edu.illinois.cs.cogcomp.ner.ExpressiveFeatures

Class TitleTextNormalizer

java.lang.Object

edu.illinois.cs.cogcomp.ner.ExpressiveFeatures.TitleTextNormalizer

public class TitleTextNormalizer
extends Object

Field Summary

Fields

Modifier and Type	Field and Description
static HashMap<String,String>	lowercasedToNormalizedTokensMap
static String	pathToBrownClusterForWordFrequencies
static int	WindowSize

Constructor Summary

Constructors

Constructor and Description
TitleTextNormalizer()

Method Summary

Modifier and Type	Method and Description
static void	getNeighborhoodWordStatistics(NEWord word, HashMap<NEWord,Boolean> wordsInMixedCasedSentences, HashMap<String,CharacteristicWords> uppercasedFormsInMixedCaseNonSentenceStart, HashMap<String,Boolean> lowecasedForms)
static void	init()
static boolean	mixedCase(edu.illinois.cs.cogcomp.lbjava.parse.LinkedVector sentence)
static void	normalizeCase(Data data)
static void	normalizeCaseData(Vector<Data> data)

Methods inherited from class java.lang.Object

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

Field Detail

WindowSize

public static final int WindowSize

See Also:

Constant Field Values

pathToBrownClusterForWordFrequencies

public static String pathToBrownClusterForWordFrequencies

lowercasedToNormalizedTokensMap

public static HashMap<String,String> lowercasedToNormalizedTokensMap

Constructor Detail

TitleTextNormalizer

public TitleTextNormalizer()

Method Detail

init

public static void init()

normalizeCaseData

public static void normalizeCaseData(Vector<Data> data)

normalizeCase

public static void normalizeCase(Data data)

getNeighborhoodWordStatistics

public static void getNeighborhoodWordStatistics(NEWord word,
                                                 HashMap<NEWord,Boolean> wordsInMixedCasedSentences,
                                                 HashMap<String,CharacteristicWords> uppercasedFormsInMixedCaseNonSentenceStart,
                                                 HashMap<String,Boolean> lowecasedForms)

mixedCase

public static boolean mixedCase(edu.illinois.cs.cogcomp.lbjava.parse.LinkedVector sentence)