public class Document
extends java.lang.Object
implements java.io.Serializable
Modifier and Type | Class and Description |
---|---|
static class |
Document.DocType |
Modifier and Type | Field and Description |
---|---|
java.util.Map<Pair<java.lang.Integer,java.lang.Integer>,java.lang.Boolean> |
acronymCache |
java.util.Map<Mention,IntTuple> |
allPositions |
Annotation |
annotation
Document annotation
|
CoNLLDocumentReader.CoNLLDocument |
conllDoc
for conll shared task 2011
|
java.util.Map<java.lang.Integer,CorefCluster> |
corefClusters
Clusters for coreferent mentions
|
java.util.Map<java.lang.String,java.lang.String> |
docInfo
Additional information about the document.
|
Document.DocType |
docType
The type of document: conversational or article
|
java.util.Set<Triple<java.lang.Integer,java.lang.Integer,java.lang.Integer>> |
filterMentionSet |
java.util.Map<java.lang.Integer,CorefCluster> |
goldCorefClusters
Gold Clusters for coreferent mentions
|
java.util.List<java.util.List<Mention>> |
goldMentions
The list of gold mentions
|
java.util.Map<java.lang.Integer,Mention> |
goldMentionsByID |
int |
maxUtter |
java.util.Map<IntTuple,Mention> |
mentionheadPositions |
int |
numParagraph |
int |
numSentences |
java.util.Map<Mention,IntTuple> |
positions
Position of each mention in the input matrix
Each mention occurrence with sentence # and position within sentence
(Nth mention, not Nth token)
|
java.util.List<java.util.List<Mention>> |
predictedMentions
The list of predicted mentions
|
java.util.Map<java.lang.Integer,Mention> |
predictedMentionsByID
All mentions in a document mentionID -> mention
|
java.util.Set<Mention> |
roleSet
Set of roles (in role apposition) in a document
|
boolean |
speakerInfoGiven |
java.util.Map<java.lang.String,SpeakerInfo> |
speakerInfoMap
Map of speaker name/id to speaker info
the key is the value of the variable 'speakers'
|
java.util.Set<Pair<java.lang.Integer,java.lang.Integer>> |
speakerPairs
Pair of mention id, and the mention's speaker id
the second value is the "speaker mention"'s id.
|
java.util.Map<java.lang.Integer,java.lang.String> |
speakers
UtteranceAnnotation -> String (speaker): mention ID or speaker string
e.g., the value can be "34" (mentionID), "Larry" (speaker string), or "PER3" (autoassigned speaker string)
|
Constructor and Description |
---|
Document() |
Document(Annotation anno,
java.util.List<java.util.List<Mention>> predictedMentions,
java.util.List<java.util.List<Mention>> goldMentions) |
Document(InputDoc input,
java.util.List<java.util.List<Mention>> mentions) |
Modifier and Type | Method and Description |
---|---|
void |
addIncompatible(Mention m1,
Mention m2) |
protected void |
extractGoldLinks()
Extract gold coref link information
|
java.util.List<Pair<IntTuple,IntTuple>> |
getGoldLinks() |
java.util.List<java.util.List<Mention>> |
getOrderedMentions()
return the list of predicted mentions
|
java.util.List<java.util.List<java.lang.String[]>> |
getSentenceWordLists()
Returns list of sentences, where token in the sentence is a list of strings (tags) associated with the sentence
|
SpeakerInfo |
getSpeakerInfo(java.lang.String speaker) |
boolean |
isCoref(Mention m1,
Mention m2) |
boolean |
isIncompatible(CorefCluster c1,
CorefCluster c2) |
boolean |
isIncompatible(Mention m1,
Mention m2) |
void |
mergeAcronymCache(CorefCluster to,
CorefCluster from) |
void |
mergeIncompatibles(CorefCluster to,
CorefCluster from) |
int |
numberOfSpeakers() |
public Document.DocType docType
public Annotation annotation
public CoNLLDocumentReader.CoNLLDocument conllDoc
public java.util.List<java.util.List<Mention>> goldMentions
public java.util.List<java.util.List<Mention>> predictedMentions
public java.util.Map<java.lang.Integer,CorefCluster> corefClusters
public java.util.Map<java.lang.Integer,CorefCluster> goldCorefClusters
public java.util.Map<java.lang.Integer,Mention> predictedMentionsByID
public java.util.Map<java.lang.Integer,Mention> goldMentionsByID
public java.util.Set<Mention> roleSet
public java.util.Map<Mention,IntTuple> positions
public java.util.Map<java.lang.Integer,java.lang.String> speakers
public java.util.Set<Pair<java.lang.Integer,java.lang.Integer>> speakerPairs
public boolean speakerInfoGiven
public int maxUtter
public int numParagraph
public int numSentences
public java.util.Map<Pair<java.lang.Integer,java.lang.Integer>,java.lang.Boolean> acronymCache
public java.util.Map<java.lang.String,SpeakerInfo> speakerInfoMap
public java.util.Map<java.lang.String,java.lang.String> docInfo
public java.util.Set<Triple<java.lang.Integer,java.lang.Integer,java.lang.Integer>> filterMentionSet
public Document()
public Document(Annotation anno, java.util.List<java.util.List<Mention>> predictedMentions, java.util.List<java.util.List<Mention>> goldMentions)
public java.util.List<java.util.List<Mention>> getOrderedMentions()
public java.util.List<java.util.List<java.lang.String[]>> getSentenceWordLists()
public boolean isIncompatible(CorefCluster c1, CorefCluster c2)
public void mergeIncompatibles(CorefCluster to, CorefCluster from)
public void mergeAcronymCache(CorefCluster to, CorefCluster from)
protected void extractGoldLinks()
public SpeakerInfo getSpeakerInfo(java.lang.String speaker)
public int numberOfSpeakers()