edu.nyu.jet.refres

Class MaxEntResolve

java.lang.Object

edu.nyu.jet.refres.MaxEntResolve

public class MaxEntResolve
extends Object

contains procedures for reference resolution within a document. Name and noun resolution are rule based, using methods from class Resolve; pronoun resolution is statistically based, using a maximum-entropy classifier.

Field Summary

Fields

Modifier and Type	Field and Description
static boolean	linkAppositesAndPredComps set to true if apposites and predicate complements should be linked coreferentially.
static boolean	nameTypeMatch set to true if a pair of names can be linked only if they have been assigned the same named entity type.
static SentenceSet	sentenceSet the set of sentences in the document
static boolean	trace

Constructor Summary

Constructors

Constructor and Description
MaxEntResolve()

Method Summary

Methods

Modifier and Type	Method and Description
static void	main(String[] args) trains the pronoun coreference model from a training collection of coreference-annotated documents.
static float	matchPronoun(Document doc, Annotation anaphor, String pronoun, Annotation entity, boolean parse, ArrayList<Annotation> antecedents) return the probability that pronoun 'pronoun' is a possible anaphor for entity 'ent' (this also includes possessive pronouns of category 'det', and headless noun phrases of category 'np').
static void	references(Document doc, Span span) Resolve.references resolves the mentions (noun groups) in span of Document doc.
static void	references(Document doc, Span span, Vector mentions, Vector clauses)
static void	train(Document doc) trains coreference from a document doc marked with coref tags.
static void	train(String directory, String fileList, int limit) trains coreference from a set of files marked with coref tags.
static void	trainOnMention(Document doc, Annotation mention) add information on mention mention and its possible antecedents to the training data which will be used to train the coreference model.

Methods inherited from class java.lang.Object

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

Field Detail

sentenceSet

public static SentenceSet sentenceSet

the set of sentences in the document

linkAppositesAndPredComps

public static boolean linkAppositesAndPredComps

set to true if apposites and predicate complements should be linked coreferentially.

nameTypeMatch

public static boolean nameTypeMatch

set to true if a pair of names can be linked only if they have been assigned the same named entity type.

trace

public static boolean trace

Constructor Detail

MaxEntResolve

public MaxEntResolve()

Method Detail

references

public static void references(Document doc,
              Span span)

Resolve.references resolves the mentions (noun groups) in span of Document doc. It generates entity annotations, corresponding to one or more mentions in the document which are coreferential. In addition, for every event annotation in span, it generates an r-event annotation in which each feature pointing to a mention is replaced by the entity to which that mention has been resolved.

references

public static void references(Document doc,
              Span span,
              Vector mentions,
              Vector clauses)

train

public static void train(String directory,
         String fileList,
         int limit)
                  throws IOException

trains coreference from a set of files marked with coref tags.

Parameters:

directory - the directory containing the marked files

fileList - a list of text file names, one per line.

Throws:

IOException

train

public static void train(Document doc)

trains coreference from a document doc marked with coref tags.

trainOnMention

public static void trainOnMention(Document doc,
                  Annotation mention)

add information on mention mention and its possible antecedents to the training data which will be used to train the coreference model.

matchPronoun

public static float matchPronoun(Document doc,
                 Annotation anaphor,
                 String pronoun,
                 Annotation entity,
                 boolean parse,
                 ArrayList<Annotation> antecedents)

return the probability that pronoun 'pronoun' is a possible anaphor for entity 'ent' (this also includes possessive pronouns of category 'det', and headless noun phrases of category 'np').

main

public static void main(String[] args)
                 throws IOException

trains the pronoun coreference model from a training collection of coreference-annotated documents.

Throws:

IOException