|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
java.lang.Object edu.illinois.cs.cogcomp.lbj.coref.features.Gazetteers
public class Gazetteers
A collection of gazetteers. Each gazetteer is a set of items. Gazetteers whose names end in CS are case-sensitive; the others contain only lowercase items. Any gazetteer may contain ambiguous items, which might appear in multiple gazetteers. For example, "Israel" is a male first name and a country name. All gazetteers will be loaded and kept in memory when any is requested.
Field Summary | |
---|---|
protected static java.util.Set<java.lang.String> |
cities
|
protected static java.util.Set<java.lang.String> |
citiesCS
|
protected static java.util.Set<java.lang.String> |
commonWords
|
protected static java.util.Set<java.lang.String> |
commonWords5
|
protected static java.util.Set<java.lang.String> |
corporations
|
protected static java.util.Set<java.lang.String> |
corporationsCS
|
protected static java.util.Set<java.lang.String> |
countries
|
protected static java.util.Set<java.lang.String> |
countriesCS
|
protected static java.util.Set<java.lang.String> |
countriesDemAdj
|
protected static java.util.Set<java.lang.String> |
countriesDemAdjCS
|
protected static java.util.Set<java.lang.String> |
femaleFirstNames
|
protected static java.util.Set<java.lang.String> |
femaleFirstNamesCS
|
protected static boolean |
gazetteersInitialized
|
protected static java.util.Set<java.lang.String> |
honors
|
protected static java.util.Set<java.lang.String> |
inflectedWords
|
protected static java.util.Set<java.lang.String> |
lastNames
|
protected static java.util.Set<java.lang.String> |
lastNamesCS
|
protected static java.util.Set<java.lang.String> |
lowercaseWords
|
protected static java.util.Set<java.lang.String> |
maleFirstNames
|
protected static java.util.Set<java.lang.String> |
maleFirstNamesCS
|
protected static java.util.Set<java.lang.String> |
orgClosings
|
protected static java.util.Set<java.lang.String> |
pluralNouns
|
protected static java.util.Set<java.lang.String> |
polParties
|
protected static java.util.Set<java.lang.String> |
polPartiesCS
|
protected static java.util.Set<java.lang.String> |
prepositions
|
protected static java.util.Set<java.lang.String> |
pronouns
|
protected static java.util.Set<java.lang.String> |
sayWords
|
protected static java.util.Set<java.lang.String> |
singularNouns
|
protected static java.util.Set<java.lang.String> |
sportTeams
|
protected static java.util.Set<java.lang.String> |
sportTeamsCS
|
protected static java.util.Set<java.lang.String> |
states
|
protected static java.util.Set<java.lang.String> |
statesCS
|
protected static java.util.Set<java.lang.String> |
stopWords
|
protected static java.util.Set<java.lang.String> |
universities
|
protected static java.util.Set<java.lang.String> |
universitiesCS
|
Constructor Summary | |
---|---|
protected |
Gazetteers()
Should not need to construct this static feature collection. |
Method Summary | |
---|---|
static java.util.Set<java.lang.String> |
getCities()
Gets the cities gazetteer. |
static java.util.Set<java.lang.String> |
getCitiesCS()
Gets the case-sensitive cities gazetteer. |
static java.util.Set<java.lang.String> |
getCommonWords()
Gets the common words gazetteer. |
static java.util.Set<java.lang.String> |
getCommonWords5()
Gets the common words appearing more than five times gazetteer. |
static java.util.Set<java.lang.String> |
getCorporations()
Gets the corporations gazetteer. |
static java.util.Set<java.lang.String> |
getCorporationsCS()
Gets the corporations gazetteer. |
static java.util.Set<java.lang.String> |
getCountries()
Gets the countries gazetteer. |
static java.util.Set<java.lang.String> |
getCountriesCS()
Gets the case-sensitive countries gazetteer. |
static java.util.Set<java.lang.String> |
getCountriesDemAdj()
Gets the countries, country adjectives, and country people names gazetteer. |
static java.util.Set<java.lang.String> |
getCountriesDemAdjCS()
Gets the countries, country adjectives, and country people names gazetteer. |
static java.util.Set<java.lang.String> |
getFemaleFirstNames()
Gets the female first names gazetteer. |
static java.util.Set<java.lang.String> |
getFemaleFirstNamesCS()
Gets the case-sensitive male first names gazetteer. |
static java.util.Set<java.lang.String> |
getHonors()
Gets the honorary titles gazetteer. |
static java.util.Set<java.lang.String> |
getInflectedWords()
Gets the inflected words gazetteer. |
static java.util.Set<java.lang.String> |
getLastNames()
Gets the last names gazetteer. |
static java.util.Set<java.lang.String> |
getLastNamesCS()
Gets the case-sensitive last names gazetteer. |
static java.util.Set<java.lang.String> |
getLowercaseWords()
Gets the lowercase words gazetteer. |
static java.util.Set<java.lang.String> |
getMaleFirstNames()
Gets the male first names gazetteer. |
static java.util.Set<java.lang.String> |
getMaleFirstNamesCS()
Gets the case-sensitive male first names gazetteer. |
static java.util.Set<java.lang.String> |
getOrgClosings()
Gets the organization identifier suffixes gazetteer. |
static java.util.Set<java.lang.String> |
getPluralNouns()
Gets the plural nouns gazetteer. |
static java.util.Set<java.lang.String> |
getPolParties()
Gets the political parties gazetteer. |
static java.util.Set<java.lang.String> |
getPrepositions()
Gets the prepositions gazetteer. |
static java.util.Set<java.lang.String> |
getPronouns()
Gets the pronouns gazetteer. |
static java.util.Set<java.lang.String> |
getSayWords()
Gets the say words gazetteer. |
static java.util.Set<java.lang.String> |
getSingularNouns()
Gets the singular nouns gazetteer. |
static java.util.Set<java.lang.String> |
getSportTeams()
Gets the sports teams gazetteer. |
static java.util.Set<java.lang.String> |
getSportTeamsCS()
Gets the sports teams gazetteer. |
static java.util.Set<java.lang.String> |
getStates()
Gets the US states gazetteer. |
static java.util.Set<java.lang.String> |
getStatesCS()
Gets the case-sensitive US states gazetteer. |
static java.util.Set<java.lang.String> |
getStopWords()
Gets the stop words gazetteer. |
static java.util.Set<java.lang.String> |
getUniversities()
Gets the universities gazetteer. |
static java.util.Set<java.lang.String> |
getUniversitiesCS()
Gets the universities gazetteer. |
private static void |
initGazetteers()
Loads the gazetteers from files in the gazetteers directory located in a directory on the classpath. |
protected static java.util.Set<java.lang.String> |
loadLinesAsSet(java.lang.String filename,
boolean lower)
|
Methods inherited from class java.lang.Object |
---|
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
Field Detail |
---|
protected static boolean gazetteersInitialized
protected static java.util.Set<java.lang.String> honors
protected static java.util.Set<java.lang.String> maleFirstNames
protected static java.util.Set<java.lang.String> femaleFirstNames
protected static java.util.Set<java.lang.String> lastNames
protected static java.util.Set<java.lang.String> orgClosings
protected static java.util.Set<java.lang.String> countriesDemAdj
protected static java.util.Set<java.lang.String> countries
protected static java.util.Set<java.lang.String> cities
protected static java.util.Set<java.lang.String> states
protected static java.util.Set<java.lang.String> polParties
protected static java.util.Set<java.lang.String> corporations
protected static java.util.Set<java.lang.String> sportTeams
protected static java.util.Set<java.lang.String> universities
protected static java.util.Set<java.lang.String> inflectedWords
protected static java.util.Set<java.lang.String> lowercaseWords
protected static java.util.Set<java.lang.String> singularNouns
protected static java.util.Set<java.lang.String> pluralNouns
protected static java.util.Set<java.lang.String> sayWords
protected static java.util.Set<java.lang.String> pronouns
protected static java.util.Set<java.lang.String> prepositions
protected static java.util.Set<java.lang.String> stopWords
protected static java.util.Set<java.lang.String> commonWords
protected static java.util.Set<java.lang.String> commonWords5
protected static java.util.Set<java.lang.String> maleFirstNamesCS
protected static java.util.Set<java.lang.String> femaleFirstNamesCS
protected static java.util.Set<java.lang.String> lastNamesCS
protected static java.util.Set<java.lang.String> countriesDemAdjCS
protected static java.util.Set<java.lang.String> countriesCS
protected static java.util.Set<java.lang.String> citiesCS
protected static java.util.Set<java.lang.String> statesCS
protected static java.util.Set<java.lang.String> polPartiesCS
protected static java.util.Set<java.lang.String> corporationsCS
protected static java.util.Set<java.lang.String> sportTeamsCS
protected static java.util.Set<java.lang.String> universitiesCS
Constructor Detail |
---|
protected Gazetteers()
Method Detail |
---|
public static java.util.Set<java.lang.String> getMaleFirstNames()
public static java.util.Set<java.lang.String> getMaleFirstNamesCS()
public static java.util.Set<java.lang.String> getFemaleFirstNames()
public static java.util.Set<java.lang.String> getFemaleFirstNamesCS()
public static java.util.Set<java.lang.String> getLastNames()
public static java.util.Set<java.lang.String> getLastNamesCS()
public static java.util.Set<java.lang.String> getHonors()
public static java.util.Set<java.lang.String> getCities()
public static java.util.Set<java.lang.String> getCitiesCS()
public static java.util.Set<java.lang.String> getStates()
public static java.util.Set<java.lang.String> getStatesCS()
public static java.util.Set<java.lang.String> getCountries()
public static java.util.Set<java.lang.String> getCountriesCS()
public static java.util.Set<java.lang.String> getCountriesDemAdj()
public static java.util.Set<java.lang.String> getCountriesDemAdjCS()
public static java.util.Set<java.lang.String> getPolParties()
public static java.util.Set<java.lang.String> getCorporations()
public static java.util.Set<java.lang.String> getCorporationsCS()
public static java.util.Set<java.lang.String> getOrgClosings()
public static java.util.Set<java.lang.String> getSportTeams()
public static java.util.Set<java.lang.String> getSportTeamsCS()
public static java.util.Set<java.lang.String> getUniversities()
public static java.util.Set<java.lang.String> getUniversitiesCS()
public static java.util.Set<java.lang.String> getStopWords()
public static java.util.Set<java.lang.String> getPrepositions()
public static java.util.Set<java.lang.String> getPronouns()
public static java.util.Set<java.lang.String> getSingularNouns()
public static java.util.Set<java.lang.String> getPluralNouns()
public static java.util.Set<java.lang.String> getSayWords()
public static java.util.Set<java.lang.String> getLowercaseWords()
public static java.util.Set<java.lang.String> getInflectedWords()
public static java.util.Set<java.lang.String> getCommonWords5()
public static java.util.Set<java.lang.String> getCommonWords()
private static void initGazetteers()
protected static java.util.Set<java.lang.String> loadLinesAsSet(java.lang.String filename, boolean lower)
|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |