Hanlp学习笔记

一、首先要引入mawen依赖包：

 <dependency>
   <groupId>com.hankcs</groupId>
   <artifactId>hanlp</artifactId>
   <version>portable-1.7.2</version>
 </dependency>
 <dependency>
   <groupId>com.alibaba</groupId>
   <artifactId>druid</artifactId>
   <version>1.1.10</version>
 </dependency>
 <dependency>
   <groupId>org.jsoup</groupId>
   <artifactId>jsoup</artifactId>
   <version>1.7.3</version>
 </dependency>

二、提取语句中的关键字

java.util.List<String> keyword =  HanLP.extractKeyword(model.getExamineeAnswer(), model.getKeywordList().size());//extractKeyword方法第二个参数为获取关键字个数
，第一个参数为你要提取关键字的语句

三、计算两个语句的相似度

 double result=getSimilarity(model.getStandardAnswer(),model.getExamineeAnswer());

计算相似度使用的方法

     /*     * 获得两个句子的相似度
     * @param sentence1
     * @param sentence2
     * @return
     */
    public static double getSimilarity(String sentence1, String sentence2) {
        List<String> sent1Words = getSplitWords(sentence1);
        System.out.println(sent1Words);
        List<String> sent2Words = getSplitWords(sentence2);
        System.out.println(sent2Words);
        List<String> allWords = mergeList(sent1Words, sent2Words);

        int[] statistic1 = statistic(allWords, sent1Words);
        int[] statistic2 = statistic(allWords, sent2Words);

        double dividend = 0;
        double divisor1 = 0;
        double divisor2 = 0;
        for (int i = 0; i < statistic1.length; i++) {
            dividend += statistic1[i] * statistic2[i];
            divisor1 += Math.pow(statistic1[i], 2);
            divisor2 += Math.pow(statistic2[i], 2);
        }

        return dividend / (Math.sqrt(divisor1) * Math.sqrt(divisor2));
    }

    private static int[] statistic(List<String> allWords, List<String> sentWords) {
        int[] result = new int[allWords.size()];
        for (int i = 0; i < allWords.size(); i++) {
            result[i] = Collections.frequency(sentWords, allWords.get(i));
        }
        return result;
    }

    private static List<String> mergeList(List<String> list1, List<String> list2) {
        List<String> result = new ArrayList<>();
        result.addAll(list1);
        result.addAll(list2);
        return result.stream().distinct().collect(Collectors.toList());
    }

    private static List<String> getSplitWords(String sentence) {
        // 去除掉html标签
         sentence = Jsoup.parse(sentence.replace("&nbsp;","")).body().text();
        // 标点符号会被单独分为一个Term，去除之
        return HanLP.segment(sentence).stream().map(a -> a.word).
filter(s -> !"`~!@#$^&*()=|{}':;',\\[\\].<>/?~！@#￥……&*（）——|{}【】‘；：”“'。，、？ ".contains(s)).collect(Collectors.toList());
    }

四、提取语句的摘要

List<String> sentenceList = HanLP.extractSummary(str, 3);//摘要

五、hanlp分词

List<Term> termList = NLPTokenizer.segment(str);

六、提取句子中的词

List<String> sentenceList= HanLP.extractPhrase(str, 3);//词