Package opennlp.tools.postag

Examples of opennlp.tools.postag.POSSample

42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
    this.detokenizer = detokenizer;
  }
 
  public TokenSample read() throws IOException {
   
    POSSample posSample = samples.read();
   
    TokenSample tokenSample = null;
   
    if (posSample != null ) {
      tokenSample = new TokenSample(detokenizer, posSample.getSentence());
    }
   
    return tokenSample;
  }
View Full Code Here
47
48
49
50
51
52
53
54
55
56
57
      for(Parse tagNode : parse.getTagNodes()) {
        sentence.add(tagNode.getCoveredText());
        tags.add(tagNode.getType());
      }
     
      return new POSSample(sentence, tags);
    }
    else {
      return null;
    }
  }
View Full Code Here
63
64
65
66
67
68
69
70
71
72
73
74
        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();
        }
      }
      catch (IOException e) {
View Full Code Here
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
        new PlainTextByLineStream(
            ADParagraphStreamTest.class
                .getResourceAsStream("/opennlp/tools/formats/ad.sample"),
            "UTF-8"), false, false);

    POSSample sample = stream.read();
   
    assertEquals(23, sample.getSentence().length);
   
    assertEquals("Inicia", sample.getSentence()[0]);
    assertEquals("v-fin", sample.getTags()[0]);
   
    assertEquals("em", sample.getSentence()[1]);
    assertEquals("prp", sample.getTags()[1]);
   
    assertEquals("o", sample.getSentence()[2]);
    assertEquals("art", sample.getTags()[2]);
   
    assertEquals("Porto_Poesia", sample.getSentence()[9]);
    assertEquals("prop", sample.getTags()[9]);
  }
View Full Code Here
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
        new PlainTextByLineStream(
            ADParagraphStreamTest.class
                .getResourceAsStream("/opennlp/tools/formats/ad.sample"),
            "UTF-8"), true, false);

    POSSample sample = stream.read();
   
    assertEquals(27, sample.getSentence().length);
   
    assertEquals("Inicia", sample.getSentence()[0]);
    assertEquals("v-fin", sample.getTags()[0]);
   
    assertEquals("em", sample.getSentence()[1]);
    assertEquals("prp", sample.getTags()[1]);
   
    assertEquals("o", sample.getSentence()[2]);
    assertEquals("art", sample.getTags()[2]);
   
    assertEquals("Porto", sample.getSentence()[9]);
    assertEquals("B-prop", sample.getTags()[9]);
   
    assertEquals("Poesia", sample.getSentence()[10]);
    assertEquals("I-prop", sample.getTags()[10]);
  }
View Full Code Here
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
        new PlainTextByLineStream(
            ADParagraphStreamTest.class
                .getResourceAsStream("/opennlp/tools/formats/ad.sample"),
            "UTF-8"), false, true);

    POSSample sample = stream.read();
   
    assertEquals(23, sample.getSentence().length);
   
    assertEquals("Inicia", sample.getSentence()[0]);
    assertEquals("v-fin=PR=3S=IND=VFIN", sample.getTags()[0]);
   
    assertEquals("em", sample.getSentence()[1]);
    assertEquals("prp", sample.getTags()[1]);
   
    assertEquals("o", sample.getSentence()[2]);
    assertEquals("art=DET=M=S", sample.getTags()[2]);
   
    assertEquals("Porto_Poesia", sample.getSentence()[9]);
    assertEquals("prop=M=S", sample.getTags()[9]);
  }
View Full Code Here
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
      try {
        String line;
        while ((line = lineStream.read()) != null) {

          POSSample posSample;
          try {
            posSample = POSSample.parse(line);
          } catch (InvalidFormatException e) {
            System.err.println("Invalid format:");
            System.err.println(line);
            continue;
          }

          String[] chunks = chunker.chunk(posSample.getSentence(),
              posSample.getTags());

          System.out.println(new ChunkSample(posSample.getSentence(),
              posSample.getTags(), chunks).nicePrint());

          perfMon.incrementCounter();
        }
      }
      catch (IOException e) {
View Full Code Here
96
97
98
99
100
101
102
103
104
      Node root = paragraph.getRoot();
      List<String> sentence = new ArrayList<String>();
      List<String> tags = new ArrayList<String>();
      process(root, sentence, tags);

      return new POSSample(sentence, tags);
    }
    return null;
  }
View Full Code Here
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
    // One paragraph contains a whole sentence and, the token
    // and tag will be read from the FORM and POSTAG field.
   
   String paragraph = samples.read();
  
   POSSample sample = null;
  
   if (paragraph != null) {
    
     // paragraph get lines
     BufferedReader reader = new BufferedReader(new StringReader(paragraph));
    
     List<String> tokens = new ArrayList<String>(100);
     List<String> tags = new ArrayList<String>(100);
    
     String line;
     while ((line = reader.readLine())  != null) {
    
       final int minNumberOfFields = 5;
      
       String parts[] = line.split("\t");
      
       if (parts.length >= minNumberOfFields) {
         tokens.add(parts[1]);
         tags.add(parts[4]);
       }
       else {
         throw new InvalidFormatException("Every non-empty line must have at least " +
             minNumberOfFields + " fields: '" + line + "'!");
       }
     }
    
     // just skip empty samples and read next sample
     if (tokens.size() == 0)
       sample = read();
      
     sample = new POSSample(tokens.toArray(new String[tokens.size()]), tags.toArray(new String[tags.size()]));
   }
  
   return sample;
  }
View Full Code Here
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
    InputStreamFactory in = new ResourceAsStreamFactory(ConllXPOSSampleStreamTest.class,
        "/opennlp/tools/formats/conllx.sample");

    ObjectStream<POSSample> sampleStream = new ConllXPOSSampleStream(in,Charset.forName("UTF-8"));

    POSSample a = sampleStream.read();

    String aSentence[] = a.getSentence();
    String aTags[] = a.getTags();

    assertEquals(22, aSentence.length);
    assertEquals(22, aTags.length);

    assertEquals("To", aSentence[0]);
    assertEquals("AC", aTags[0]);

    assertEquals("kendte", aSentence[1]);
    assertEquals("AN", aTags[1]);

    assertEquals("russiske", aSentence[2]);
    assertEquals("AN", aTags[2]);

    assertEquals("historikere", aSentence[3]);
    assertEquals("NC", aTags[3]);

    assertEquals("Andronik", aSentence[4]);
    assertEquals("NP", aTags[4]);

    assertEquals("Andronik", aSentence[5]);
    assertEquals("NP", aTags[5]);

    assertEquals("og", aSentence[6]);
    assertEquals("CC", aTags[6]);

    assertEquals("Igor", aSentence[7]);
    assertEquals("NP", aTags[7]);

    assertEquals("Klamkin", aSentence[8]);
    assertEquals("NP", aTags[8]);

    assertEquals("tror", aSentence[9]);
    assertEquals("VA", aTags[9]);

    assertEquals("ikke", aSentence[10]);
    assertEquals("RG", aTags[10]);

    assertEquals(",", aSentence[11]);
    assertEquals("XP", aTags[11]);

    assertEquals("at", aSentence[12]);
    assertEquals("CS", aTags[12]);

    assertEquals("Rusland", aSentence[13]);
    assertEquals("NP", aTags[13]);

    assertEquals("kan", aSentence[14]);
    assertEquals("VA", aTags[14]);

    assertEquals("udvikles", aSentence[15]);
    assertEquals("VA", aTags[15]);

    assertEquals("uden", aSentence[16]);
    assertEquals("SP", aTags[16]);

    assertEquals("en", aSentence[17]);
    assertEquals("PI", aTags[17]);

    assertEquals("\"", aSentence[18]);
    assertEquals("XP", aTags[18]);

    assertEquals("jernnæve", aSentence[19]);
    assertEquals("NC", aTags[19]);

    assertEquals("\"", aSentence[20]);
    assertEquals("XP", aTags[20]);

    assertEquals(".", aSentence[21]);
    assertEquals("XP", aTags[21]);

    POSSample b = sampleStream.read();

    String bSentence[] = b.getSentence();
    String bTags[] = b.getTags();

    assertEquals(12, bSentence.length);
    assertEquals(12, bTags.length);

    assertEquals("De", bSentence[0]);
View Full Code Here
TOP

Related Classes of opennlp.tools.postag.POSSample

  • opennlp.tools.cmdline.chunker.ChunkerMETool
  • opennlp.tools.cmdline.postag.POSTaggerTool
  • opennlp.tools.formats.ad.ADPOSSampleStream
  • opennlp.tools.formats.ad.ADPOSSampleStreamTest
  • opennlp.tools.formats.ConllXPOSSampleStream
  • opennlp.tools.formats.ConllXPOSSampleStreamTest
  • opennlp.tools.formats.convert.ParseToPOSSampleStream
  • opennlp.tools.formats.convert.POSToTokenSampleStream
  • opennlp.tools.formats.POSToTokenSampleStream
  • opennlp.tools.parser.PosSampleStream
    • Copyright © 2018 www.massapicom. 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.