自然语言处理 -- 中文分词

pom.xml引入jar

      <dependency>
          <groupId>edu.stanford.nlp</groupId>
          <artifactId>stanford-corenlp</artifactId>
          <version>3.9.2</version>
      </dependency>
      <dependency>
          <groupId>edu.stanford.nlp</groupId>
          <artifactId>stanford-corenlp</artifactId>
          <version>3.9.2</version>
          <classifier>models</classifier>
      </dependency>
      <dependency>
          <groupId>edu.stanford.nlp</groupId>
          <artifactId>stanford-corenlp</artifactId>
          <version>3.9.2</version>
          <classifier>models-chinese</classifier>
      </dependency>

加载模型和初始化

        Properties properties = new Properties();
        /**
         * Pipeline options - lemma is no-op for Chinese but currently needed because coref demands it (bad old requirements system)
         */
        properties.setProperty("annotators", "tokenize,ssplit,pos,lemma,ner,parse,depparse,coref,kbp,quote");
        /**
         * segment
         */
        properties.setProperty("tokenize.language", "zh");
        properties.setProperty("segment.model", "edu/stanford/nlp/models/segmenter/chinese/ctb.gz");
        properties.setProperty("segment.sighanCorporaDict", "edu/stanford/nlp/models/segmenter/chinese");
        properties.setProperty("segment.serDictionary", "edu/stanford/nlp/models/segmenter/chinese/dict-chris6.ser.gz");
        properties.setProperty("segment.sighanPostProcessing", "true");
        /**
         * sentence split
         */
        properties.setProperty("ssplit.boundaryTokenRegex", "[.。]|[!?！？,;，]+");
        /**
         * pos
         */
        properties.setProperty("pos.model", "edu/stanford/nlp/models/pos-tagger/chinese-distsim/chinese-distsim.tagger");
        /**
         * ner
         */
        properties.setProperty("ner.language", "chinese");
        properties.setProperty("ner.model", "edu/stanford/nlp/models/ner/chinese.misc.distsim.crf.ser.gz");
        properties.setProperty("ner.applyNumericClassifiers", "true");
        properties.setProperty("ner.useSUTime", "false");
        properties.setProperty("ner.fine.regexner.mapping", "edu/stanford/nlp/models/kbp/chinese/gazetteers/cn_regexner_mapping.tab");
        properties.setProperty("ner.fine.regexner.noDefaultOverwriteLabels", "");

		/**
		* parse
		*/
        properties.setProperty("parse.model", "edu/stanford/nlp/models/srparser/chineseSR.ser.gz");

       /** 
       * depparse
       */
        properties.setProperty("depparse.model", "edu/stanford/nlp/models/parser/nndep/UD_Chinese.gz");
        properties.setProperty("depparse.language", "chinese");

        /**
         * entitylink
         */
        properties.setProperty("entitylink.wikidict", "edu/stanford/nlp/models/kbp/chinese/wikidict_chinese.tsv.gz");

        StanfordCoreNLP pipline = new StanfordCoreNLP(properties);

分词

        String text = "乔·史密斯出生于加利福尼亚。2017年夏天，他去了法国巴黎。他的航班于2017年7月10日下午3点起飞。第一次吃了一些蜗牛后，乔说:“太好吃了!”他寄了一张明信片给他的妹妹简·史密斯，他打了他的女儿汤姆。听了乔的旅行后，简决定有一天去法国。";
        // make an example document
        CoreDocument doc = new CoreDocument(text);
        // annotate the document
        pipline.annotate(doc);

        List<CoreLabel> tokens = doc.tokens();

        System.out.println("-----------分词-------------");

        for (CoreLabel toke : tokens) {
            System.out.println(toke.word());
        }