在WS4J中使用wu-palmer计算器来查找单词之间的相似性 [英] Use wu-palmer calculator in WS4J to find similarity between words

问题描述

我正在使用WS4j来查找两个单词之间的相似性。我也在使用Wu-Palmer相关性计算器。它适用于很多单词，但是当我试图找到'play'和'playing'之间的相似性时，它给出了得分1.3333，这是不可能的，因为它必须在0和1或-1之间返回。我无法弄清楚原因。当我使用其网页界面'http://ws4jdemo.appspot.com/?mode=w&s1=&w1=play&s2=&w2=playing'时，它返回0.875。

这是我的代码：

I am using WS4j to find the similarity between two words. Also I am using Wu-Palmer relatedness calculator. It is working fine for many words, but when I tried to find the similarity between 'play' and 'playing', it gave the score 1.3333, which is not possible as it has to return between 0 and 1 or -1. I can't figure out the reason. When I used its web interface 'http://ws4jdemo.appspot.com/?mode=w&s1=&w1=play&s2=&w2=playing' it returned 0.875.
Here is my code:

private static void findSimilarity(String word1, String word2) {
	WS4JConfiguration.getInstance().setMFS(true);
	List<POS[]> posPairs = wup.getPOSPairs();
	double maxScore = -1D;

	for(POS[] posPair: posPairs) {
		List<Concept> synsets1 =
		(List<Concept>)db.getAllConcepts(word1, posPair[0].toString());

		List<Concept> synsets2 =
		(List<Concept>)db.getAllConcepts(word2, posPair[1].toString());

		for(Concept synset1: synsets1) {
			for (Concept synset2: synsets2) {
				Relatedness relatedness = wup.calcRelatednessOfSynset(synset1, synset2);
				double score = relatedness.getScore();

				if (score > maxScore) {
					maxScore = score;
				}
			}
		}
	}

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

	System.out.println("sim('" + word1 + "', '" + word2 + "') =  " + maxScore);
}

我的尝试：



java - Wu- Palmer相关性计算器返回1.33333得分 - Stack Overflow [ ^ ]

推荐答案

您好y可以使用此代码：



ILexicalDatabase db = new NictWordNet（）;

WS4JConfiguration.getInstance（）。setMFS（true）;

RelatednessCalculator rc = new Lin（db）;

String word1 =gender;

String word2 =sex;

List< POS []> posPairs = rc.getPOSPairs（）;

double maxScore = -1D;



for（POS [] posPair：posPairs）{

列表< concept> synsets1 =（List< concept>）db.getAllConcepts（word1，posPair [0] .toString（））;

List< concept> synsets2 =（List< concept>）db.getAllConcepts（word2，posPair [1] .toString（））;



for（Concept synset1：synsets1）{

for（概念synset2：synsets2）{

相关性相关性= rc.calcRelatednessOfSynset（synset1，synset2）;

double score = relatedness.getScore（） ;

if（得分> maxScore）{

maxScore =得分;

}

}

}

}



if（maxScore == -1D）{

maxScore = 0.0;

}



System.out.println（sim（'+ word1 +'，'+ word2 + '）=+ maxScore）;

Hello y can use this code:

ILexicalDatabase db = new NictWordNet();
WS4JConfiguration.getInstance().setMFS(true);
RelatednessCalculator rc = new Lin(db);
String word1 = "gender";
String word2 = "sex";
List<POS[]> posPairs = rc.getPOSPairs();
double maxScore = -1D;

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

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

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

System.out.println("sim('" + word1 + "', '" + word2 + "') = " + maxScore);

这篇关于在WS4J中使用wu-palmer计算器来查找单词之间的相似性的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！