edu.illinois.cs.cogcomp.nlp.utilities

Class POSUtils

java.lang.Object

edu.illinois.cs.cogcomp.nlp.utilities.POSUtils

public class POSUtils
extends Object

This class represents a collection of utility functions related to POS tags. Functions from ParseTreeProperties will eventually move here.

Author:

Vivek Srikumar

Field Summary

Fields

Modifier and Type	Field and Description
static List<String>	allPOS
static Set<String>	closedSetPOS

Constructor Summary

Constructors

Constructor and Description
POSUtils()

Method Summary

Modifier and Type	Method and Description
static String	getCoarsePOS(String pos) Converts the input part of speech tag into a coarse set, consisting of the labels Noun, Verb, Adjective, Adverb, Punctuation, Pronoun and Other
static String	getPOS(TextAnnotation ta, int tokenId)
static boolean	isPOSAdjective(String token)
static boolean	isPOSAdverb(String token)
static boolean	isPOSClosedSet(String token)
static boolean	isPOSNoun(String token)
static boolean	isPOSNumber(String token)
static boolean	isPOSOpenSet(String token)
static boolean	isPOSPossessive(String label)
static boolean	isPOSPossessivePronoun(String token)
static boolean	isPOSPreposition(String token)
static boolean	isPOSPronoun(String token)
static boolean	isPOSPunctuation(String label)
static boolean	isPOSTag(String token) Very simple way of testing whether something is a part of speech tag.
static boolean	isPOSVerb(String token)

Methods inherited from class java.lang.Object

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

Field Detail

closedSetPOS

public static final Set<String> closedSetPOS

allPOS

public static final List<String> allPOS

Constructor Detail

POSUtils

public POSUtils()

Method Detail

isPOSTag

public static boolean isPOSTag(String token)

Very simple way of testing whether something is a part of speech tag. Just look up a list of allowed POS tags and see if the label is in it.

getCoarsePOS

public static String getCoarsePOS(String pos)

Converts the input part of speech tag into a coarse set, consisting of the labels Noun, Verb, Adjective, Adverb, Punctuation, Pronoun and Other

isPOSOpenSet

public static boolean isPOSOpenSet(String token)

isPOSClosedSet

public static boolean isPOSClosedSet(String token)

isPOSNumber

public static boolean isPOSNumber(String token)

isPOSPunctuation

public static boolean isPOSPunctuation(String label)

isPOSPossessive

public static boolean isPOSPossessive(String label)

isPOSAdjective

public static boolean isPOSAdjective(String token)

isPOSNoun

public static boolean isPOSNoun(String token)

isPOSPronoun

public static boolean isPOSPronoun(String token)

isPOSPossessivePronoun

public static boolean isPOSPossessivePronoun(String token)

isPOSAdverb

public static boolean isPOSAdverb(String token)

isPOSPreposition

public static boolean isPOSPreposition(String token)

isPOSVerb

public static boolean isPOSVerb(String token)

getPOS

public static String getPOS(TextAnnotation ta,
                            int tokenId)