apache opennlp 简单使用(java)

• maven

  <dependency>
     <groupId>org.apache.opennlp</groupId>
     <artifactId>opennlp-tools</artifactId>
     <version>1.9.4</version>
  </dependency>
  

• model 文件 (http://opennlp.sourceforge.net/models-1.5/)

  • en-sent.bin
  • en-token.bin
  • en-pos-perceptron.bin

• 新建项目， 并把model放到resources目录， 在此放到src/test/resources (目录不存在则创建)
  

• 句子分析

  private static String text = "Java is a programming language and computing platform first released by Sun Microsystems in 1995. It has evolved from humble beginnings to power a large share of today’s digital world, by providing the reliable platform upon which many services and applications are built. New, innovative products and digital services designed for the future continue to rely on Java, as well.";
  @Test
  public void sentenceDetectionTest() throws IOException {
  	Path path = Paths.get("src", "test", "resources", "en-sent.bin");
  	InputStream is = new FileInputStream(path.toFile());
  	SentenceModel model = new SentenceModel(is);
  	SentenceDetectorME sdetector = new SentenceDetectorME(model);
  	String[] sentences = sdetector.sentDetect(text);
  	for (String sentence : sentences) {
  		System.out.println(sentence);
  	}
  }
  
  
  //-- 结果
  // Java is a programming language and computing platform first released by Sun Microsystems in 1995.
  // It has evolved from humble beginnings to power a large share of today’s digital world, by providing the reliable platform upon which many services and applications are built.
  // New, innovative products and digital services designed for the future continue to rely on Java, as well.
  

• 词性分析

  @Test
  public void posTagTest() throws IOException {
  	String text = "Java is a programming language and computing platform first released by Sun Microsystems in 1995. ";
  	Path path = Paths.get("src", "test", "resources", "en-sent.bin");
  	InputStream is = new FileInputStream(path.toFile());
  	SentenceDetectorME sdetector = new SentenceDetectorME(new SentenceModel(is));
  	String[] sentences = sdetector.sentDetect(text);
  	for (String sentence : sentences) {
  		Path tokenPath = Paths.get("src", "test", "resources", "en-token.bin");
  		InputStream tokeInputStream = new FileInputStream(tokenPath.toFile());
  		TokenizerME tokenizer = new TokenizerME(new TokenizerModel(tokeInputStream));
  		String[] tokens = tokenizer.tokenize(sentence);
  		Path posPath = Paths.get("src", "test", "resources", "en-pos-perceptron.bin");
  		InputStream posInputStream = new FileInputStream(posPath.toFile());
  		POSModel posModel = new POSModel(posInputStream);
  		POSTaggerME posTagger = new POSTaggerME(posModel);
  		String[] tagArray = posTagger.tag(tokens);
  		for (int i = 0; i < tokens.length; i++) {
  			System.out.printf("%s -- %s%n", tokens[i], tagArray[i]);
  		}
  	}
  }
  
  
  // -- 结果
  // Java -- NNP
  // is -- VBZ
  // a -- DT
  // programming -- NN
  // language -- NN
  // and -- CC
  // computing -- NN
  // platform -- NN
  // first -- JJ
  // released -- VBN
  // by -- IN
  // Sun -- NNP
  // Microsystems -- NNPS
  // in -- IN
  // 1995 -- CD
  // . -- .