Package de.julielab.gene.candidateretrieval.scoring

Class MaxEntScorerPairExtractor

java.lang.Object

de.julielab.gene.candidateretrieval.scoring.MaxEntScorerPairExtractor

public class MaxEntScorerPairExtractor
extends Object

Constructor Summary

Constructors

Constructor	Description
MaxEntScorerPairExtractor()

Method Summary

Modifier and Type	Method	Description
boolean	addPair(String first, String second)	simple pair add rule: terms must not be the same and must have at least one token in common.
boolean	addPair(String first, String second, double overlapRatio, int maxSynLength)	overlap must be at least overlapRatio in both terms and both terms must not be longer than a maximal synonym length
boolean	addPairSpecialRules(String first, String second, double overlapRatio, int maxSynLength)	as addPair but pair is only allowed if - difference is not only a number or a single character - overlap is not only a number or a single character
String[][]	compareStrings(String S1, String S2)	TODO: comment!
ArrayList<String[]>	getPairs(File trueList, File completeList, int amountTrue, float ratioFalse)	TODO: comment!
void	showPairs(ArrayList<String[]> pairs)
void	storePairs(ArrayList<String[]> pairs, File filename)

Methods inherited from class java.lang.Object

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

Constructor Detail

MaxEntScorerPairExtractor

public MaxEntScorerPairExtractor()

Method Detail

getPairs

public ArrayList<String[]> getPairs(File trueList,
                                    File completeList,
                                    int amountTrue,
                                    float ratioFalse)

TODO: comment!

Parameters:

trueList -

completeList -

amountTrue -

ratioFalse -

Returns:

showPairs

public void showPairs(ArrayList<String[]> pairs)

storePairs

public void storePairs(ArrayList<String[]> pairs,
                       File filename)
                throws IOException

Throws:

IOException

addPair

public boolean addPair(String first,
                       String second)

simple pair add rule: terms must not be the same and must have at least one token in common. Works on normalized terms.

Parameters:

first - normalized term

second - normalized term

Returns:

addPair

public boolean addPair(String first,
                       String second,
                       double overlapRatio,
                       int maxSynLength)

overlap must be at least overlapRatio in both terms and both terms must not be longer than a maximal synonym length

Parameters:

first - normalized term

second - normalized term

overlapRatio - intersection-size / term-length

maxSynLength - length in tokens

Returns:

addPairSpecialRules

public boolean addPairSpecialRules(String first,
                                   String second,
                                   double overlapRatio,
                                   int maxSynLength)

as addPair but pair is only allowed if - difference is not only a number or a single character - overlap is not only a number or a single character

Parameters:

first -

second -

overlapRatio -

maxSynLength -

Returns:

compareStrings

public String[][] compareStrings(String S1,
                                 String S2)

TODO: comment!

Parameters:

S1 -

S2 -

Returns: