Stanford 中文分词

1. http://nlp.stanford.edu/software/segmenter.shtml
2. https://github.com/jiekechoo/NLPStudy
3. http://blog.csdn.net/shijiebei2009/article/details/42525091

貌似实际用的不是这几篇。中间2. github上那篇，是怎么在maven中使用，通过properties文件生效。然而没有尝试成功，properties里设置不成功。

首先，去【1】下载Download Stanford Word Segmenter version 3.5.2，取得里面的 data 文件夹，放在maven project的 src/main/resources 里。

然后，maven依赖添加：

 <properties>
        <java.version>1.8</java.version>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <corenlp.version>3.6.0</corenlp.version>
    </properties>
    <dependencies>
        <dependency>
            <groupId>edu.stanford.nlp</groupId>
            <artifactId>stanford-corenlp</artifactId>
            <version>${corenlp.version}</version>
        </dependency>
        <dependency>
            <groupId>edu.stanford.nlp</groupId>
            <artifactId>stanford-corenlp</artifactId>
            <version>${corenlp.version}</version>
            <classifier>models</classifier>
        </dependency>
        <dependency>
            <groupId>edu.stanford.nlp</groupId>
            <artifactId>stanford-corenlp</artifactId>
            <version>${corenlp.version}</version>
            <classifier>models-chinese</classifier>
        </dependency>
    </dependencies>

最后，代码如下：

import java.util.Properties;

import edu.stanford.nlp.ie.crf.CRFClassifier;

public class CoreNLPSegment {

    private static CoreNLPSegment instance;
    private CRFClassifier         classifier;

    private CoreNLPSegment(){
        Properties props = new Properties();
        props.setProperty("sighanCorporaDict", "data");
        props.setProperty("serDictionary", "data/dict-chris6.ser.gz");
        props.setProperty("inputEncoding", "UTF-8");
        props.setProperty("sighanPostProcessing", "true");
        classifier = new CRFClassifier(props);
        classifier.loadClassifierNoExceptions("data/ctb.gz", props);
        classifier.flags.setProperties(props);
    }

    public static CoreNLPSegment getInstance() {
        if (instance == null) {
            instance = new CoreNLPSegment();
        }

        return instance;
    }

    public String[] doSegment(String data) {
        return (String[]) classifier.segmentString(data).toArray();
    }

    public static void main(String[] args) {

        String sentence = "他和我在学校里常打桌球。";
        String ret[] = CoreNLPSegment.getInstance().doSegment(sentence);
        for (String str : ret) {
            System.out.println(str);
        }

    }

}