Package opennlp.tools.postag

Examples of opennlp.tools.postag.POSTaggerME.tag()

47
48
49
50
51
52
53
54
55
56
57
    POSModel model = new POSModel(posModelStream);
   
    POSTaggerME tagger = new POSTaggerME(model);
    String[] words = SimpleTokenizer.INSTANCE.tokenize( //<co id="opennlpPOS.co.tokenize"/>
        "The quick, red fox jumped over the lazy, brown dogs.");
    String[] result = tagger.tag(words);//<co id="opennlpPOS.co.dotag"/>
    for (int i=0 ; i < words.length; i++) {
      System.err.print(words[i] + "/" + result[i] + " ");
    }
    System.err.println("\n");
    /*
 
View Full Code Here
67
68
69
70
71
72
73
74
75
76
77
    try {
      String line;
      while ((line = lineStream.read()) != null) {
       
        String whitespaceTokenizerLine[] = WhitespaceTokenizer.INSTANCE.tokenize(line);
        String[] tags = tagger.tag(whitespaceTokenizerLine);
       
        POSSample sample = new POSSample(whitespaceTokenizerLine, tags);
        System.out.println(sample.toString());
       
        perfMon.incrementCounter();
View Full Code Here
92
93
94
95
96
97
98
99
100
101
102
    }
    else {
      tagger = new PosTagger(modelFile);
    }
    if (test) {
      System.out.println(tagger.tag(args[ai]));
    }
    else {
      BufferedReader in = new BufferedReader(new InputStreamReader(System.in,"ISO-8859-1"));
      PrintStream out = new PrintStream(System.out,true,"ISO-8859-1");
      for (String line = in.readLine(); line != null; line = in.readLine()) {
View Full Code Here
98
99
100
101
102
103
104
105
106
107
    }
    else {
      BufferedReader in = new BufferedReader(new InputStreamReader(System.in,"ISO-8859-1"));
      PrintStream out = new PrintStream(System.out,true,"ISO-8859-1");
      for (String line = in.readLine(); line != null; line = in.readLine()) {
        out.println(tagger.tag(line));
      }
    }
  }
}
View Full Code Here
112
113
114
115
116
117
118
119
120
121
122
      else {
        tagger = new PosTagger(model,(Dictionary)null);
      }
    }
    if (test) {
      System.out.println(tagger.tag(args[ai]));
    }
    else {
      BufferedReader in = new BufferedReader(new InputStreamReader(System.in));
     
      for (String line = in.readLine(); line != null; line = in.readLine()) {
View Full Code Here
118
119
120
121
122
123
124
125
126
127
    }
    else {
      BufferedReader in = new BufferedReader(new InputStreamReader(System.in));
     
      for (String line = in.readLine(); line != null; line = in.readLine()) {
        System.out.println(tagger.tag(line));
      }
    }
  }
}
View Full Code Here
61
62
63
64
65
66
67
68
69
70
71
      try {
        String line;
        while ((line = lineStream.read()) != null) {

          String whitespaceTokenizerLine[] = WhitespaceTokenizer.INSTANCE.tokenize(line);
          String[] tags = tagger.tag(whitespaceTokenizerLine);

          POSSample sample = new POSSample(whitespaceTokenizerLine, tags);
          System.out.println(sample.toString());

          perfMon.incrementCounter();
View Full Code Here
165
166
167
168
169
170
171
172
173
174
175
      // System.out.println("\n\nTokens:");
      for (int i = 0; i < tokens.length; i++) {
        tokens[i] = tokSpans[i].getCoveredText(sentence).toString();
        // System.out.println(tokens[i]);
      }
      String[] tags = posTagger.tag(tokens);
      Span[] chunks = chunker.chunkAsSpans(tokens, tags);
      for (Span chunk : chunks) {
        if ("NP".equals(chunk.getType())) {
          //Note: getStart()/getEnd() methods of Chunk spans only give the start and end token indexes of the chunk.
          //The actual Start/End positions of the chunk in the sentence need to be extracted from POS sentenceSpans.
View Full Code Here
97
98
99
100
101
102
103
104
105
106
107
    return tokenizer.tokenize(cleanString);
  }

  private String[] posTag(String[] tokens) {
    POSTaggerME posTagger = new POSTaggerME(posModel);
    return posTagger.tag(tokens);
  }

  private String[] chunk(String[] tokens, String[] posTags) {
    ChunkerME chunker = new ChunkerME(chunkerModel);
    return chunker.chunk(tokens, posTags);
View Full Code Here
60
61
62
63
64
65
66
67
68
69
70
        perfMon.start();
        String line;
        while ((line = lineStream.read()) != null) {

          String whitespaceTokenizerLine[] = WhitespaceTokenizer.INSTANCE.tokenize(line);
          String[] tags = tagger.tag(whitespaceTokenizerLine);

          POSSample sample = new POSSample(whitespaceTokenizerLine, tags);
          System.out.println(sample.toString());

          perfMon.incrementCounter();
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. All rights reserved.
All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.