句子级ws4j中的语义匹配

Posted 2021-04-18

我目前正试图在语法上匹配ws4j中的两个句子。我在单词级别实现了这个概念，但是在句子级别实现相同的功能并且以在线演示中显示的矩阵形式获得输出。如何开发代码来做同样的事情？

import java.util.List;
import edu.cmu.lti.ws4j.impl.Lesk;
import edu.cmu.lti.jawjaw.pobj.POS;
import edu.cmu.lti.lexical_db.ILexicalDatabase;
import edu.cmu.lti.lexical_db.NictWordNet;
import edu.cmu.lti.lexical_db.data.Concept;
import edu.cmu.lti.ws4j.Relatedness;
import edu.cmu.lti.ws4j.RelatednessCalculator;

public class WordMatcher1 {
public static void main(String[] args)
{
    String word1="rifle";
    String word2="gun";

    ILexicalDatabase db = new NictWordNet();
    RelatednessCalculator lesk = new Lesk(db);

    List<POS[]> posPairs = lesk.getPOSPairs();
    double maxScore = -1D;

    for(POS[] posPair: posPairs) 
    {
        String p1 = null,p2 = null;
        List<Concept> synsets1 = (List<Concept>)db.getAllConcepts(word1, posPair[0].toString());
        List<Concept> synsets2 = (List<Concept>)db.getAllConcepts(word2, posPair[1].toString());

        for(Concept ss1: synsets1) 
        {
            for (Concept ss2: synsets2) 
            {
                p1 = ss1.getPos().toString();
                p2 = ss2.getPos().toString();
                Relatedness relatedness = lesk.calcRelatednessOfSynset(ss1, ss2);
                double score = relatedness.getScore();
                if (score > maxScore) 
                { 
                    maxScore = score;
                }

            }
        }

        if (maxScore == -1D) 
        {
            maxScore = 0.0;
        }
        System.out.println("sim('" + word1 +" "+ p1 +"', '" + p2 +" "+ word2+ "') =  " + maxScore);
    }
}

答案

我有类似的问题，这个例子有效：

import java.util.List;
import edu.cmu.lti.jawjaw.pobj.POS;
import edu.cmu.lti.lexical_db.ILexicalDatabase;
import edu.cmu.lti.lexical_db.NictWordNet;
import edu.cmu.lti.lexical_db.data.Concept;
import edu.cmu.lti.ws4j.Relatedness;
import edu.cmu.lti.ws4j.RelatednessCalculator;
import edu.cmu.lti.ws4j.impl.Lesk;
import edu.cmu.lti.ws4j.util.WS4JConfiguration;

public class LeskSimilarity{

    public static void main(String[] args) {
    ILexicalDatabase db = new NictWordNet();
    RelatednessCalculator lesk = new Lesk(db);
    String word1="rifle";
    POS posWord1=  POS.n;
    String word2= "gun";
    POS posWord2= POS.n;
    double maxScore = 0;

        WS4JConfiguration.getInstance().setMFS(true);

        List<Concept> synsets1 = (List<Concept>)db.getAllConcepts(word1, posWord1.name());
        List<Concept> synsets2 = (List<Concept>)db.getAllConcepts(word2, posWord2.name());

        for(Concept synset1: synsets1) {
            for (Concept synset2: synsets2) {
                Relatedness relatedness =     lesk.calcRelatednessOfSynset(synset1, synset2);
            double score = relatedness.getScore();
            if (score > maxScore) { 
                maxScore = score;
            }
          }
        }

    if (maxScore == -1D) {
        maxScore = 0.0;
    }

    System.out.println("Similarity score of " + word1 + " & " + word2 + " : " + maxScore);
  }
}