
Chinese: split Chinese punctuation several ways, along the lines of English punctuation plus another category for the dou hao. Good.

chineseSplitPunctLR

boolean chineseSplitPunctLR
Chinese: split left right/paren quote (if chineseSplitPunct is also true. Only very marginal gains, but seems positive.

markVVsisterIP

boolean markVVsisterIP
Chinese: mark VVs that are sister of IP (communication & small-clause-taking verbs). Good: give 0.5%

markPsisterIP

boolean markPsisterIP
Chinese: mark P's that are sister of IP. Negative effect

markIPsisterVVorP

boolean markIPsisterVVorP
Chinese: mark IP's that are sister of VV or P. These rarely have punctuation. Small positive effect.

markADgrandchildOfIP

boolean markADgrandchildOfIP
Chinese: mark ADs that are grandchild of IP.

gpaAD

boolean gpaAD
Grandparent annotate all AD. Seems slightly negative.

chineseVerySelectiveTagPA

boolean chineseVerySelectiveTagPA

chineseSelectiveTagPA

boolean chineseSelectiveTagPA

markIPsisterBA

boolean markIPsisterBA
Chinese: mark IPs that are sister of BA. These always have overt NP. Very slightly positive.

markVPadjunct

boolean markVPadjunct
Chinese: mark phrases that are adjuncts of VP (these tend to be locatives/temporals, and have a specific distribution). Necessary even with chineseSplitVP==3 and parent annotation because parent annotation happens with unsplit parent categories. Slightly positive.

markNPmodNP

boolean markNPmodNP
Chinese: mark NP modifiers of NPs. Quite positive (0.5%)

markModifiedNP

boolean markModifiedNP
Chinese: mark left-modified NPs (rightmost NPs with a left-side mod). Slightly positive.

markNPconj

boolean markNPconj
Chinese: mark NPs that are conjuncts. Negative on small set.

markMultiNtag

boolean markMultiNtag
Chinese: mark nominal tags that are part of multi-nominal rewrites. Doesn't seem any good.

markIPsisDEC

boolean markIPsisDEC
Chinese: mark IPs that are part of prenominal modifiers. Negative.

markIPconj

boolean markIPconj
Chinese: mark IPs that are conjuncts. Or those that have (adjuncts or subjects)

markIPadjsubj

boolean markIPadjsubj

chineseSplitVP

int chineseSplitVP
Chinese VP splitting. 0 = none; 1 = mark with -BA a VP that directly dominates a BA; 2 = mark with -BA a VP that directly dominates a BA or a VP that directly dominates a BA 3 = split VPs into VP-COMP, VP-CRD, VP-ADJ. (Negative value.)

mergeNNVV

boolean mergeNNVV
Chinese: merge NN and VV. A lark.

unaryIP

boolean unaryIP
Chinese: unary category marking

unaryCP

boolean unaryCP

paRootDtr

boolean paRootDtr
Chinese: parent annotate daughter of root. Meant only for selectivesplit=false.

markPostverbalP

boolean markPostverbalP
Chinese: mark P with a left aunt VV, and PP with a left sister VV. Note that it's necessary to mark both to thread the context-marking. Used to identify post-verbal P's, which are rare.

markPostverbalPP

boolean markPostverbalPP

splitBaseNP

boolean splitBaseNP
Mark base NPs. Good.

tagWordSize

boolean tagWordSize
Annotate tags for number of characters contained.

markCC

boolean markCC
Mark phrases which are conjunctions. Appears negative, even with 200K words training data.

splitNPTMP

boolean splitNPTMP
Whether to retain the -TMP functional tag on various phrasal categories. On 80K words training, minutely helpful; on 200K words, best option gives 0.6%. Doing splitNPTMP and splitPPTMP (but not splitXPTMP) is best.

splitPPTMP

boolean splitPPTMP

splitXPTMP

boolean splitXPTMP

dominatesV

boolean dominatesV
Verbal distance -- mark whether symbol dominates a verb (V*). Seems bad for Chinese.

useGoodTuringUnknownWordModel

boolean useGoodTuringUnknownWordModel

useCharBasedUnknownWordModel

boolean useCharBasedUnknownWordModel

lengthPenalty

double lengthPenalty
Parameters for a ChineseCharacterBasedLexicon

useUnknownCharacterModel

boolean useUnknownCharacterModel

penaltyType

int penaltyType
penaltyType should be set as follows: 0: no length penalty 1: quadratic length penalty 2: penalty for continuation chars only TODO: make this an enum

depGramFeatureLevel

int depGramFeatureLevel

Class edu.stanford.nlp.parser.lexparser.ChineseUnknownWordModel extends BaseUnknownWordModel implements Serializable

serialVersionUID: 221L

Serialized Fields

useUnicodeType

boolean useUnicodeType

seenFirst

java.util.Set<E> seenFirst

Class edu.stanford.nlp.parser.lexparser.EnglishTreebankParserParams extends AbstractTreebankParserParams implements Serializable

serialVersionUID: 4153878351331522581L

Serialized Fields

headFinder

HeadFinder headFinder

englishTrain

EnglishTreebankParserParams.EnglishTrain englishTrain

englishTest

EnglishTreebankParserParams.EnglishTest englishTest

Class edu.stanford.nlp.parser.lexparser.EnglishTreebankParserParams.EnglishTest extends java.lang.Object implements Serializable

serialVersionUID: 183157656745674521L

Serialized Fields

retainNPTMPSubcategories

boolean retainNPTMPSubcategories

retainTMPSubcategories

boolean retainTMPSubcategories

retainADVSubcategories

boolean retainADVSubcategories

makeCopulaHead

boolean makeCopulaHead

Class edu.stanford.nlp.parser.lexparser.EnglishTreebankParserParams.EnglishTrain extends java.lang.Object implements Serializable

serialVersionUID: 1831576434872643L

Serialized Fields

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 BaseUnknownWordModel implements Serializable

serialVersionUID: 4825624957364628770L

Serialized Fields

smartMutation

boolean smartMutation

unknownSuffixSize

int unknownSuffixSize

unknownPrefixSize

int unknownPrefixSize

Class edu.stanford.nlp.parser.lexparser.FactoredLexicon extends BaseLexicon implements Serializable

serialVersionUID: -744693222804176489L

Serialized Fields

morphoSpec

MorphoFeatureSpecification morphoSpec

morphIndex

Index<E> morphIndex

wordTag

TwoDimensionalIntCounter<K1,K2> wordTag

wordTagUnseen

Counter<E> wordTagUnseen

lemmaTag

TwoDimensionalIntCounter<K1,K2> lemmaTag

lemmaTagUnseen

Counter<E> lemmaTagUnseen

morphTag

TwoDimensionalIntCounter<K1,K2> morphTag

morphTagUnseen

Counter<E> morphTagUnseen

tagCounter

Counter<E> tagCounter

Class edu.stanford.nlp.parser.lexparser.FrenchTreebankParserParams extends AbstractTreebankParserParams implements Serializable

serialVersionUID: -6976724734594763986L

Serialized Fields

optionsString

java.lang.StringBuilder optionsString

headFinder

HeadFinder headFinder

annotationPatterns

java.util.Map<K,V> annotationPatterns

activeAnnotations

java.util.List<E> activeAnnotations

readPennFormat

boolean readPennFormat

collinizerRetainsPunctuation

boolean collinizerRetainsPunctuation

mwCounter

TwoDimensionalCounter<K1,K2> mwCounter

morphoSpec

MorphoFeatureSpecification morphoSpec

tagSpec

MorphoFeatureSpecification tagSpec

baselineFeatures

java.util.List<E> baselineFeatures

additionalFeatures

java.util.List<E> additionalFeatures

Class edu.stanford.nlp.parser.lexparser.FrenchUnknownWordModel extends BaseUnknownWordModel implements Serializable

serialVersionUID: -776564693549194424L

Serialized Fields

smartMutation

boolean smartMutation

unknownSuffixSize

int unknownSuffixSize

unknownPrefixSize

int unknownPrefixSize

Class edu.stanford.nlp.parser.lexparser.GermanUnknownWordModel extends BaseUnknownWordModel implements Serializable

serialVersionUID: 221L

Class edu.stanford.nlp.parser.lexparser.HebrewTreebankParserParams extends AbstractTreebankParserParams implements Serializable

serialVersionUID: -3466519995341208619L

Serialized Fields

optionsString

java.lang.StringBuilder optionsString

Class edu.stanford.nlp.parser.lexparser.IntDependency extends java.lang.Object implements Serializable

serialVersionUID: 1L

Serialized Fields

head

IntTaggedWord head

arg

IntTaggedWord arg

leftHeaded

boolean leftHeaded

distance

short distance

Class edu.stanford.nlp.parser.lexparser.IntTaggedWord extends java.lang.Object implements Serializable

serialVersionUID: 1L

Serialized Fields

word

int word

tag

short tag

Class edu.stanford.nlp.parser.lexparser.Lattice extends java.lang.Object implements Serializable

serialVersionUID: 5135076134500512556L

Serialized Fields

constraints

java.util.List<E> constraints

edges

java.util.List<E> edges

nodes

java.util.Set<E> nodes

edgeStartsAt

java.util.Map<K,V> edgeStartsAt

maxNode

int maxNode

Class edu.stanford.nlp.parser.lexparser.LatticeEdge extends java.lang.Object implements Serializable

serialVersionUID: 4416189959485854286L

Serialized Fields

word

java.lang.String word

label

java.lang.String label

weight

double weight

start

int start

end

int end

attrs

java.util.Map<K,V> attrs

Class edu.stanford.nlp.parser.lexparser.LexicalizedParser extends java.lang.Object implements Serializable

serialVersionUID: 2L

Serialized Fields

lex

Lexicon lex

bg

BinaryGrammar bg

ug

UnaryGrammar ug

dg

DependencyGrammar dg

stateIndex

Index<E> stateIndex

wordIndex

Index<E> wordIndex

tagIndex

Index<E> tagIndex

op

Options op

Class edu.stanford.nlp.parser.lexparser.MLEDependencyGrammar extends AbstractDependencyGrammar implements Serializable

serialVersionUID: 1L

Serialization Methods

readObject

private void readObject(java.io.ObjectInputStream stream)
                 throws java.io.IOException,
                        java.lang.ClassNotFoundException
Throws:
java.io.IOException
java.lang.ClassNotFoundException

writeObject

private void writeObject(java.io.ObjectOutputStream stream)
                  throws java.io.IOException
Throws:
java.io.IOException
Serialized Fields

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

Class edu.stanford.nlp.parser.lexparser.NegraPennTreebankParserParams extends AbstractTreebankParserParams implements Serializable

serialVersionUID: 757812264219400466L

Serialized Fields

markRC

boolean markRC

markZuVP

boolean markZuVP

markLP

boolean markLP

markColon

boolean markColon

markKonjParent

boolean markKonjParent

markHDParent

boolean markHDParent

markContainsV

boolean markContainsV

nodeCleanup

int nodeCleanup
Node cleanup is how node names are normalized. The known values are: 0 = do nothing; 1 = keep category and function; 2 = keep only category

headFinder

HeadFinder headFinder

treeNormalizerInsertNPinPP

boolean treeNormalizerInsertNPinPP

treeNormalizerLeaveGF

boolean treeNormalizerLeaveGF

treeReaderFactory

NegraPennTreeReaderFactory treeReaderFactory

Class edu.stanford.nlp.parser.lexparser.Options extends java.lang.Object implements Serializable

serialVersionUID: 4L

Serialization Methods

readObject

private void readObject(java.io.ObjectInputStream in)
                 throws java.io.IOException,
                        java.lang.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:
java.io.IOException
java.lang.ClassNotFoundException
Serialized Fields

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.

Class edu.stanford.nlp.parser.lexparser.Options.LexOptions extends java.lang.Object implements Serializable

serialVersionUID: 2805351374506855632L

Serialized Fields

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.

uwModelTrainer

java.lang.String uwModelTrainer
Trainer which produces 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 java.lang.Object implements Serializable

serialVersionUID: 4955237758572202093L

Serialized Fields

start

int start

end

int end

state

java.util.regex.Pattern state

Class edu.stanford.nlp.parser.lexparser.TestOptions extends java.lang.Object implements Serializable

serialVersionUID: 7256526346598L

Serialized Fields

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

java.lang.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

java.lang.String outputFormat
Determines format of output trees: choose among penn, oneline

outputFormatOptions

java.lang.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

java.lang.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

java.lang.String outputFilesExtension
If the writeOutputFiles option is true, then output files appear with this extension. Use "" for no extension.

outputFilesPrefix

java.lang.String outputFilesPrefix
If the writeOutputFiles option is true, then output files appear with this prefix.

outputkBestEquivocation

java.lang.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.

evalPCFGkBest

int evalPCFGkBest
If using a kBest eval, use this many trees.

printFactoredKGood

int printFactoredKGood
Printing k-best parses from PCFG, when k > 0.

evals

java.util.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.

Class edu.stanford.nlp.parser.lexparser.TrainOptions extends java.lang.Object implements Serializable

serialVersionUID: 72571349843538L

Serialized Fields

trainTreeFile

java.lang.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

java.util.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

java.util.Set<E> splitters
Set the splitter strings. These are a set of parent and/or grandparent annotated categories which should be split off.

postSplitters

java.util.Set<E> postSplitters

deleteSplitters

java.util.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

java.io.PrintWriter printAnnotatedPW

printBinarizedPW

java.io.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

preTransformer

TreeTransformer preTransformer
A transformer to use on the training data before any other processing step. This is specified by using the -preTransformer flag when training the parser. A comma separated list of classes will be turned into a CompositeTransformer. This can be used to strip subcategories, to run a tsurgeon pattern, or any number of other useful operations.

taggedFiles

java.lang.String taggedFiles
A set of files to use as extra information in the lexicon. This can provide tagged words which are not part of trees

predictSplits

boolean predictSplits
Use the method reported by Berkeley for splitting and recombining states. This is an experimental and still in development reimplementation of that work.

splitCount

int splitCount
If we are predicting splits, we loop this many times

splitRecombineRate

double splitRecombineRate
If we are predicting splits, we recombine states at this rate every loop

simpleBinarizedLabels

boolean simpleBinarizedLabels
When binarizing trees, don't annotate the labels with anything

noRebinarization

boolean noRebinarization
When binarizing trees, don't binarize trees with two children. Only applies when using inside markov binarization for now.

splitTrainingThreads

int splitTrainingThreads
How many simultaneous threads to launch when counting up trees on each iteration of the split/merge algorithm. For example, you could set this to the number of processors you have

Class edu.stanford.nlp.parser.lexparser.TueBaDZParserParams extends AbstractTreebankParserParams implements Serializable

serialVersionUID: 7303189408025355170L

Serialized Fields

hf

HeadFinder hf

nodeCleanup

int nodeCleanup
How to clean up node labels: 0 = do nothing, 1 = keep category and function, 2 = just category.

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 java.lang.Object implements Serializable

serialVersionUID: 1L

Serialization Methods

readObject

private void readObject(java.io.ObjectInputStream stream)
                 throws java.io.IOException,
                        java.lang.ClassNotFoundException
Throws:
java.io.IOException
java.lang.ClassNotFoundException
Serialized Fields

index

Index<E> index

coreRules

java.util.Map<K,V> coreRules
The basic list of UnaryRules. Really this is treated as a set

Class edu.stanford.nlp.parser.lexparser.UnaryRule extends java.lang.Object implements Serializable

serialVersionUID: 1L

Serialized Fields

parent

int parent

score

float score
Score should be a log probability

child

int child
Package edu.stanford.nlp.parser.ui

Class edu.stanford.nlp.parser.ui.Parser extends javax.swing.JFrame implements Serializable

serialVersionUID: 7179757799978939358L

Serialized Fields

parserPanel

ParserPanel parserPanel

untokEngItem

javax.swing.JCheckBoxMenuItem untokEngItem

tokChineseItem

javax.swing.JCheckBoxMenuItem tokChineseItem

untokChineseItem

javax.swing.JCheckBoxMenuItem untokChineseItem

jMenu2

javax.swing.JMenu jMenu2

loadParserItem

javax.swing.JMenuItem loadParserItem

loadDataItem

javax.swing.JMenuItem loadDataItem

jSeparator1

javax.swing.JSeparator jSeparator1

jMenu1

javax.swing.JMenu jMenu1

exitItem

javax.swing.JMenuItem exitItem

jMenuBar1

javax.swing.JMenuBar jMenuBar1

Class edu.stanford.nlp.parser.ui.ParserPanel extends javax.swing.JPanel implements Serializable

serialVersionUID: -2118491857333662471L

Serialized Fields

encoding

java.lang.String encoding

segmentWords

boolean segmentWords

jfc

javax.swing.JFileChooser jfc

jfcLocation

edu.stanford.nlp.parser.ui.ParserPanel.JFileChooserLocation jfcLocation

chooseJarParser

JarFileChooser chooseJarParser

pageDialog

OpenPageDialog pageDialog

normalStyle

javax.swing.text.SimpleAttributeSet normalStyle

highlightStyle

javax.swing.text.SimpleAttributeSet highlightStyle

startIndex

int startIndex

endIndex

int endIndex

treePanel

TreeJPanel treePanel

parser

LexicalizedParser parser

lpThread

edu.stanford.nlp.parser.ui.ParserPanel.LoadParserThread lpThread

parseThread

edu.stanford.nlp.parser.ui.ParserPanel.ParseThread parseThread

timer

javax.swing.Timer timer

count

int count

glassPane

java.awt.Component glassPane

scrollWhenDone

boolean scrollWhenDone
Whether to scroll one sentence forward after parsing.

dataFileLabel

javax.swing.JLabel dataFileLabel

treeContainer

javax.swing.JPanel treeContainer

topPanel

javax.swing.JPanel topPanel

textScrollPane

javax.swing.JScrollPane textScrollPane

backButton

javax.swing.JButton backButton

statusLabel

javax.swing.JLabel statusLabel

loadFileButton

javax.swing.JButton loadFileButton

loadButtonPanel

javax.swing.JPanel loadButtonPanel

buttonsAndFilePanel

javax.swing.JPanel buttonsAndFilePanel

parseButton

javax.swing.JButton parseButton

parseNextButton

javax.swing.JButton parseNextButton

forwardButton

javax.swing.JButton forwardButton

parserFileLabel

javax.swing.JLabel parserFileLabel

clearButton

javax.swing.JButton clearButton

splitPane

javax.swing.JSplitPane splitPane

statusPanel

javax.swing.JPanel statusPanel

dataFilePanel

javax.swing.JPanel dataFilePanel

buttonPanel

javax.swing.JPanel buttonPanel

textPane

javax.swing.JTextPane textPane

progressBar

javax.swing.JProgressBar progressBar

parserFilePanel

javax.swing.JPanel parserFilePanel

loadParserButton

javax.swing.JButton loadParserButton

saveOutputButton

javax.swing.JButton saveOutputButton

Class edu.stanford.nlp.parser.ui.TreeJPanel extends javax.swing.JPanel implements Serializable

Serialized Fields

VERTICAL_ALIGN

int VERTICAL_ALIGN

HORIZONTAL_ALIGN

int HORIZONTAL_ALIGN

maxFontSize

int maxFontSize

minFontSize

int minFontSize

tree

Tree tree
Package edu.stanford.nlp.process

Class edu.stanford.nlp.process.CoreLabelTokenFactory extends java.lang.Object implements Serializable

serialVersionUID: 4L

Serialized Fields

addIndices

boolean addIndices
Package edu.stanford.nlp.stats

Class edu.stanford.nlp.stats.ClassicCounter extends java.lang.Object implements Serializable

serialVersionUID: 4L

Serialized Fields

map

java.util.Map<K,V> map

mapFactory

MapFactory<K,V> mapFactory

totalCount

double totalCount

defaultValue

double defaultValue

Class edu.stanford.nlp.stats.Distribution extends java.lang.Object implements Serializable

serialVersionUID: 6707148234288637809L

Serialized Fields

numberOfKeys

int numberOfKeys

reservedMass

double reservedMass

counter

Counter<E> counter

Class edu.stanford.nlp.stats.GeneralizedCounter extends java.lang.Object implements Serializable

serialVersionUID: 1L

Serialized Fields

map

java.util.Map<K,V> map

depth

int depth

total

double total

Class edu.stanford.nlp.stats.IntCounter extends AbstractCounter<E> implements Serializable

serialVersionUID: 4L

Serialized Fields

map

java.util.Map<K,V> map

mapFactory

MapFactory<K,V> mapFactory

totalCount

int totalCount

defaultValue

int defaultValue

Class edu.stanford.nlp.stats.TwoDimensionalCounter extends java.lang.Object implements Serializable

serialVersionUID: 1L

Serialized Fields

map

java.util.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 java.lang.Object implements Serializable

serialVersionUID: 1L

Serialized Fields

map

java.util.Map<K,V> map

total

int total

outerMF

MapFactory<K,V> outerMF

innerMF

MapFactory<K,V> innerMF

defaultValue

int defaultValue
Package edu.stanford.nlp.tagger.maxent

Class edu.stanford.nlp.tagger.maxent.TaggerConfig extends java.util.Properties implements Serializable

serialVersionUID: -4136407850147157497L

Serialized Fields

mode

TaggerConfig.Mode mode
Package edu.stanford.nlp.trees

Class edu.stanford.nlp.trees.AbstractCollinsHeadFinder extends java.lang.Object implements Serializable

serialVersionUID: -6540278059442931087L

Serialized Fields

tlp

TreebankLanguagePack tlp

nonTerminalInfo

java.util.Map<K,V> nonTerminalInfo

defaultRule

java.lang.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

java.lang.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

java.lang.String[] defaultRightRule

Class edu.stanford.nlp.trees.AbstractTreebankLanguagePack extends java.lang.Object implements Serializable

serialVersionUID: -6506749780512708352L

Serialized Fields

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

Class edu.stanford.nlp.trees.BobChrisTreeNormalizer extends TreeNormalizer implements Serializable

serialVersionUID: -1005188028979810143L

Serialized Fields

tlp

TreebankLanguagePack tlp

emptyFilter

Filter<T> emptyFilter

aOverAFilter

Filter<T> aOverAFilter

Class edu.stanford.nlp.trees.BobChrisTreeNormalizer.AOverAFilter extends java.lang.Object implements Serializable

serialVersionUID: 1L

Class edu.stanford.nlp.trees.BobChrisTreeNormalizer.EmptyFilter extends java.lang.Object implements Serializable

serialVersionUID: 8914098359495987617L

Class edu.stanford.nlp.trees.CollinsHeadFinder extends AbstractCollinsHeadFinder implements Serializable

serialVersionUID: -8747319554557223437L

Class edu.stanford.nlp.trees.Dependencies.DependentPuncTagRejectFilter extends java.lang.Object implements Serializable

serialVersionUID: -7732189363171164852L

Serialized Fields

tagRejectFilter

Filter<T> tagRejectFilter

Class edu.stanford.nlp.trees.Dependencies.DependentPuncWordRejectFilter extends java.lang.Object implements Serializable

serialVersionUID: 1166489968248785287L

Serialized Fields

wordRejectFilter

Filter<T> wordRejectFilter

Class edu.stanford.nlp.trees.EnglishGrammaticalStructure extends GrammaticalStructure implements Serializable

serialVersionUID: -1866362375001969402L

Class edu.stanford.nlp.trees.GrammaticalFunctionTreeNormalizer extends TreeNormalizer implements Serializable

serialVersionUID: -2270472762938163327L

Serialized Fields

nodeCleanup

int nodeCleanup
How to clean up node labels: 0 = do nothing, 1 = keep category and function, 2 = just category.

root

java.lang.String root

tlp

TreebankLanguagePack tlp

Class edu.stanford.nlp.trees.GrammaticalRelation extends java.lang.Object implements Serializable

serialVersionUID: 892618003417550128L

Serialized Fields

language

GrammaticalRelation.Language language

shortName

java.lang.String shortName

longName

java.lang.String longName

parent

GrammaticalRelation parent

children

java.util.List<E> children

sourcePattern

java.util.regex.Pattern sourcePattern

targetPatterns

java.util.List<E> targetPatterns

specific

java.lang.String specific

Class edu.stanford.nlp.trees.GrammaticalStructure extends TreeGraph implements Serializable

serialVersionUID: 2286294455343892678L

Serialized Fields

dependencies

java.util.Set<E> dependencies

typedDependencies

java.util.List<E> typedDependencies

allTypedDependencies

java.util.List<E> allTypedDependencies

Class edu.stanford.nlp.trees.LabeledScoredTreeNode extends Tree implements Serializable

serialVersionUID: -8992385140984593817L

Serialized Fields

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 java.lang.Object implements Serializable

serialVersionUID: 8453889846239508208L

Class edu.stanford.nlp.trees.LengthTreeFilter extends java.lang.Object implements Serializable

serialVersionUID: 1L

Serialized Fields

length

int length

Class edu.stanford.nlp.trees.ModCollinsHeadFinder extends CollinsHeadFinder implements Serializable

serialVersionUID: -5870387458902637256L

Class edu.stanford.nlp.trees.NamedDependency extends UnnamedDependency implements Serializable

serialVersionUID: -1635646451505721133L

Serialized Fields

name

java.lang.Object name

Class edu.stanford.nlp.trees.NPTmpRetainingTreeNormalizer extends BobChrisTreeNormalizer implements Serializable

serialVersionUID: 7548777133196579107L

Serialized Fields

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

Serialized Fields

tns

java.util.List<E> tns

Class edu.stanford.nlp.trees.PennTreebankLanguagePack extends AbstractTreebankLanguagePack implements Serializable

serialVersionUID: 9081305982861675328L

Class edu.stanford.nlp.trees.SemanticHeadFinder extends ModCollinsHeadFinder implements Serializable

serialVersionUID: 5721799188009249808L

Serialized Fields

verbalAuxiliaries

java.util.HashSet<E> verbalAuxiliaries

copulars

java.util.HashSet<E> copulars

passiveAuxiliaries

java.util.HashSet<E> passiveAuxiliaries

verbalTags

java.util.HashSet<E> verbalTags

Class edu.stanford.nlp.trees.SimpleTree extends Tree implements Serializable

serialVersionUID: -8075763706877132926L

Serialized Fields

daughterTrees

Tree[] daughterTrees
Daughters of the parse tree.

Class edu.stanford.nlp.trees.Tree extends java.util.AbstractCollection<Tree> implements Serializable

serialVersionUID: 5441849457648722744L

Serialized Fields

score

double score

Class edu.stanford.nlp.trees.TreeGraph extends java.lang.Object implements Serializable

serialVersionUID: 1L

Serialized Fields

root

TreeGraphNode root
The root node of this treegraph.

indexMap

java.util.Map<K,V> indexMap
A map from arbitrary integer indices to nodes.

Class edu.stanford.nlp.trees.TreeGraphNode extends Tree implements Serializable

serialVersionUID: 5080098143617475328L

Serialized Fields

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.

Class edu.stanford.nlp.trees.TreeNormalizer extends java.lang.Object implements Serializable

serialVersionUID: 1540681875853883387L

Class edu.stanford.nlp.trees.TypedDependency extends java.lang.Object implements Serializable

serialVersionUID: -7690294213151279779L

Serialized Fields

reln

GrammaticalRelation reln

gov

TreeGraphNode gov

dep

TreeGraphNode dep

extra

boolean extra

Class edu.stanford.nlp.trees.UnnamedConcreteDependency extends UnnamedDependency implements Serializable

serialVersionUID: -8836949694741145222L

Serialized Fields

headIndex

int headIndex

depIndex

int depIndex

Class edu.stanford.nlp.trees.UnnamedDependency extends java.lang.Object implements Serializable

serialVersionUID: -3768440215342256085L

Serialized Fields

regentText

java.lang.String regentText

dependentText

java.lang.String dependentText

regent

Label regent

dependent

Label dependent
Package edu.stanford.nlp.trees.international.arabic

Class edu.stanford.nlp.trees.international.arabic.ArabicHeadFinder extends AbstractCollinsHeadFinder implements Serializable

serialVersionUID: 6203368998430280740L

Serialized Fields

tagSet

ArabicHeadFinder.TagSet tagSet

predPattern

java.util.regex.Pattern predPattern

Class edu.stanford.nlp.trees.international.arabic.ArabicTreebankLanguagePack extends AbstractTreebankLanguagePack implements Serializable

serialVersionUID: 9081305982861675328L

Serialized Fields

tf

TokenizerFactory<T> tf
TODO: there is no way to change this using options.

Class edu.stanford.nlp.trees.international.arabic.ArabicTreeNormalizer extends BobChrisTreeNormalizer implements Serializable

serialVersionUID: -1592231121068698494L

Serialized Fields

retainNPTmp

boolean retainNPTmp

retainNPSbj

boolean retainNPSbj

markPRDverb

boolean markPRDverb

changeNoLabels

boolean changeNoLabels

retainPPClr

boolean retainPPClr

prdPattern

java.util.regex.Pattern prdPattern

prdVerbPattern

TregexPattern prdVerbPattern

npSbjPattern

TregexPattern npSbjPattern

rootLabel

java.lang.String rootLabel

lexMapper

Mapper lexMapper

Class edu.stanford.nlp.trees.international.arabic.ArabicTreeNormalizer.ArabicEmptyFilter extends java.lang.Object implements Serializable

serialVersionUID: 7417844982953945964L

Class edu.stanford.nlp.trees.international.arabic.ArabicTreeReaderFactory extends java.lang.Object implements Serializable

serialVersionUID: 1973767605277873017L

Serialized Fields

retainNPTmp

boolean retainNPTmp

retainNPSbj

boolean retainNPSbj

retainPRD

boolean retainPRD

retainPPClr

boolean retainPPClr

changeNoLabels

boolean changeNoLabels

filterX

boolean filterX

noNormalization

boolean noNormalization

Class edu.stanford.nlp.trees.international.arabic.ArabicTreeReaderFactory.ArabicRawTreeReaderFactory extends ArabicTreeReaderFactory implements Serializable

serialVersionUID: -5693371540982097793L

Package edu.stanford.nlp.trees.international.french

Class edu.stanford.nlp.trees.international.french.DybroFrenchHeadFinder extends AbstractCollinsHeadFinder implements Serializable

serialVersionUID: 8798606577201646967L

Class edu.stanford.nlp.trees.international.french.FrenchHeadFinder extends AbstractCollinsHeadFinder implements Serializable

serialVersionUID: 8747319554557223422L

Class edu.stanford.nlp.trees.international.french.FrenchTreebankLanguagePack extends AbstractTreebankLanguagePack implements Serializable

serialVersionUID: -7338244949063822519L

Class edu.stanford.nlp.trees.international.french.FrenchTreeNormalizer extends BobChrisTreeNormalizer implements Serializable

serialVersionUID: 7868735300308066991L

Serialized Fields

rootLabel

java.lang.String rootLabel

Class edu.stanford.nlp.trees.international.french.FrenchTreeNormalizer.FrenchAOverAFilter extends java.lang.Object implements Serializable

serialVersionUID: 793800623099852951L

Class edu.stanford.nlp.trees.international.french.FrenchTreeReaderFactory extends java.lang.Object implements Serializable

serialVersionUID: 6928967570430642163L

Serialized Fields

readPennFormat

boolean readPennFormat
Package edu.stanford.nlp.trees.international.hebrew

Class edu.stanford.nlp.trees.international.hebrew.HebrewTreebankLanguagePack extends AbstractTreebankLanguagePack implements Serializable

serialVersionUID: 4787589385598144401L

Class edu.stanford.nlp.trees.international.hebrew.HebrewTreeNormalizer extends BobChrisTreeNormalizer implements Serializable

serialVersionUID: -3129547164200725933L

Serialized Fields

hebrewEmptyFilter

Filter<T> hebrewEmptyFilter

Class edu.stanford.nlp.trees.international.hebrew.HebrewTreeNormalizer.HebrewEmptyFilter extends java.lang.Object implements Serializable

serialVersionUID: -7256461296718287280L

Class edu.stanford.nlp.trees.international.hebrew.HebrewTreeReaderFactory extends java.lang.Object implements Serializable

serialVersionUID: 818065349424602548L

Package edu.stanford.nlp.trees.international.negra

Class edu.stanford.nlp.trees.international.negra.NegraHeadFinder extends AbstractCollinsHeadFinder implements Serializable

serialVersionUID: -7253035927065152766L

Serialized Fields

coordSwitch

boolean coordSwitch

left

java.lang.String left

right

java.lang.String right

Class edu.stanford.nlp.trees.international.negra.NegraLabel extends StringLabel implements Serializable

serialVersionUID: 2847331882765391095L

Serialized Fields

edge

java.lang.String edge

features

java.util.Map<K,V> features

Class edu.stanford.nlp.trees.international.negra.NegraPennLanguagePack extends AbstractTreebankLanguagePack implements Serializable

serialVersionUID: 9081305982861675328L

Serialized Fields

leaveGF

boolean leaveGF

Class edu.stanford.nlp.trees.international.negra.NegraPennTreeNormalizer extends TreeNormalizer implements Serializable

serialVersionUID: 8529514903815041064L

Serialized Fields

nodeCleanup

int nodeCleanup
How to clean up node labels: 0 = do nothing, 1 = keep category and function, 2 = just category

tlp

TreebankLanguagePack tlp

insertNPinPP

boolean insertNPinPP

emptyFilter

Filter<T> emptyFilter

aOverAFilter

Filter<T> aOverAFilter

prepositionTags

java.util.Set<E> prepositionTags

postpositionTags

java.util.Set<E> postpositionTags

Class edu.stanford.nlp.trees.international.negra.NegraPennTreeReaderFactory extends java.lang.Object implements Serializable

serialVersionUID: 5731352106152470304L

Serialized Fields

nodeCleanup

int nodeCleanup

tlp

TreebankLanguagePack tlp

treeNormalizerInsertNPinPP

boolean treeNormalizerInsertNPinPP
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.ChineseEnglishWordMap extends java.lang.Object implements Serializable

serialVersionUID: 7655332268578049993L

Serialized Fields

map

java.util.Map<K,V> map

normalized

boolean normalized

Class edu.stanford.nlp.trees.international.pennchinese.ChineseGrammaticalStructure extends GrammaticalStructure implements Serializable

serialVersionUID: 8877651855167458256L

Class edu.stanford.nlp.trees.international.pennchinese.ChineseHeadFinder extends AbstractCollinsHeadFinder implements Serializable

serialVersionUID: 6143632784691159283L

Class edu.stanford.nlp.trees.international.pennchinese.ChineseSemanticHeadFinder extends ChineseHeadFinder implements Serializable

serialVersionUID: 2L

Class edu.stanford.nlp.trees.international.pennchinese.ChineseTreebankLanguagePack extends AbstractTreebankLanguagePack implements Serializable

serialVersionUID: 5757403475523638802L

Class edu.stanford.nlp.trees.international.pennchinese.CTBErrorCorrectingTreeNormalizer extends BobChrisTreeNormalizer implements Serializable

serialVersionUID: -8203853817025401845L

Serialized Fields

tagExtender

TreeTransformer tagExtender

splitNPTMP

boolean splitNPTMP

splitPPTMP

boolean splitPPTMP

splitXPTMP

boolean splitXPTMP

chineseEmptyFilter

Filter<T> chineseEmptyFilter

Class edu.stanford.nlp.trees.international.pennchinese.SunJurafskyChineseHeadFinder extends AbstractCollinsHeadFinder implements Serializable

serialVersionUID: -7942375587642755210L

Package edu.stanford.nlp.trees.international.tuebadz

Class edu.stanford.nlp.trees.international.tuebadz.TueBaDZHeadFinder extends AbstractCollinsHeadFinder implements Serializable

serialVersionUID: 1L

Serialized Fields

left

java.lang.String left

right

java.lang.String right

coordSwitch

boolean coordSwitch

headMarkedPattern

java.util.regex.Pattern headMarkedPattern

headMarkedPattern2

java.util.regex.Pattern headMarkedPattern2

Class edu.stanford.nlp.trees.international.tuebadz.TueBaDZLanguagePack extends AbstractTreebankLanguagePack implements Serializable

serialVersionUID: 2697418320262700673L

Serialized Fields

limitedGF

boolean limitedGF

leaveGF

boolean leaveGF

Class edu.stanford.nlp.trees.international.tuebadz.TueBaDZPennTreeNormalizer extends TreeNormalizer implements Serializable

serialVersionUID: 8009544230321390490L

Serialized Fields

nodeCleanup

int nodeCleanup
How to clean up node labels: 0 = do nothing, 1 = keep category and function, 2 = just category.

root

java.lang.String root

tlp

TreebankLanguagePack tlp

tns

java.util.List<E> tns

Class edu.stanford.nlp.trees.international.tuebadz.TueBaDZTreeReaderFactory extends java.lang.Object implements Serializable

serialVersionUID: 1614799885744961795L

Serialized Fields

tlp

TreebankLanguagePack tlp

nodeCleanup

int nodeCleanup
Package edu.stanford.nlp.trees.semgraph

Class edu.stanford.nlp.trees.semgraph.SemanticGraph extends java.lang.Object implements Serializable

serialVersionUID: 1L

Serialized Fields

roots

java.util.Collection<E> roots
The distinguished root vertices, if known.

graph

DirectedMultiGraph<V,E> graph

Class edu.stanford.nlp.trees.semgraph.SemanticGraphEdge extends java.lang.Object implements Serializable

serialVersionUID: 2L

Serialized Fields

relation

GrammaticalRelation relation

weight

double weight

source

IndexedWord source

target

IndexedWord target
Package edu.stanford.nlp.trees.tregex

Class edu.stanford.nlp.trees.tregex.ParseException extends java.lang.Exception implements Serializable

serialVersionUID: 1L

Serialized Fields

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

java.lang.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

java.lang.String eol
The end of line string for this machine.

Class edu.stanford.nlp.trees.tregex.TregexParseException extends java.lang.RuntimeException implements Serializable

Class edu.stanford.nlp.trees.tregex.TregexPattern extends java.lang.Object implements Serializable

serialVersionUID: 5060298043763944913L

Serialized Fields

neg

boolean neg

opt

boolean opt

patternString

java.lang.String patternString
Package edu.stanford.nlp.trees.tregex.tsurgeon

Class edu.stanford.nlp.trees.tregex.tsurgeon.ParseException extends java.lang.Exception implements Serializable

serialVersionUID: 1L

Serialized Fields

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

java.lang.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

java.lang.String eol
The end of line string for this machine.

Class edu.stanford.nlp.trees.tregex.tsurgeon.TsurgeonParseException extends java.lang.RuntimeException implements Serializable

Package edu.stanford.nlp.util

Class edu.stanford.nlp.util.ArrayCoreMap extends java.lang.Object implements Serializable

serialVersionUID: 1L

Serialization Methods

writeObject

private void writeObject(java.io.ObjectOutputStream out)
                  throws java.io.IOException
Overridden serialization method: compacts our map before writing.

Throws:
java.io.IOException - If IO error
Serialized Fields

keys

java.lang.Class<T>[] keys
Array of keys

values

java.lang.Object[] values
Array of values

size

int size
Total number of elements actually in keys,values

Class edu.stanford.nlp.util.ArrayMap extends java.util.AbstractMap<K,V> implements Serializable

serialVersionUID: 1L

Serialized Fields

entryArray

edu.stanford.nlp.util.ArrayMap.Entry<K,V>[] entryArray

capacity

int capacity

size

int size

hashCodeCache

int hashCodeCache

Class edu.stanford.nlp.util.ArrayStringFilter extends java.lang.Object implements Serializable

serialVersionUID: 1L

Serialized Fields

words

java.lang.String[] words

length

int length

Class edu.stanford.nlp.util.CollectionFactory extends java.lang.Object implements Serializable

serialVersionUID: 3711321773145894069L

Class edu.stanford.nlp.util.CollectionFactory.ArrayListFactory extends CollectionFactory<T> implements Serializable

serialVersionUID: 1L

Class edu.stanford.nlp.util.CollectionFactory.HashSetFactory extends CollectionFactory<T> implements Serializable

serialVersionUID: -6268401669449458602L

Class edu.stanford.nlp.util.CollectionFactory.LinkedListFactory extends CollectionFactory<T> implements Serializable

serialVersionUID: -4236184979948498000L

Class edu.stanford.nlp.util.CollectionFactory.SizedArrayListFactory extends CollectionFactory<T> implements Serializable

serialVersionUID: 1L

Serialized Fields

defaultSize

int defaultSize

Class edu.stanford.nlp.util.CollectionFactory.TreeSetFactory extends CollectionFactory<T> implements Serializable

serialVersionUID: -3451920268219478134L

Class edu.stanford.nlp.util.CollectionValuedMap extends java.lang.Object implements Serializable

serialVersionUID: -9064664153962599076L

Serialized Fields

map

java.util.Map<K,V> map

cf

CollectionFactory<T> cf

treatCollectionsAsImmutable

boolean treatCollectionsAsImmutable

mf

MapFactory<K,V> mf

emptyValue

java.util.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.DeltaCollectionValuedMap extends CollectionValuedMap<K,V> implements Serializable

serialVersionUID: 1L

Serialized Fields

originalMap

CollectionValuedMap<K,V> originalMap

deltaMap

java.util.Map<K,V> deltaMap

Class edu.stanford.nlp.util.DeltaIndex extends java.util.AbstractCollection<E> implements Serializable

serialVersionUID: -1459230891686013411L

Serialized Fields

backingIndex

Index<E> backingIndex

spilloverIndex

Index<E> spilloverIndex

backingIndexSize

int backingIndexSize

locked

boolean locked

Class edu.stanford.nlp.util.Filters.ConjFilter extends java.lang.Object implements Serializable

Serialized Fields

filters

java.util.List<E> filters

Class edu.stanford.nlp.util.Filters.DisjFilter extends java.lang.Object implements Serializable

Serialized Fields

filters

java.util.List<E> filters

Class edu.stanford.nlp.util.FixedPrioritiesPriorityQueue extends java.util.AbstractSet<E> implements Serializable

serialVersionUID: 1L

Serialized Fields

size

int size

capacity

int capacity

elements

java.util.List<E> elements

priorities

double[] priorities

Class edu.stanford.nlp.util.HashableCoreMap extends ArrayCoreMap implements Serializable

serialVersionUID: 1L

Serialized Fields

immutableKeys

java.util.Set<E> immutableKeys
Set of immutable keys

hashcode

int hashcode
Pre-computed hashcode

Class edu.stanford.nlp.util.HashableCoreMap.HashableCoreMapException extends java.lang.RuntimeException implements Serializable

serialVersionUID: 1L

Class edu.stanford.nlp.util.HashIndex extends java.util.AbstractCollection<E> implements Serializable

serialVersionUID: 5398562825928375260L

Serialized Fields

objects

java.util.ArrayList<E> objects

indexes

java.util.HashMap<K,V> indexes

locked

boolean locked

semaphore

java.util.concurrent.Semaphore semaphore

Class edu.stanford.nlp.util.IdentityHashSet extends java.util.AbstractSet<E> implements Serializable

serialVersionUID: -5024744406713321676L

Serialization Methods

readObject

private void readObject(java.io.ObjectInputStream s)
                 throws java.io.IOException,
                        java.lang.ClassNotFoundException
Deserialize this Object in a manner which is binary-compatible with the JDK.

Throws:
java.io.IOException
java.lang.ClassNotFoundException

writeObject

private void writeObject(java.io.ObjectOutputStream s)
                  throws java.io.IOException
Serialize this Object in a manner which is binary-compatible with the JDK.

Throws:
java.io.IOException

Class edu.stanford.nlp.util.Interval extends Pair<E extends java.lang.Comparable<E>,E extends java.lang.Comparable<E>> implements Serializable

Serialized Fields

flags

int flags

Class edu.stanford.nlp.util.IntPair extends IntTuple implements Serializable

serialVersionUID: 1L

Class edu.stanford.nlp.util.IntQuadruple extends IntTuple implements Serializable

serialVersionUID: 7154973101012473479L

Class edu.stanford.nlp.util.IntTriple extends IntTuple implements Serializable

serialVersionUID: -3744404627253652799L

Class edu.stanford.nlp.util.IntTuple extends java.lang.Object implements Serializable

serialVersionUID: 7266305463893511982L

Serialized Fields

elements

int[] elements

Class edu.stanford.nlp.util.IntUni extends IntTuple implements Serializable

serialVersionUID: -7182556672628741200L

Class edu.stanford.nlp.util.LowercaseFunction extends java.lang.Object implements Serializable

serialVersionUID: 1L

Class edu.stanford.nlp.util.MapFactory extends java.lang.Object implements Serializable

serialVersionUID: 4529666940763477360L

Class edu.stanford.nlp.util.MetaClass.ClassCreationException extends java.lang.RuntimeException implements Serializable

serialVersionUID: -5980065992461870357L

Class edu.stanford.nlp.util.MetaClass.ConstructorNotFoundException extends MetaClass.ClassCreationException implements Serializable

serialVersionUID: -5980065992461870357L

Class edu.stanford.nlp.util.MutableDouble extends java.lang.Number implements Serializable

serialVersionUID: 624465615824626762L

Serialized Fields

d

double d

Class edu.stanford.nlp.util.MutableInteger extends java.lang.Number implements Serializable

serialVersionUID: 624465615824626762L

Serialized Fields

i

int i

Class edu.stanford.nlp.util.Pair extends java.lang.Object implements Serializable

serialVersionUID: 1360822168806852921L

Serialized Fields

first

java.lang.Object first
Direct access is deprecated. Use first().

 

second

java.lang.Object second
Direct access is deprecated. Use second().

 

Class edu.stanford.nlp.util.ReflectionLoading.ReflectionLoadingException extends java.lang.RuntimeException implements Serializable

Class edu.stanford.nlp.util.ScoredComparator extends java.lang.Object implements Serializable

serialVersionUID: 1L

Serialized Fields

ascending

boolean ascending

Class edu.stanford.nlp.util.StringParsingTask.ParserException extends java.lang.RuntimeException implements Serializable

serialVersionUID: 1L

Class edu.stanford.nlp.util.ThreeDimensionalMap extends java.lang.Object implements Serializable

serialVersionUID: 1L

Serialized Fields

map

java.util.Map<K,V> map

Class edu.stanford.nlp.util.Triple extends java.lang.Object implements Serializable

serialVersionUID: -4182871682751645440L

Serialized Fields

first

java.lang.Object first

second

java.lang.Object second

third

java.lang.Object third

Class edu.stanford.nlp.util.TwoDimensionalMap extends java.lang.Object implements Serializable

serialVersionUID: 2L

Serialized Fields

mf1

MapFactory<K,V> mf1

mf2

MapFactory<K,V> mf2

map

java.util.Map<K,V> map

Overview  Package  Class  Tree  Deprecated  Index  Help 
 PREV   NEXT FRAMES    NO FRAMES    
Stanford NLP Group