sg.edu.nus.comp.nlp.ims.util
Class CWordNetSenseIndex

java.lang.Object
  extended by sg.edu.nus.comp.nlp.ims.util.CWordNetSenseIndex
All Implemented Interfaces:
ISenseIndex

public class CWordNetSenseIndex
extends java.lang.Object
implements ISenseIndex

wordnet sense index.

Author:
zhongzhi

Nested Class Summary
static class CWordNetSenseIndex.SenseType
          sense type
 
Field Summary
protected static java.util.regex.Pattern LEMMAPATTERN
           
protected  java.util.Hashtable<java.lang.String,java.lang.String> m_FirstSenses
          first sense of each lexelt lexelt -> first sense
protected  java.util.Hashtable<java.lang.String,java.lang.String> m_Glosses
           
protected  java.util.Hashtable<java.lang.String,java.lang.Integer> m_Indice
           
protected  java.util.Hashtable<java.lang.String,java.util.List<java.lang.String>> m_Offsets
           
protected  java.util.ArrayList<java.lang.Integer> m_SenseNo
           
protected  java.util.ArrayList<java.lang.String> m_SenseOffset
           
protected  java.util.Hashtable<java.lang.String,java.util.List<java.lang.String>> m_Senses
           
protected static java.util.regex.Pattern POSPATTERN
           
 
Constructor Summary
CWordNetSenseIndex(java.lang.String p_SenseIndexFile)
          constructor
CWordNetSenseIndex(java.lang.String p_SenseIndexFile, CWordNetSenseIndex.SenseType p_SenseType)
          constructor
 
Method Summary
 java.lang.String getFirstSense(java.lang.String p_Lexelt)
          get the first sense of p_Lexelt
static java.lang.String getLemma(java.lang.String p_Sense)
          get the lemma of given sense
 java.util.Set<java.lang.String> getLexelts()
          get lexelts
 java.util.List<java.lang.String> getOffsets(java.lang.String p_Lexelt)
          get the ordered offset list of p_Lexelt
static java.lang.String getPOS(java.lang.String p_Sense)
          get the POS of given sense
protected  java.lang.String getSense(java.lang.String p_Sense, java.lang.String p_Offset, java.lang.String p_POS, java.lang.Integer p_No, CWordNetSenseIndex.SenseType p_SenseType)
          generate sense of the given sense type
 java.lang.String getSenseGloss(java.lang.String p_Sense)
          get the sense gloss
 int getSenseNo(java.lang.String sense)
          get sense number of p_Sense
 java.util.List<java.lang.String> getSenses(java.lang.String p_Lexelt)
          get the ordered sense list of p_Lexelt
 void loadDataFiles(java.lang.String p_Dir)
          load WordNet data files
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Field Detail

LEMMAPATTERN

protected static java.util.regex.Pattern LEMMAPATTERN

POSPATTERN

protected static java.util.regex.Pattern POSPATTERN

m_FirstSenses

protected java.util.Hashtable<java.lang.String,java.lang.String> m_FirstSenses
first sense of each lexelt lexelt -> first sense


m_Offsets

protected java.util.Hashtable<java.lang.String,java.util.List<java.lang.String>> m_Offsets

m_Senses

protected java.util.Hashtable<java.lang.String,java.util.List<java.lang.String>> m_Senses

m_Indice

protected java.util.Hashtable<java.lang.String,java.lang.Integer> m_Indice

m_SenseOffset

protected java.util.ArrayList<java.lang.String> m_SenseOffset

m_SenseNo

protected java.util.ArrayList<java.lang.Integer> m_SenseNo

m_Glosses

protected java.util.Hashtable<java.lang.String,java.lang.String> m_Glosses
Constructor Detail

CWordNetSenseIndex

public CWordNetSenseIndex(java.lang.String p_SenseIndexFile)
                   throws java.io.IOException
constructor

Parameters:
p_SenseIndexFile - sense index file path
Throws:
java.io.IOException - exception while loading sense index

CWordNetSenseIndex

public CWordNetSenseIndex(java.lang.String p_SenseIndexFile,
                          CWordNetSenseIndex.SenseType p_SenseType)
                   throws java.io.IOException
constructor

Parameters:
p_SenseIndexFile - sense index file path
p_SenseType - sense type
Throws:
java.io.IOException - exception while loading sense index
Method Detail

getSense

protected java.lang.String getSense(java.lang.String p_Sense,
                                    java.lang.String p_Offset,
                                    java.lang.String p_POS,
                                    java.lang.Integer p_No,
                                    CWordNetSenseIndex.SenseType p_SenseType)
generate sense of the given sense type

Parameters:
p_Sense - sense
p_Offset - offset
p_POS - pos
p_No - sense number
p_SenseType - sense type
Returns:
sense

getLemma

public static java.lang.String getLemma(java.lang.String p_Sense)
get the lemma of given sense

Parameters:
p_Sense - sense
Returns:
lemma

getPOS

public static java.lang.String getPOS(java.lang.String p_Sense)
get the POS of given sense

Parameters:
p_Sense - sense
Returns:
POS (n, v, a, r)

getFirstSense

public java.lang.String getFirstSense(java.lang.String p_Lexelt)
Description copied from interface: ISenseIndex
get the first sense of p_Lexelt

Specified by:
getFirstSense in interface ISenseIndex
Parameters:
p_Lexelt - lexelt id
Returns:
first sense

getSenseNo

public int getSenseNo(java.lang.String sense)
Description copied from interface: ISenseIndex
get sense number of p_Sense

Specified by:
getSenseNo in interface ISenseIndex
Parameters:
sense - sense
Returns:
sense number

getSenseGloss

public java.lang.String getSenseGloss(java.lang.String p_Sense)
get the sense gloss

Parameters:
p_Sense - sense id
Returns:
sense gloss

getOffsets

public java.util.List<java.lang.String> getOffsets(java.lang.String p_Lexelt)
get the ordered offset list of p_Lexelt

Parameters:
p_Lexelt - lexelt
Returns:
offset list

getSenses

public java.util.List<java.lang.String> getSenses(java.lang.String p_Lexelt)
get the ordered sense list of p_Lexelt

Parameters:
p_Lexelt - lexelt
Returns:
sense list

getLexelts

public java.util.Set<java.lang.String> getLexelts()
get lexelts

Returns:
lexelts

loadDataFiles

public void loadDataFiles(java.lang.String p_Dir)
                   throws java.io.IOException
load WordNet data files

Parameters:
p_Dir - WordNet dict directory
Throws:
java.io.IOException - exception during reading data.pos