public static interface CoreNLPProtos.TokenOrBuilder extends com.google.protobuf.GeneratedMessageV3.ExtendableMessageOrBuilder<CoreNLPProtos.Token>
| Modifier and Type | Method and Description |
|---|---|
java.lang.String |
getAfter()
The whitespace/xml after the token
|
com.google.protobuf.ByteString |
getAfterBytes()
The whitespace/xml after the token
|
java.lang.String |
getAnswer()
A temporary annotation which is occasionally left in
|
com.google.protobuf.ByteString |
getAnswerBytes()
A temporary annotation which is occasionally left in
|
java.lang.String |
getArabicSeg()
Arabic character info
|
com.google.protobuf.ByteString |
getArabicSegBytes()
Arabic character info
|
java.lang.String |
getBefore()
The whitespace/xml before the token
|
com.google.protobuf.ByteString |
getBeforeBytes()
The whitespace/xml before the token
|
int |
getBeginChar()
The character offset begin, in the document
|
int |
getBeginIndex()
The begin index of, e.g., a span
|
java.lang.String |
getCategory()
The word's 'category' (e.g., parse tree node)
|
com.google.protobuf.ByteString |
getCategoryBytes()
The word's 'category' (e.g., parse tree node)
|
java.lang.String |
getChineseChar()
Chinese character info
|
com.google.protobuf.ByteString |
getChineseCharBytes()
Chinese character info
|
java.lang.String |
getChineseSeg()
optional string chineseSeg = 55; |
com.google.protobuf.ByteString |
getChineseSegBytes()
optional string chineseSeg = 55; |
java.lang.String |
getChineseXMLChar()
optional string chineseXMLChar = 60; |
com.google.protobuf.ByteString |
getChineseXMLCharBytes()
optional string chineseXMLChar = 60; |
java.lang.String |
getCoarseNER()
The word's coarse NER tag
|
com.google.protobuf.ByteString |
getCoarseNERBytes()
The word's coarse NER tag
|
java.lang.String |
getCoarseTag()
The coarse POS tag (used to store the UPOS tag)
|
com.google.protobuf.ByteString |
getCoarseTagBytes()
The coarse POS tag (used to store the UPOS tag)
|
int |
getCodepointOffsetBegin()
optional uint32 codepointOffsetBegin = 74; |
int |
getCodepointOffsetEnd()
optional uint32 codepointOffsetEnd = 75; |
CoreNLPProtos.MapStringString |
getConllUFeatures()
optional .edu.stanford.nlp.pipeline.MapStringString conllUFeatures = 32; |
CoreNLPProtos.MapStringStringOrBuilder |
getConllUFeaturesOrBuilder()
optional .edu.stanford.nlp.pipeline.MapStringString conllUFeatures = 32; |
java.lang.String |
getConllUMisc()
optional string conllUMisc = 35; |
com.google.protobuf.ByteString |
getConllUMiscBytes()
optional string conllUMisc = 35; |
CoreNLPProtos.MapStringString |
getConllUSecondaryDeps()
optional .edu.stanford.nlp.pipeline.MapStringString conllUSecondaryDeps = 36; |
CoreNLPProtos.MapStringStringOrBuilder |
getConllUSecondaryDepsOrBuilder()
optional .edu.stanford.nlp.pipeline.MapStringString conllUSecondaryDeps = 36; |
CoreNLPProtos.Span |
getConllUTokenSpan()
optional .edu.stanford.nlp.pipeline.Span conllUTokenSpan = 34; |
CoreNLPProtos.SpanOrBuilder |
getConllUTokenSpanOrBuilder()
optional .edu.stanford.nlp.pipeline.Span conllUTokenSpan = 34; |
int |
getCorefClusterID()
The [primary] cluster id for this token
|
int |
getCorefMentionIndex(int index)
mention index info
|
int |
getCorefMentionIndexCount()
mention index info
|
java.util.List<java.lang.Integer> |
getCorefMentionIndexList()
mention index info
|
int |
getEmptyIndex()
optional uint32 emptyIndex = 80; |
int |
getEndChar()
The character offset end, in the document
|
int |
getEndIndex()
The begin index of, e.g., a span
|
int |
getEntityMentionIndex()
optional uint32 entityMentionIndex = 65; |
java.lang.String |
getFineGrainedNER()
The word's fine-grained NER tag
|
com.google.protobuf.ByteString |
getFineGrainedNERBytes()
The word's fine-grained NER tag
|
java.lang.String |
getGender()
Fields set by other annotators in CoreNLP
|
com.google.protobuf.ByteString |
getGenderBytes()
Fields set by other annotators in CoreNLP
|
boolean |
getHasXmlContext()
Used by clean xml annotator
|
int |
getHeadWordIndex()
optional string projectedCategory = 25; // The syntactic category of the maximal constituent headed by the word.
|
int |
getIndex()
Most serialized annotations will not have this
Some code paths may not correctly process this if serialized,
since many places will read the index off the position in a sentence
In particular, deserializing a Document using ProtobufAnnotationSerializer
will clobber any index value
But Semgrex and Ssurgeon in particular need a way
to pass around nodes where the node's index is not strictly 1, 2, 3, ...
|
boolean |
getIsFirstMWT()
optional bool isFirstMWT = 68; |
boolean |
getIsMWT()
mwt stuff
|
boolean |
getIsNewline()
optional bool isNewline = 38; |
java.lang.String |
getLemma()
The word's lemma
|
com.google.protobuf.ByteString |
getLemmaBytes()
The word's lemma
|
java.lang.String |
getMwtMisc()
setting this to a map might be nice, but there are a couple issues
for one, there can be values with no key
for another, it's a pain to correctly parse, since different treebanks
can have different standards for how to write out the misc field
|
com.google.protobuf.ByteString |
getMwtMiscBytes()
setting this to a map might be nice, but there are a couple issues
for one, there can be values with no key
for another, it's a pain to correctly parse, since different treebanks
can have different standards for how to write out the misc field
|
java.lang.String |
getMwtText()
optional string mwtText = 69; |
com.google.protobuf.ByteString |
getMwtTextBytes()
optional string mwtText = 69; |
java.lang.String |
getNer()
The word's NER tag
|
com.google.protobuf.ByteString |
getNerBytes()
The word's NER tag
|
java.lang.String |
getNerLabelProbs(int index)
listing of probs
|
com.google.protobuf.ByteString |
getNerLabelProbsBytes(int index)
listing of probs
|
int |
getNerLabelProbsCount()
listing of probs
|
java.util.List<java.lang.String> |
getNerLabelProbsList()
listing of probs
|
java.lang.String |
getNormalizedNER()
The word's normalized NER tag
|
com.google.protobuf.ByteString |
getNormalizedNERBytes()
The word's normalized NER tag
|
java.lang.String |
getNumericCompositeType()
optional string numericCompositeType = 73; |
com.google.protobuf.ByteString |
getNumericCompositeTypeBytes()
optional string numericCompositeType = 73; |
long |
getNumericCompositeValue()
optional uint64 numericCompositeValue = 72; |
java.lang.String |
getNumericType()
optional string numericType = 71; |
com.google.protobuf.ByteString |
getNumericTypeBytes()
optional string numericType = 71; |
long |
getNumericValue()
number info
|
CoreNLPProtos.Operator |
getOperator()
If this is an operator, which one is it and what is its scope (as per Natural Logic)?
|
CoreNLPProtos.OperatorOrBuilder |
getOperatorOrBuilder()
If this is an operator, which one is it and what is its scope (as per Natural Logic)?
|
java.lang.String |
getOriginalText()
The original text for this token
|
com.google.protobuf.ByteString |
getOriginalTextBytes()
The original text for this token
|
java.lang.String |
getParent()
French tokens have parents
|
com.google.protobuf.ByteString |
getParentBytes()
French tokens have parents
|
CoreNLPProtos.Polarity |
getPolarity()
The polarity of this word, according to Natural Logic
|
java.lang.String |
getPolarityDir()
The polarity of this word, either "up", "down", or "flat"
|
com.google.protobuf.ByteString |
getPolarityDirBytes()
The polarity of this word, either "up", "down", or "flat"
|
CoreNLPProtos.PolarityOrBuilder |
getPolarityOrBuilder()
The polarity of this word, according to Natural Logic
|
java.lang.String |
getPos()
The word's part of speech tag
|
com.google.protobuf.ByteString |
getPosBytes()
The word's part of speech tag
|
int |
getQuotationIndex()
The index of the quotation this token refers to
|
java.lang.String |
getSectionAuthor()
optional string sectionAuthor = 57; |
com.google.protobuf.ByteString |
getSectionAuthorBytes()
optional string sectionAuthor = 57; |
java.lang.String |
getSectionDate()
optional string sectionDate = 58; |
com.google.protobuf.ByteString |
getSectionDateBytes()
optional string sectionDate = 58; |
java.lang.String |
getSectionEndLabel()
optional string sectionEndLabel = 59; |
com.google.protobuf.ByteString |
getSectionEndLabelBytes()
optional string sectionEndLabel = 59; |
java.lang.String |
getSectionName()
Section info
|
com.google.protobuf.ByteString |
getSectionNameBytes()
Section info
|
java.lang.String |
getSentiment()
The final sentiment of the sentence
|
com.google.protobuf.ByteString |
getSentimentBytes()
The final sentiment of the sentence
|
CoreNLPProtos.Span |
getSpan()
The span of a leaf node of a tree
|
CoreNLPProtos.SpanOrBuilder |
getSpanOrBuilder()
The span of a leaf node of a tree
|
java.lang.String |
getSpeaker()
The speaker speaking this word
|
com.google.protobuf.ByteString |
getSpeakerBytes()
The speaker speaking this word
|
java.lang.String |
getSpeakerType()
The type of speaker speaking this word
|
com.google.protobuf.ByteString |
getSpeakerTypeBytes()
The type of speaker speaking this word
|
CoreNLPProtos.Timex |
getTimexValue()
The time this word refers to
|
CoreNLPProtos.TimexOrBuilder |
getTimexValueOrBuilder()
The time this word refers to
|
int |
getTokenBeginIndex()
The begin index of the token
|
int |
getTokenEndIndex()
The end index of the token
|
java.lang.String |
getTrueCase()
true case type of token
|
com.google.protobuf.ByteString |
getTrueCaseBytes()
true case type of token
|
java.lang.String |
getTrueCaseText()
true case gloss of token
|
com.google.protobuf.ByteString |
getTrueCaseTextBytes()
true case gloss of token
|
int |
getUtterance()
The utterance tag used in dcoref
|
java.lang.String |
getValue()
The word's 'value', (e.g., parse tree node)
|
com.google.protobuf.ByteString |
getValueBytes()
The word's 'value', (e.g., parse tree node)
|
java.lang.String |
getWikipediaEntity()
optional string wikipediaEntity = 37; |
com.google.protobuf.ByteString |
getWikipediaEntityBytes()
optional string wikipediaEntity = 37; |
java.lang.String |
getWord()
Fields set by the default annotators [new CoreNLP(new Properties())]
|
com.google.protobuf.ByteString |
getWordBytes()
Fields set by the default annotators [new CoreNLP(new Properties())]
|
java.lang.String |
getXmlContext(int index)
Used by clean xml annotator
|
com.google.protobuf.ByteString |
getXmlContextBytes(int index)
Used by clean xml annotator
|
int |
getXmlContextCount()
Used by clean xml annotator
|
java.util.List<java.lang.String> |
getXmlContextList()
Used by clean xml annotator
|
boolean |
hasAfter()
The whitespace/xml after the token
|
boolean |
hasAnswer()
A temporary annotation which is occasionally left in
|
boolean |
hasArabicSeg()
Arabic character info
|
boolean |
hasBefore()
The whitespace/xml before the token
|
boolean |
hasBeginChar()
The character offset begin, in the document
|
boolean |
hasBeginIndex()
The begin index of, e.g., a span
|
boolean |
hasCategory()
The word's 'category' (e.g., parse tree node)
|
boolean |
hasChineseChar()
Chinese character info
|
boolean |
hasChineseSeg()
optional string chineseSeg = 55; |
boolean |
hasChineseXMLChar()
optional string chineseXMLChar = 60; |
boolean |
hasCoarseNER()
The word's coarse NER tag
|
boolean |
hasCoarseTag()
The coarse POS tag (used to store the UPOS tag)
|
boolean |
hasCodepointOffsetBegin()
optional uint32 codepointOffsetBegin = 74; |
boolean |
hasCodepointOffsetEnd()
optional uint32 codepointOffsetEnd = 75; |
boolean |
hasConllUFeatures()
optional .edu.stanford.nlp.pipeline.MapStringString conllUFeatures = 32; |
boolean |
hasConllUMisc()
optional string conllUMisc = 35; |
boolean |
hasConllUSecondaryDeps()
optional .edu.stanford.nlp.pipeline.MapStringString conllUSecondaryDeps = 36; |
boolean |
hasConllUTokenSpan()
optional .edu.stanford.nlp.pipeline.Span conllUTokenSpan = 34; |
boolean |
hasCorefClusterID()
The [primary] cluster id for this token
|
boolean |
hasEmptyIndex()
optional uint32 emptyIndex = 80; |
boolean |
hasEndChar()
The character offset end, in the document
|
boolean |
hasEndIndex()
The begin index of, e.g., a span
|
boolean |
hasEntityMentionIndex()
optional uint32 entityMentionIndex = 65; |
boolean |
hasFineGrainedNER()
The word's fine-grained NER tag
|
boolean |
hasGender()
Fields set by other annotators in CoreNLP
|
boolean |
hasHasXmlContext()
Used by clean xml annotator
|
boolean |
hasHeadWordIndex()
optional string projectedCategory = 25; // The syntactic category of the maximal constituent headed by the word.
|
boolean |
hasIndex()
Most serialized annotations will not have this
Some code paths may not correctly process this if serialized,
since many places will read the index off the position in a sentence
In particular, deserializing a Document using ProtobufAnnotationSerializer
will clobber any index value
But Semgrex and Ssurgeon in particular need a way
to pass around nodes where the node's index is not strictly 1, 2, 3, ...
|
boolean |
hasIsFirstMWT()
optional bool isFirstMWT = 68; |
boolean |
hasIsMWT()
mwt stuff
|
boolean |
hasIsNewline()
optional bool isNewline = 38; |
boolean |
hasLemma()
The word's lemma
|
boolean |
hasMwtMisc()
setting this to a map might be nice, but there are a couple issues
for one, there can be values with no key
for another, it's a pain to correctly parse, since different treebanks
can have different standards for how to write out the misc field
|
boolean |
hasMwtText()
optional string mwtText = 69; |
boolean |
hasNer()
The word's NER tag
|
boolean |
hasNormalizedNER()
The word's normalized NER tag
|
boolean |
hasNumericCompositeType()
optional string numericCompositeType = 73; |
boolean |
hasNumericCompositeValue()
optional uint64 numericCompositeValue = 72; |
boolean |
hasNumericType()
optional string numericType = 71; |
boolean |
hasNumericValue()
number info
|
boolean |
hasOperator()
If this is an operator, which one is it and what is its scope (as per Natural Logic)?
|
boolean |
hasOriginalText()
The original text for this token
|
boolean |
hasParent()
French tokens have parents
|
boolean |
hasPolarity()
The polarity of this word, according to Natural Logic
|
boolean |
hasPolarityDir()
The polarity of this word, either "up", "down", or "flat"
|
boolean |
hasPos()
The word's part of speech tag
|
boolean |
hasQuotationIndex()
The index of the quotation this token refers to
|
boolean |
hasSectionAuthor()
optional string sectionAuthor = 57; |
boolean |
hasSectionDate()
optional string sectionDate = 58; |
boolean |
hasSectionEndLabel()
optional string sectionEndLabel = 59; |
boolean |
hasSectionName()
Section info
|
boolean |
hasSentiment()
The final sentiment of the sentence
|
boolean |
hasSpan()
The span of a leaf node of a tree
|
boolean |
hasSpeaker()
The speaker speaking this word
|
boolean |
hasSpeakerType()
The type of speaker speaking this word
|
boolean |
hasTimexValue()
The time this word refers to
|
boolean |
hasTokenBeginIndex()
The begin index of the token
|
boolean |
hasTokenEndIndex()
The end index of the token
|
boolean |
hasTrueCase()
true case type of token
|
boolean |
hasTrueCaseText()
true case gloss of token
|
boolean |
hasUtterance()
The utterance tag used in dcoref
|
boolean |
hasValue()
The word's 'value', (e.g., parse tree node)
|
boolean |
hasWikipediaEntity()
optional string wikipediaEntity = 37; |
boolean |
hasWord()
Fields set by the default annotators [new CoreNLP(new Properties())]
|
getDefaultInstanceForType, getExtension, getExtension, getExtension, getExtension, getExtension, getExtension, getExtensionCount, getExtensionCount, getExtensionCount, hasExtension, hasExtension, hasExtensionboolean hasWord()
Fields set by the default annotators [new CoreNLP(new Properties())]
optional string word = 1;java.lang.String getWord()
Fields set by the default annotators [new CoreNLP(new Properties())]
optional string word = 1;com.google.protobuf.ByteString getWordBytes()
Fields set by the default annotators [new CoreNLP(new Properties())]
optional string word = 1;boolean hasPos()
The word's part of speech tag
optional string pos = 2;java.lang.String getPos()
The word's part of speech tag
optional string pos = 2;com.google.protobuf.ByteString getPosBytes()
The word's part of speech tag
optional string pos = 2;boolean hasValue()
The word's 'value', (e.g., parse tree node)
optional string value = 3;java.lang.String getValue()
The word's 'value', (e.g., parse tree node)
optional string value = 3;com.google.protobuf.ByteString getValueBytes()
The word's 'value', (e.g., parse tree node)
optional string value = 3;boolean hasCategory()
The word's 'category' (e.g., parse tree node)
optional string category = 4;java.lang.String getCategory()
The word's 'category' (e.g., parse tree node)
optional string category = 4;com.google.protobuf.ByteString getCategoryBytes()
The word's 'category' (e.g., parse tree node)
optional string category = 4;boolean hasBefore()
The whitespace/xml before the token
optional string before = 5;java.lang.String getBefore()
The whitespace/xml before the token
optional string before = 5;com.google.protobuf.ByteString getBeforeBytes()
The whitespace/xml before the token
optional string before = 5;boolean hasAfter()
The whitespace/xml after the token
optional string after = 6;java.lang.String getAfter()
The whitespace/xml after the token
optional string after = 6;com.google.protobuf.ByteString getAfterBytes()
The whitespace/xml after the token
optional string after = 6;boolean hasOriginalText()
The original text for this token
optional string originalText = 7;java.lang.String getOriginalText()
The original text for this token
optional string originalText = 7;com.google.protobuf.ByteString getOriginalTextBytes()
The original text for this token
optional string originalText = 7;boolean hasNer()
The word's NER tag
optional string ner = 8;java.lang.String getNer()
The word's NER tag
optional string ner = 8;com.google.protobuf.ByteString getNerBytes()
The word's NER tag
optional string ner = 8;boolean hasCoarseNER()
The word's coarse NER tag
optional string coarseNER = 62;java.lang.String getCoarseNER()
The word's coarse NER tag
optional string coarseNER = 62;com.google.protobuf.ByteString getCoarseNERBytes()
The word's coarse NER tag
optional string coarseNER = 62;boolean hasFineGrainedNER()
The word's fine-grained NER tag
optional string fineGrainedNER = 63;java.lang.String getFineGrainedNER()
The word's fine-grained NER tag
optional string fineGrainedNER = 63;com.google.protobuf.ByteString getFineGrainedNERBytes()
The word's fine-grained NER tag
optional string fineGrainedNER = 63;java.util.List<java.lang.String> getNerLabelProbsList()
listing of probs
repeated string nerLabelProbs = 66;int getNerLabelProbsCount()
listing of probs
repeated string nerLabelProbs = 66;java.lang.String getNerLabelProbs(int index)
listing of probs
repeated string nerLabelProbs = 66;index - The index of the element to return.com.google.protobuf.ByteString getNerLabelProbsBytes(int index)
listing of probs
repeated string nerLabelProbs = 66;index - The index of the value to return.boolean hasNormalizedNER()
The word's normalized NER tag
optional string normalizedNER = 9;java.lang.String getNormalizedNER()
The word's normalized NER tag
optional string normalizedNER = 9;com.google.protobuf.ByteString getNormalizedNERBytes()
The word's normalized NER tag
optional string normalizedNER = 9;boolean hasLemma()
The word's lemma
optional string lemma = 10;java.lang.String getLemma()
The word's lemma
optional string lemma = 10;com.google.protobuf.ByteString getLemmaBytes()
The word's lemma
optional string lemma = 10;boolean hasBeginChar()
The character offset begin, in the document
optional uint32 beginChar = 11;int getBeginChar()
The character offset begin, in the document
optional uint32 beginChar = 11;boolean hasEndChar()
The character offset end, in the document
optional uint32 endChar = 12;int getEndChar()
The character offset end, in the document
optional uint32 endChar = 12;boolean hasUtterance()
The utterance tag used in dcoref
optional uint32 utterance = 13;int getUtterance()
The utterance tag used in dcoref
optional uint32 utterance = 13;boolean hasSpeaker()
The speaker speaking this word
optional string speaker = 14;java.lang.String getSpeaker()
The speaker speaking this word
optional string speaker = 14;com.google.protobuf.ByteString getSpeakerBytes()
The speaker speaking this word
optional string speaker = 14;boolean hasSpeakerType()
The type of speaker speaking this word
optional string speakerType = 77;java.lang.String getSpeakerType()
The type of speaker speaking this word
optional string speakerType = 77;com.google.protobuf.ByteString getSpeakerTypeBytes()
The type of speaker speaking this word
optional string speakerType = 77;boolean hasBeginIndex()
The begin index of, e.g., a span
optional uint32 beginIndex = 15;int getBeginIndex()
The begin index of, e.g., a span
optional uint32 beginIndex = 15;boolean hasEndIndex()
The begin index of, e.g., a span
optional uint32 endIndex = 16;int getEndIndex()
The begin index of, e.g., a span
optional uint32 endIndex = 16;boolean hasTokenBeginIndex()
The begin index of the token
optional uint32 tokenBeginIndex = 17;int getTokenBeginIndex()
The begin index of the token
optional uint32 tokenBeginIndex = 17;boolean hasTokenEndIndex()
The end index of the token
optional uint32 tokenEndIndex = 18;int getTokenEndIndex()
The end index of the token
optional uint32 tokenEndIndex = 18;boolean hasTimexValue()
The time this word refers to
optional .edu.stanford.nlp.pipeline.Timex timexValue = 19;CoreNLPProtos.Timex getTimexValue()
The time this word refers to
optional .edu.stanford.nlp.pipeline.Timex timexValue = 19;CoreNLPProtos.TimexOrBuilder getTimexValueOrBuilder()
The time this word refers to
optional .edu.stanford.nlp.pipeline.Timex timexValue = 19;boolean hasHasXmlContext()
Used by clean xml annotator
optional bool hasXmlContext = 21;boolean getHasXmlContext()
Used by clean xml annotator
optional bool hasXmlContext = 21;java.util.List<java.lang.String> getXmlContextList()
Used by clean xml annotator
repeated string xmlContext = 22;int getXmlContextCount()
Used by clean xml annotator
repeated string xmlContext = 22;java.lang.String getXmlContext(int index)
Used by clean xml annotator
repeated string xmlContext = 22;index - The index of the element to return.com.google.protobuf.ByteString getXmlContextBytes(int index)
Used by clean xml annotator
repeated string xmlContext = 22;index - The index of the value to return.boolean hasCorefClusterID()
The [primary] cluster id for this token
optional uint32 corefClusterID = 23;int getCorefClusterID()
The [primary] cluster id for this token
optional uint32 corefClusterID = 23;boolean hasAnswer()
A temporary annotation which is occasionally left in
optional string answer = 24;java.lang.String getAnswer()
A temporary annotation which is occasionally left in
optional string answer = 24;com.google.protobuf.ByteString getAnswerBytes()
A temporary annotation which is occasionally left in
optional string answer = 24;boolean hasHeadWordIndex()
optional string projectedCategory = 25; // The syntactic category of the maximal constituent headed by the word. Not used anywhere, so deleted.
optional uint32 headWordIndex = 26;int getHeadWordIndex()
optional string projectedCategory = 25; // The syntactic category of the maximal constituent headed by the word. Not used anywhere, so deleted.
optional uint32 headWordIndex = 26;boolean hasOperator()
If this is an operator, which one is it and what is its scope (as per Natural Logic)?
optional .edu.stanford.nlp.pipeline.Operator operator = 27;CoreNLPProtos.Operator getOperator()
If this is an operator, which one is it and what is its scope (as per Natural Logic)?
optional .edu.stanford.nlp.pipeline.Operator operator = 27;CoreNLPProtos.OperatorOrBuilder getOperatorOrBuilder()
If this is an operator, which one is it and what is its scope (as per Natural Logic)?
optional .edu.stanford.nlp.pipeline.Operator operator = 27;boolean hasPolarity()
The polarity of this word, according to Natural Logic
optional .edu.stanford.nlp.pipeline.Polarity polarity = 28;CoreNLPProtos.Polarity getPolarity()
The polarity of this word, according to Natural Logic
optional .edu.stanford.nlp.pipeline.Polarity polarity = 28;CoreNLPProtos.PolarityOrBuilder getPolarityOrBuilder()
The polarity of this word, according to Natural Logic
optional .edu.stanford.nlp.pipeline.Polarity polarity = 28;boolean hasPolarityDir()
The polarity of this word, either "up", "down", or "flat"
optional string polarity_dir = 39;java.lang.String getPolarityDir()
The polarity of this word, either "up", "down", or "flat"
optional string polarity_dir = 39;com.google.protobuf.ByteString getPolarityDirBytes()
The polarity of this word, either "up", "down", or "flat"
optional string polarity_dir = 39;boolean hasSpan()
The span of a leaf node of a tree
optional .edu.stanford.nlp.pipeline.Span span = 29;CoreNLPProtos.Span getSpan()
The span of a leaf node of a tree
optional .edu.stanford.nlp.pipeline.Span span = 29;CoreNLPProtos.SpanOrBuilder getSpanOrBuilder()
The span of a leaf node of a tree
optional .edu.stanford.nlp.pipeline.Span span = 29;boolean hasSentiment()
The final sentiment of the sentence
optional string sentiment = 30;java.lang.String getSentiment()
The final sentiment of the sentence
optional string sentiment = 30;com.google.protobuf.ByteString getSentimentBytes()
The final sentiment of the sentence
optional string sentiment = 30;boolean hasQuotationIndex()
The index of the quotation this token refers to
optional int32 quotationIndex = 31;int getQuotationIndex()
The index of the quotation this token refers to
optional int32 quotationIndex = 31;boolean hasConllUFeatures()
optional .edu.stanford.nlp.pipeline.MapStringString conllUFeatures = 32;CoreNLPProtos.MapStringString getConllUFeatures()
optional .edu.stanford.nlp.pipeline.MapStringString conllUFeatures = 32;CoreNLPProtos.MapStringStringOrBuilder getConllUFeaturesOrBuilder()
optional .edu.stanford.nlp.pipeline.MapStringString conllUFeatures = 32;boolean hasCoarseTag()
The coarse POS tag (used to store the UPOS tag)
optional string coarseTag = 33;java.lang.String getCoarseTag()
The coarse POS tag (used to store the UPOS tag)
optional string coarseTag = 33;com.google.protobuf.ByteString getCoarseTagBytes()
The coarse POS tag (used to store the UPOS tag)
optional string coarseTag = 33;boolean hasConllUTokenSpan()
optional .edu.stanford.nlp.pipeline.Span conllUTokenSpan = 34;CoreNLPProtos.Span getConllUTokenSpan()
optional .edu.stanford.nlp.pipeline.Span conllUTokenSpan = 34;CoreNLPProtos.SpanOrBuilder getConllUTokenSpanOrBuilder()
optional .edu.stanford.nlp.pipeline.Span conllUTokenSpan = 34;boolean hasConllUMisc()
optional string conllUMisc = 35;java.lang.String getConllUMisc()
optional string conllUMisc = 35;com.google.protobuf.ByteString getConllUMiscBytes()
optional string conllUMisc = 35;boolean hasConllUSecondaryDeps()
optional .edu.stanford.nlp.pipeline.MapStringString conllUSecondaryDeps = 36;CoreNLPProtos.MapStringString getConllUSecondaryDeps()
optional .edu.stanford.nlp.pipeline.MapStringString conllUSecondaryDeps = 36;CoreNLPProtos.MapStringStringOrBuilder getConllUSecondaryDepsOrBuilder()
optional .edu.stanford.nlp.pipeline.MapStringString conllUSecondaryDeps = 36;boolean hasWikipediaEntity()
optional string wikipediaEntity = 37;java.lang.String getWikipediaEntity()
optional string wikipediaEntity = 37;com.google.protobuf.ByteString getWikipediaEntityBytes()
optional string wikipediaEntity = 37;boolean hasIsNewline()
optional bool isNewline = 38;boolean getIsNewline()
optional bool isNewline = 38;boolean hasGender()
Fields set by other annotators in CoreNLP
optional string gender = 51;java.lang.String getGender()
Fields set by other annotators in CoreNLP
optional string gender = 51;com.google.protobuf.ByteString getGenderBytes()
Fields set by other annotators in CoreNLP
optional string gender = 51;boolean hasTrueCase()
true case type of token
optional string trueCase = 52;java.lang.String getTrueCase()
true case type of token
optional string trueCase = 52;com.google.protobuf.ByteString getTrueCaseBytes()
true case type of token
optional string trueCase = 52;boolean hasTrueCaseText()
true case gloss of token
optional string trueCaseText = 53;java.lang.String getTrueCaseText()
true case gloss of token
optional string trueCaseText = 53;com.google.protobuf.ByteString getTrueCaseTextBytes()
true case gloss of token
optional string trueCaseText = 53;boolean hasChineseChar()
Chinese character info
optional string chineseChar = 54;java.lang.String getChineseChar()
Chinese character info
optional string chineseChar = 54;com.google.protobuf.ByteString getChineseCharBytes()
Chinese character info
optional string chineseChar = 54;boolean hasChineseSeg()
optional string chineseSeg = 55;java.lang.String getChineseSeg()
optional string chineseSeg = 55;com.google.protobuf.ByteString getChineseSegBytes()
optional string chineseSeg = 55;boolean hasChineseXMLChar()
optional string chineseXMLChar = 60;java.lang.String getChineseXMLChar()
optional string chineseXMLChar = 60;com.google.protobuf.ByteString getChineseXMLCharBytes()
optional string chineseXMLChar = 60;boolean hasArabicSeg()
Arabic character info
optional string arabicSeg = 76;java.lang.String getArabicSeg()
Arabic character info
optional string arabicSeg = 76;com.google.protobuf.ByteString getArabicSegBytes()
Arabic character info
optional string arabicSeg = 76;boolean hasSectionName()
Section info
optional string sectionName = 56;java.lang.String getSectionName()
Section info
optional string sectionName = 56;com.google.protobuf.ByteString getSectionNameBytes()
Section info
optional string sectionName = 56;boolean hasSectionAuthor()
optional string sectionAuthor = 57;java.lang.String getSectionAuthor()
optional string sectionAuthor = 57;com.google.protobuf.ByteString getSectionAuthorBytes()
optional string sectionAuthor = 57;boolean hasSectionDate()
optional string sectionDate = 58;java.lang.String getSectionDate()
optional string sectionDate = 58;com.google.protobuf.ByteString getSectionDateBytes()
optional string sectionDate = 58;boolean hasSectionEndLabel()
optional string sectionEndLabel = 59;java.lang.String getSectionEndLabel()
optional string sectionEndLabel = 59;com.google.protobuf.ByteString getSectionEndLabelBytes()
optional string sectionEndLabel = 59;boolean hasParent()
French tokens have parents
optional string parent = 61;java.lang.String getParent()
French tokens have parents
optional string parent = 61;com.google.protobuf.ByteString getParentBytes()
French tokens have parents
optional string parent = 61;java.util.List<java.lang.Integer> getCorefMentionIndexList()
mention index info
repeated uint32 corefMentionIndex = 64;int getCorefMentionIndexCount()
mention index info
repeated uint32 corefMentionIndex = 64;int getCorefMentionIndex(int index)
mention index info
repeated uint32 corefMentionIndex = 64;index - The index of the element to return.boolean hasEntityMentionIndex()
optional uint32 entityMentionIndex = 65;int getEntityMentionIndex()
optional uint32 entityMentionIndex = 65;boolean hasIsMWT()
mwt stuff
optional bool isMWT = 67;boolean getIsMWT()
mwt stuff
optional bool isMWT = 67;boolean hasIsFirstMWT()
optional bool isFirstMWT = 68;boolean getIsFirstMWT()
optional bool isFirstMWT = 68;boolean hasMwtText()
optional string mwtText = 69;java.lang.String getMwtText()
optional string mwtText = 69;com.google.protobuf.ByteString getMwtTextBytes()
optional string mwtText = 69;boolean hasMwtMisc()
setting this to a map might be nice, but there are a couple issues for one, there can be values with no key for another, it's a pain to correctly parse, since different treebanks can have different standards for how to write out the misc field
optional string mwtMisc = 78;java.lang.String getMwtMisc()
setting this to a map might be nice, but there are a couple issues for one, there can be values with no key for another, it's a pain to correctly parse, since different treebanks can have different standards for how to write out the misc field
optional string mwtMisc = 78;com.google.protobuf.ByteString getMwtMiscBytes()
setting this to a map might be nice, but there are a couple issues for one, there can be values with no key for another, it's a pain to correctly parse, since different treebanks can have different standards for how to write out the misc field
optional string mwtMisc = 78;boolean hasNumericValue()
number info
optional uint64 numericValue = 70;long getNumericValue()
number info
optional uint64 numericValue = 70;boolean hasNumericType()
optional string numericType = 71;java.lang.String getNumericType()
optional string numericType = 71;com.google.protobuf.ByteString getNumericTypeBytes()
optional string numericType = 71;boolean hasNumericCompositeValue()
optional uint64 numericCompositeValue = 72;long getNumericCompositeValue()
optional uint64 numericCompositeValue = 72;boolean hasNumericCompositeType()
optional string numericCompositeType = 73;java.lang.String getNumericCompositeType()
optional string numericCompositeType = 73;com.google.protobuf.ByteString getNumericCompositeTypeBytes()
optional string numericCompositeType = 73;boolean hasCodepointOffsetBegin()
optional uint32 codepointOffsetBegin = 74;int getCodepointOffsetBegin()
optional uint32 codepointOffsetBegin = 74;boolean hasCodepointOffsetEnd()
optional uint32 codepointOffsetEnd = 75;int getCodepointOffsetEnd()
optional uint32 codepointOffsetEnd = 75;boolean hasIndex()
Most serialized annotations will not have this Some code paths may not correctly process this if serialized, since many places will read the index off the position in a sentence In particular, deserializing a Document using ProtobufAnnotationSerializer will clobber any index value But Semgrex and Ssurgeon in particular need a way to pass around nodes where the node's index is not strictly 1, 2, 3, ... thanks to the empty nodes in UD treebanks such as English EWT or Estonian EWT (not related to each other)
optional uint32 index = 79;int getIndex()
Most serialized annotations will not have this Some code paths may not correctly process this if serialized, since many places will read the index off the position in a sentence In particular, deserializing a Document using ProtobufAnnotationSerializer will clobber any index value But Semgrex and Ssurgeon in particular need a way to pass around nodes where the node's index is not strictly 1, 2, 3, ... thanks to the empty nodes in UD treebanks such as English EWT or Estonian EWT (not related to each other)
optional uint32 index = 79;boolean hasEmptyIndex()
optional uint32 emptyIndex = 80;int getEmptyIndex()
optional uint32 emptyIndex = 80;