edu.stanford.nlp.ie.machinereading.domains.ace.reader
Class AceDocument

java.lang.Object
  edu.stanford.nlp.ie.machinereading.domains.ace.reader.AceElement
      edu.stanford.nlp.ie.machinereading.domains.ace.reader.AceDocument

public class AceDocument
extends AceElement

Stores the ACE elements annotated in this document

Field Summary

static java.lang.String	ORIG_EXT
static java.lang.String	XML_EXT

Fields inherited from class edu.stanford.nlp.ie.machinereading.domains.ace.reader.AceElement

mId

Constructor Summary

AceDocument(java.lang.String id)

Method Summary

void	addEntity(AceEntity e)
void	addEntityMention(AceEntityMention em)
void	addEvent(AceEvent r)
void	addEventMention(AceEventMention e)
void	addRelation(AceRelation r)
void	addRelationMention(AceRelationMention e)
void	addToken(AceToken t)
void	constructSentenceRelationMentions()
int	countCommas(int start, int end)
int	countVerbs(int start, int end)
int	findChunkEnd(int pos)
int	findChunkStart(int pos)
java.util.ArrayList<java.util.ArrayList<AceEntityMention>>	getAllEntityMentions()
java.util.ArrayList<java.util.ArrayList<AceEventMention>>	getAllEventMentions()
java.util.ArrayList<java.util.ArrayList<AceRelationMention>>	getAllRelationMentions()
AceEntity	getEntity(java.lang.String id)
AceEntityMention	getEntityMention(java.lang.String id)
java.util.HashMap<java.lang.String,AceEntityMention>	getEntityMentions()
java.util.ArrayList<AceEntityMention>	getEntityMentions(int sent)
AceEvent	getEvent(java.lang.String id)
AceEventMention	getEventMention(java.lang.String id)
java.util.HashMap<java.lang.String,AceEventMention>	getEventMentions()
java.util.ArrayList<AceEventMention>	getEventMentions(int sent)
java.util.Set<java.lang.String>	getKeySetEntities()
java.lang.String	getPrefix()
AceRelation	getRelation(java.lang.String id)
AceRelationMention	getRelationMention(java.lang.String id)
java.util.HashMap<java.lang.String,AceRelationMention>	getRelationMentions()
java.util.ArrayList<AceRelationMention>	getRelationMentions(int sent)
java.util.List<AceToken>	getSentence(int index)
int	getSentenceCount()
java.util.List<java.util.List<AceToken>>	getSentences()
AceToken	getToken(int i)
int	getTokenCount()
boolean	isApposition(int left, int right)
boolean	isChunkHead(int pos)
AceCharSeq	makeCharSeq(int startToken, int endToken)
void	matchCharSeqs(java.lang.String filePrefix) Matches all relevant mentions, i.e.
static AceDocument	parseDocument(java.lang.String prefix, boolean usePredictedBoundaries) Parses an ACE document.
static AceDocument	parseDocument(java.lang.String prefix, boolean usePredictedBoundaries, java.lang.String AceVersion)
boolean	sameChunk(int left, int right) Verifies if the two tokens are part of the same chunk
void	setPrefix(java.lang.String p)
void	setSentences(java.util.List<java.util.List<AceToken>> sentences)
void	setSource(java.lang.String p)
java.lang.String	toString()
java.lang.String	toXml(int offset)

Methods inherited from class edu.stanford.nlp.ie.machinereading.domains.ace.reader.AceElement

appendOffset, getId

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Field Detail

XML_EXT

public static final java.lang.String XML_EXT

See Also:

Constant Field Values

ORIG_EXT

public static final java.lang.String ORIG_EXT

See Also:

Constant Field Values

Constructor Detail

AceDocument

public AceDocument(java.lang.String id)

Method Detail

setPrefix

public void setPrefix(java.lang.String p)

getPrefix

public java.lang.String getPrefix()

setSource

public void setSource(java.lang.String p)

getSentenceCount

public int getSentenceCount()

getEntityMentions

public java.util.ArrayList<AceEntityMention> getEntityMentions(int sent)

getAllEntityMentions

public java.util.ArrayList<java.util.ArrayList<AceEntityMention>> getAllEntityMentions()

getRelationMentions

public java.util.ArrayList<AceRelationMention> getRelationMentions(int sent)

getAllRelationMentions

public java.util.ArrayList<java.util.ArrayList<AceRelationMention>> getAllRelationMentions()

getEventMentions

public java.util.ArrayList<AceEventMention> getEventMentions(int sent)

getAllEventMentions

public java.util.ArrayList<java.util.ArrayList<AceEventMention>> getAllEventMentions()

getEntity

public AceEntity getEntity(java.lang.String id)

getKeySetEntities

public java.util.Set<java.lang.String> getKeySetEntities()

addEntity

public void addEntity(AceEntity e)

getEntityMentions

public java.util.HashMap<java.lang.String,AceEntityMention> getEntityMentions()

getEntityMention

public AceEntityMention getEntityMention(java.lang.String id)

addEntityMention

public void addEntityMention(AceEntityMention em)

getRelation

public AceRelation getRelation(java.lang.String id)

addRelation

public void addRelation(AceRelation r)

getRelationMentions

public java.util.HashMap<java.lang.String,AceRelationMention> getRelationMentions()

getRelationMention

public AceRelationMention getRelationMention(java.lang.String id)

addRelationMention

public void addRelationMention(AceRelationMention e)

getEvent

public AceEvent getEvent(java.lang.String id)

addEvent

public void addEvent(AceEvent r)

getEventMentions

public java.util.HashMap<java.lang.String,AceEventMention> getEventMentions()

getEventMention

public AceEventMention getEventMention(java.lang.String id)

addEventMention

public void addEventMention(AceEventMention e)

addToken

public void addToken(AceToken t)

getTokenCount

public int getTokenCount()

getToken

public AceToken getToken(int i)

getSentence

public java.util.List<AceToken> getSentence(int index)

getSentences

public java.util.List<java.util.List<AceToken>> getSentences()

setSentences

public void setSentences(java.util.List<java.util.List<AceToken>> sentences)

toString

public java.lang.String toString()

Overrides:

toString in class java.lang.Object

toXml

public java.lang.String toXml(int offset)

matchCharSeqs

public void matchCharSeqs(java.lang.String filePrefix)

Matches all relevant mentions, i.e. entities and anchors, to tokens Note: entity mentions may match with multiple tokens!

parseDocument

public static AceDocument parseDocument(java.lang.String prefix,
                                        boolean usePredictedBoundaries)
                                 throws java.io.IOException,
                                        org.xml.sax.SAXException,
                                        javax.xml.parsers.ParserConfigurationException

Parses an ACE document. Works in the following steps: (a) reads both the XML annotations; (b) reads the tokens; (c) matches the tokens against the annotations (d) constructs mSentenceEntityMentions and mRelationEntityMentions

Throws:

java.io.IOException

org.xml.sax.SAXException

javax.xml.parsers.ParserConfigurationException

parseDocument

public static AceDocument parseDocument(java.lang.String prefix,
                                        boolean usePredictedBoundaries,
                                        java.lang.String AceVersion)
                                 throws java.io.IOException,
                                        org.xml.sax.SAXException,
                                        javax.xml.parsers.ParserConfigurationException

Throws:

java.io.IOException

org.xml.sax.SAXException

javax.xml.parsers.ParserConfigurationException

constructSentenceRelationMentions

public void constructSentenceRelationMentions()

sameChunk

public boolean sameChunk(int left,
                         int right)

Verifies if the two tokens are part of the same chunk

isChunkHead

public boolean isChunkHead(int pos)

findChunkEnd

public int findChunkEnd(int pos)

findChunkStart

public int findChunkStart(int pos)

isApposition

public boolean isApposition(int left,
                            int right)

countVerbs

public int countVerbs(int start,
                      int end)

countCommas

public int countCommas(int start,
                       int end)

makeCharSeq

public AceCharSeq makeCharSeq(int startToken,
                              int endToken)