Package opennlp.tools.util

Examples of opennlp.tools.util.Span

147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
  ChunkSample sample = new ChunkSample(createSentence(), createTags(),
      createChunks());
  Span[] spans = sample.getPhrasesAsSpanList();

  assertEquals(10, spans.length);
  assertEquals(new Span(0, 1, "NP"), spans[0]);
  assertEquals(new Span(1, 2, "PP"), spans[1]);
  assertEquals(new Span(2, 5, "NP"), spans[2]);
  assertEquals(new Span(5, 6, "VP"), spans[3]);
  assertEquals(new Span(6, 7, "ADVP"), spans[4]);
  assertEquals(new Span(8, 9, "NP"), spans[5]);
    assertEquals(new Span(9, 10, "PP"), spans[6]);
    assertEquals(new Span(10, 13, "NP"), spans[7]);
    assertEquals(new Span(13, 14, "VP"), spans[8]);
    assertEquals(new Span(14, 15, "ADVP"), spans[9]);
  }
View Full Code Here
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
  public void testPhraseAsSpan() {
    Span[] spans = ChunkSample.phrasesAsSpanList(createSentence(),
        createTags(), createChunks());

      assertEquals(10, spans.length);
      assertEquals(new Span(0, 1, "NP"), spans[0]);
      assertEquals(new Span(1, 2, "PP"), spans[1]);
      assertEquals(new Span(2, 5, "NP"), spans[2]);
      assertEquals(new Span(5, 6, "VP"), spans[3]);
      assertEquals(new Span(6, 7, "ADVP"), spans[4]);
      assertEquals(new Span(8, 9, "NP"), spans[5]);
      assertEquals(new Span(9, 10, "PP"), spans[6]);
      assertEquals(new Span(10, 13, "NP"), spans[7]);
      assertEquals(new Span(13, 14, "VP"), spans[8]);
      assertEquals(new Span(14, 15, "ADVP"), spans[9]);
  }
View Full Code Here
60
61
62
63
64
65
66
67
68
69
    String sentence = "Max a b c d";

    SimpleTokenizer tokenizer = SimpleTokenizer.INSTANCE;
    String tokens[] = tokenizer.tokenize(sentence);

    Span names[] = mNameFinder.find(tokens);

    assertTrue(names.length == 1);
    assertTrue(names[0].getStart() == 0 && names[0].getEnd() == 1);
  }
View Full Code Here
73
74
75
76
77
78
79
80
81
82
    String sentence = "a b  Max c d";

    SimpleTokenizer tokenizer = SimpleTokenizer.INSTANCE;
    String tokens[] = tokenizer.tokenize(sentence);

    Span names[] = mNameFinder.find(tokens);

    assertTrue(names.length == 1);
    assertTrue(names[0].getStart() == 2 && names[0].getEnd() == 3);
  }
View Full Code Here
86
87
88
89
90
91
92
93
94
95
    String sentence = "a b c Max";

    SimpleTokenizer tokenizer = SimpleTokenizer.INSTANCE;
    String tokens[] = tokenizer.tokenize(sentence);

    Span names[] = mNameFinder.find(tokens);

    assertTrue(names.length == 1);
    assertTrue(names[0].getStart() == 3 && names[0].getEnd() == 4);
  }
View Full Code Here
96
97
98
99
100
101
102
103
104
105
  @Test
  public void testLastMatchingTokenNameIsChoosen() {
    String sentence[] = {"a", "b", "c", "Vanessa"};

    Span names[] = mNameFinder.find(sentence);

    assertTrue(names.length == 1);
    assertTrue(names[0].getStart() == 3 && names[0].getEnd() == 4);
  }
View Full Code Here
106
107
108
109
110
111
112
113
114
115
  @Test
  public void testLongerTokenNameIsPreferred() {
    String sentence[] = {"a", "b", "c", "Vanessa", "Williams"};

    Span names[] = mNameFinder.find(sentence);

    assertTrue(names.length == 1);
    assertTrue(names[0].getStart() == 3 && names[0].getEnd() == 5);
  }
View Full Code Here
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
  public Span[] find(String[] tokenStrings) {
    List<Span> foundNames = new LinkedList<Span>();

    for (int startToken = 0; startToken < tokenStrings.length; startToken++) {

      Span foundName = null;

      String  tokens[] = new String[]{};

      for (int endToken = startToken; endToken < tokenStrings.length; endToken++) {

        String token = tokenStrings[endToken];

        // TODO: improve performance here
        String newTokens[] = new String[tokens.length + 1];
        System.arraycopy(tokens, 0, newTokens, 0, tokens.length);
        newTokens[newTokens.length - 1] = token;
        tokens = newTokens;

        if (mMetaDictionary.contains(token)) {

          StringList tokenList = new StringList(tokens);

          if (mDictionary.contains(tokenList)) {
            foundName = new Span(startToken, endToken + 1);
          }
        }
        else {
          break;
        }
View Full Code Here
79
80
81
82
83
84
85
86
87
88
89
90
   
    if (reference.isClearAdaptiveDataSet()) {
      nameFinder.clearAdaptiveData();
    }
   
    Span predictedNames[] = nameFinder.find(reference.getSentence());   
    Span references[] = reference.getNames();

    fmeasure.updateScores(references, predictedNames);
   
    return new NameSample(reference.getSentence(), predictedNames, reference.isClearAdaptiveDataSet());
  }
View Full Code Here
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
      System.out.print(" ");
    }
    Parse[] children = p.getChildren();
    for (int pi=0,pn=children.length;pi<pn;pi++) {
      Parse c = children[pi];
      Span s = c.getSpan();
      if (start < s.getStart()) {
        System.out.print(p.getText().substring(start, s.getStart()));
      }
      show(c);
      start = s.getEnd();
    }
    System.out.print(p.getText().substring(start, p.getSpan().getEnd()));
    if (!p.getType().equals(Parser.TOK_NODE)) {
      System.out.print(")");
    }
View Full Code Here
TOP

Related Classes of opennlp.tools.util.Span

  • com.bericotech.clavin.extractor.ApacheExtractor
  • com.tamingtext.opennlp.NameFinderTest
  • net.sf.nlpshell.CorefParse
  • net.sf.nlpshell.Main
  • opennlp.tools.chunker.ChunkerMETest
  • opennlp.tools.chunker.ChunkSample
  • opennlp.tools.chunker.ChunkSampleTest
  • opennlp.tools.cmdline.EvaluationErrorPrinter
  • opennlp.tools.cmdline.namefind.TokenNameFinderTool
  • opennlp.tools.cmdline.parser.ParserTool
    • 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.