org.aksw.limes.core.measures.measure.semantic.edgecounting.measures

Class LiMeasure

java.lang.Object

org.aksw.limes.core.measures.measure.AMeasure

org.aksw.limes.core.measures.measure.semantic.edgecounting.AEdgeCountingSemanticMeasure

org.aksw.limes.core.measures.measure.semantic.edgecounting.measures.LiMeasure

All Implemented Interfaces:

IMeasure, IEdgeCountingSemanticMeasure

public class LiMeasure
extends AEdgeCountingSemanticMeasure

Implements the Li et al. (LI) semantic string similarity between two concepts (synsets), using the path between two concepts and their least common subsumer.

Version:

1.0

Author:

Kleanthi Georgala (georgala@informatik.uni-leipzig.de)

Field Summary

Fields inherited from class org.aksw.limes.core.measures.measure.semantic.edgecounting.AEdgeCountingSemanticMeasure

ADJECTIVE_DEPTH, ADVERB_DEPTH, dictionary, Indexer, NOUN_DEPTH, VERB_DEPTH

Constructor Summary

Constructors

Constructor and Description
LiMeasure(AIndex Indexer)

Method Summary

Modifier and Type	Method and Description
double	calculate(ArrayList<ArrayList<edu.mit.jwi.item.ISynsetID>> synset1Tree, ArrayList<ArrayList<edu.mit.jwi.item.ISynsetID>> synset2Tree) Calculates the actual LI similarity.
String	getName() Returns name of a measure.
double	getRuntimeApproximation(double mappingSize) Returns the runtime approximation of a measure.
double	getSimilarityBetweenConcepts(edu.mit.jwi.item.ISynset synset1, edu.mit.jwi.item.ISynset synset2) Computes the LI similarity between two concepts.
String	getType() Returns type of a measure.

Methods inherited from class org.aksw.limes.core.measures.measure.semantic.edgecounting.AEdgeCountingSemanticMeasure

checkSimilarity, close, getHierarchyDepth, getIIndexWord, getIWord, getPaths, getSemanticDictionary, getSimilarity, getSimilarity, getSimilarity, getSimilarity, getSynset, getWordIDs, setDictionary, tokenize

Methods inherited from class java.lang.Object

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

Constructor Detail

LiMeasure

public LiMeasure(AIndex Indexer)

Method Detail

calculate

public double calculate(ArrayList<ArrayList<edu.mit.jwi.item.ISynsetID>> synset1Tree,
                        ArrayList<ArrayList<edu.mit.jwi.item.ISynsetID>> synset2Tree)

Calculates the actual LI similarity.

Parameters:

synset1Tree, - the set of all hypernym paths for a concept synset1

synset2Tree, - the set of all hypernym paths for a concept synset2

Returns:

the LI similarity between two concepts

getSimilarityBetweenConcepts

public double getSimilarityBetweenConcepts(edu.mit.jwi.item.ISynset synset1,
                                           edu.mit.jwi.item.ISynset synset2)

Computes the LI similarity between two concepts. To do so, it retrieves all possible hypernym paths for the two concepts, finds their least common subsumer concept, calculates the length of the shortest path between the concepts which passes via their least common subsumer.

Parameters:

synset1, - the first input synset

synset2, - the second input synset

Returns:

the LCH similarity between synset1 and synset2

getRuntimeApproximation

public double getRuntimeApproximation(double mappingSize)

Description copied from interface: IMeasure

Returns the runtime approximation of a measure.

Returns:

The runtime of the measure

getName

public String getName()

Description copied from interface: IMeasure

Returns name of a measure.

Returns:

Measure name as a string

getType

public String getType()

Description copied from interface: IMeasure

Returns type of a measure.

Returns:

The runtime of the measure