edu.stanford.nlp.coref.data

Class Dictionaries

java.lang.Object

edu.stanford.nlp.coref.data.Dictionaries

public class Dictionaries
extends java.lang.Object

Stores various data used for coreference. TODO: get rid of dependence on HybridCorefProperties

Author:

Heeyoung Lee

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	Dictionaries.Animacy
static class	Dictionaries.Gender
static class	Dictionaries.MentionType
static class	Dictionaries.Number
static class	Dictionaries.Person

Field Summary

Fields

Modifier and Type	Field and Description
java.util.Set<java.lang.String>	allPronouns
java.util.Set<java.lang.String>	animatePronouns
java.util.Set<java.lang.String>	animateWords
java.util.Set<java.lang.String>	copulas
java.util.ArrayList<Counter<Pair<java.lang.String,java.lang.String>>>	corefDict
Counter<Pair<java.lang.String,java.lang.String>>	corefDictPMI
java.util.Set<java.lang.String>	countries
java.util.Set<java.lang.String>	dateTimePronouns
java.util.Set<java.lang.String>	demonymSet
java.util.Set<java.lang.String>	determiners
Counter<java.lang.String>	dictScore
int	dimVector
java.util.Set<java.lang.String>	facilityVehicleWeaponPronouns
java.util.Set<java.lang.String>	femalePronouns
java.util.Set<java.lang.String>	femaleWords
java.util.Set<java.lang.String>	firstPersonPronouns
java.util.Map<java.util.List<java.lang.String>,Dictionaries.Gender>	genderNumber
java.util.Set<java.lang.String>	GPEPronouns
java.util.Set<java.lang.String>	inanimatePronouns
java.util.Set<java.lang.String>	inanimateWords
java.util.Set<java.lang.String>	indefinitePronouns
java.util.Set<java.lang.String>	interrogativePronouns
java.util.Set<java.lang.String>	locationPronouns
java.util.Set<java.lang.String>	malePronouns
java.util.Set<java.lang.String>	maleWords
java.util.Set<java.lang.String>	miscPronouns
java.util.Set<java.lang.String>	modals
java.util.Set<java.lang.String>	moneyPercentNumberPronouns
java.util.Map<java.lang.String,Counter<java.lang.String>>	NE_signatures
java.util.Set<java.lang.String>	neg_relations
java.util.Set<java.lang.String>	negations
java.util.Set<java.lang.String>	neutralPronouns
java.util.Set<java.lang.String>	neutralWords
java.util.Set<java.lang.String>	nonWords
java.util.Set<java.lang.String>	notOrganizationPRP
java.util.Set<java.lang.String>	organizationPronouns
java.util.Set<java.lang.String>	otherPronouns
java.util.Set<java.lang.String>	parts
java.util.Set<java.lang.String>	personPronouns
java.util.Set<java.lang.String>	pluralPronouns
java.util.Set<java.lang.String>	pluralWords
java.util.Set<java.lang.String>	possessivePronouns
java.util.Set<java.lang.String>	quantifiers
java.util.Set<java.lang.String>	quantifiers2
java.util.Set<java.lang.String>	reflexivePronouns
java.util.Set<java.lang.String>	relativePronouns
java.util.Set<java.lang.String>	removeChars
java.util.Set<java.lang.String>	removeWords
java.util.Set<java.lang.String>	reportNoun
java.util.Set<java.lang.String>	reportVerb
java.util.Set<java.lang.String>	secondPersonPronouns
java.util.Set<java.lang.String>	singularPronouns
java.util.Set<java.lang.String>	singularWords
java.util.Map<java.lang.String,java.lang.String>	statesAbbreviation
java.util.Set<java.lang.String>	statesAndProvinces
java.util.Set<java.lang.String>	stopWords
java.util.Map<java.lang.String,java.lang.String>	strToEntity
java.util.Set<java.lang.String>	temporals
java.util.Set<java.lang.String>	thirdPersonPronouns
java.util.Set<java.lang.String>	titleWords
java.util.Set<java.lang.String>	transparentNouns
VectorMap	vectors

Constructor Summary

Constructors

Constructor and Description
Dictionaries()
Dictionaries(java.util.Properties props)
Dictionaries(java.lang.String language, java.lang.String demonymWords, java.lang.String animateWords, java.lang.String inanimateWords, java.lang.String maleWords, java.lang.String neutralWords, java.lang.String femaleWords, java.lang.String pluralWords, java.lang.String singularWords, java.lang.String statesWords, java.lang.String genderNumber, java.lang.String countries, java.lang.String states, boolean loadCorefDict, java.lang.String[] corefDictFiles, java.lang.String corefDictPMIFile, java.lang.String signaturesFile)

Method Summary

Modifier and Type	Method and Description
java.util.Set<java.lang.String>	getDemonyms(java.lang.String name) Returns a set of demonyms for a country (or city or region).
boolean	isAdjectivalDemonym(java.lang.String token) Returns whether this mention (possibly multi-word) is the adjectival form of a demonym, like "African" or "Iraqi".
void	loadSemantics(java.util.Properties props)
java.lang.String	lookupCanonicalAmericanStateName(java.lang.String name) If the input string is an abbreviation of a U.S.
static java.lang.String	signature(java.util.Properties props)

Methods inherited from class java.lang.Object

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

Field Detail

reportVerb

public java.util.Set<java.lang.String> reportVerb

reportNoun

public java.util.Set<java.lang.String> reportNoun

nonWords

public java.util.Set<java.lang.String> nonWords

copulas

public java.util.Set<java.lang.String> copulas

quantifiers

public java.util.Set<java.lang.String> quantifiers

parts

public java.util.Set<java.lang.String> parts

temporals

public java.util.Set<java.lang.String> temporals

femalePronouns

public java.util.Set<java.lang.String> femalePronouns

malePronouns

public java.util.Set<java.lang.String> malePronouns

neutralPronouns

public java.util.Set<java.lang.String> neutralPronouns

possessivePronouns

public java.util.Set<java.lang.String> possessivePronouns

otherPronouns

public java.util.Set<java.lang.String> otherPronouns

thirdPersonPronouns

public java.util.Set<java.lang.String> thirdPersonPronouns

secondPersonPronouns

public java.util.Set<java.lang.String> secondPersonPronouns

firstPersonPronouns

public java.util.Set<java.lang.String> firstPersonPronouns

moneyPercentNumberPronouns

public java.util.Set<java.lang.String> moneyPercentNumberPronouns

dateTimePronouns

public java.util.Set<java.lang.String> dateTimePronouns

organizationPronouns

public java.util.Set<java.lang.String> organizationPronouns

locationPronouns

public java.util.Set<java.lang.String> locationPronouns

inanimatePronouns

public java.util.Set<java.lang.String> inanimatePronouns

animatePronouns

public java.util.Set<java.lang.String> animatePronouns

indefinitePronouns

public java.util.Set<java.lang.String> indefinitePronouns

relativePronouns

public java.util.Set<java.lang.String> relativePronouns

interrogativePronouns

public java.util.Set<java.lang.String> interrogativePronouns

GPEPronouns

public java.util.Set<java.lang.String> GPEPronouns

pluralPronouns

public java.util.Set<java.lang.String> pluralPronouns

singularPronouns

public java.util.Set<java.lang.String> singularPronouns

facilityVehicleWeaponPronouns

public java.util.Set<java.lang.String> facilityVehicleWeaponPronouns

miscPronouns

public java.util.Set<java.lang.String> miscPronouns

reflexivePronouns

public java.util.Set<java.lang.String> reflexivePronouns

transparentNouns

public java.util.Set<java.lang.String> transparentNouns

stopWords

public java.util.Set<java.lang.String> stopWords

notOrganizationPRP

public java.util.Set<java.lang.String> notOrganizationPRP

quantifiers2

public java.util.Set<java.lang.String> quantifiers2

determiners

public java.util.Set<java.lang.String> determiners

negations

public java.util.Set<java.lang.String> negations

neg_relations

public java.util.Set<java.lang.String> neg_relations

modals

public java.util.Set<java.lang.String> modals

titleWords

public java.util.Set<java.lang.String> titleWords

removeWords

public java.util.Set<java.lang.String> removeWords

removeChars

public java.util.Set<java.lang.String> removeChars

personPronouns

public final java.util.Set<java.lang.String> personPronouns

allPronouns

public final java.util.Set<java.lang.String> allPronouns

statesAbbreviation

public final java.util.Map<java.lang.String,java.lang.String> statesAbbreviation

demonymSet

public final java.util.Set<java.lang.String> demonymSet

countries

public final java.util.Set<java.lang.String> countries

statesAndProvinces

public final java.util.Set<java.lang.String> statesAndProvinces

neutralWords

public final java.util.Set<java.lang.String> neutralWords

femaleWords

public final java.util.Set<java.lang.String> femaleWords

maleWords

public final java.util.Set<java.lang.String> maleWords

pluralWords

public final java.util.Set<java.lang.String> pluralWords

singularWords

public final java.util.Set<java.lang.String> singularWords

inanimateWords

public final java.util.Set<java.lang.String> inanimateWords

animateWords

public final java.util.Set<java.lang.String> animateWords

genderNumber

public final java.util.Map<java.util.List<java.lang.String>,Dictionaries.Gender> genderNumber

corefDict

public final java.util.ArrayList<Counter<Pair<java.lang.String,java.lang.String>>> corefDict

corefDictPMI

public final Counter<Pair<java.lang.String,java.lang.String>> corefDictPMI

NE_signatures

public final java.util.Map<java.lang.String,Counter<java.lang.String>> NE_signatures

dimVector

public int dimVector

vectors

public VectorMap vectors

strToEntity

public java.util.Map<java.lang.String,java.lang.String> strToEntity

dictScore

public Counter<java.lang.String> dictScore

Constructor Detail

Dictionaries

public Dictionaries(java.util.Properties props)
             throws java.lang.ClassNotFoundException,
                    java.io.IOException

Throws:

java.lang.ClassNotFoundException

java.io.IOException

Dictionaries

public Dictionaries(java.lang.String language,
                    java.lang.String demonymWords,
                    java.lang.String animateWords,
                    java.lang.String inanimateWords,
                    java.lang.String maleWords,
                    java.lang.String neutralWords,
                    java.lang.String femaleWords,
                    java.lang.String pluralWords,
                    java.lang.String singularWords,
                    java.lang.String statesWords,
                    java.lang.String genderNumber,
                    java.lang.String countries,
                    java.lang.String states,
                    boolean loadCorefDict,
                    java.lang.String[] corefDictFiles,
                    java.lang.String corefDictPMIFile,
                    java.lang.String signaturesFile)

Dictionaries

public Dictionaries()
             throws java.lang.ClassNotFoundException,
                    java.io.IOException

Throws:

java.lang.ClassNotFoundException

java.io.IOException

Method Detail

lookupCanonicalAmericanStateName

public java.lang.String lookupCanonicalAmericanStateName(java.lang.String name)

If the input string is an abbreviation of a U.S. state name or the canonical name, the canonical name is returned. Otherwise, null is returned.

Parameters:

name - Is treated as a cased string. ME != me

getDemonyms

public java.util.Set<java.lang.String> getDemonyms(java.lang.String name)

Returns a set of demonyms for a country (or city or region).

Parameters:

name - Some string perhaps a country name like "Australia"

Returns:

A Set of demonym Strings, perhaps { "Australian", "Aussie", "Aussies" }. If none are known (including if the argument isn't a country/region name, then the empty set will be returned.

isAdjectivalDemonym

public boolean isAdjectivalDemonym(java.lang.String token)

Returns whether this mention (possibly multi-word) is the adjectival form of a demonym, like "African" or "Iraqi". True if it is an adjectival form, even if also a name for a person of that country (such as "Iraqi").

loadSemantics

public void loadSemantics(java.util.Properties props)
                   throws java.lang.ClassNotFoundException,
                          java.io.IOException

Throws:

java.lang.ClassNotFoundException

java.io.IOException

signature

public static java.lang.String signature(java.util.Properties props)