Package opennlp.tools.sentdetect

Examples of opennlp.tools.sentdetect.SentenceSample

146
147
148
149
150
151
152
    for (AnnotationFS sentenceAnnotation : sentenceIndex) {
      sentSpans[i++] = new Span(sentenceAnnotation.getBegin(), sentenceAnnotation.getEnd());
    }

    // TODO: The line cleaning should be done more carefully
    sentenceSamples.add(new SentenceSample(cas.getDocumentText().replace('\n', ' '), sentSpans));
  }
View Full Code Here
62
63
64
65
66
67
68
69
70
71
72
      sentences.add(toSentence(posSample));
      chunks++;
    }

    if (sentences.size() > 0)
      return new SentenceSample(detokenizer,
          sentences.toArray(new String[sentences.size()][]));
    else if (posSample != null)
      return read(); // filter out empty line
    else {
      return null; // last sample was read
View Full Code Here
121
122
123
124
125
126
127
      AnnotationFS sentenceAnnotation = (AnnotationFS) sentenceIterator.next();

      sentSpans[i++] = new Span(sentenceAnnotation.getBegin(), sentenceAnnotation.getEnd());
    }

    sentenceSamples.add(new SentenceSample(cas.getDocumentText(), sentSpans));
  }
View Full Code Here
62
63
64
65
66
67
68
69
70
71
72
      sentences.add(toSentence(posSample));
      chunks++;
    }

    if (sentences.size() > 0)
      return new SentenceSample(detokenizer,
          sentences.toArray(new String[sentences.size()][]));
    else if (posSample != null)
      return read(); // filter out empty line
    else {
      return null; // last sample was read
View Full Code Here
126
127
128
129
130
131
132
133
      doc = document.substring(0, document.length() - 1);
    } else {
      doc = document.toString();
    }

    return new SentenceSample(doc,
        sentences.toArray(new Span[sentences.size()]));
  }
View Full Code Here
56
57
58
59
60
61
62
63
64
65
66
67
68
69
        .getResourceAsStream("/opennlp/tools/formats/ad.sample");

    ADSentenceSampleStream stream = new ADSentenceSampleStream(
        new PlainTextByLineStream(in, "UTF-8"), true);

    SentenceSample sample = stream.read();

    while (sample != null) {
      System.out.println(sample.getDocument());
      System.out.println("<fim>");
      samples.add(sample);
      sample = stream.read();
    }
  }
View Full Code Here
57
58
59
60
61
62
63
64
65
66
67
68
69
70
        "/opennlp/tools/formats/ad.sample");

    ADSentenceSampleStream stream = new ADSentenceSampleStream(
        new PlainTextByLineStream(in, "UTF-8"), true);

    SentenceSample sample = stream.read();

    while (sample != null) {
      System.out.println(sample.getDocument());
      System.out.println("<fim>");
      samples.add(sample);
      sample = stream.read();
    }
  }
View Full Code Here
152
153
154
155
156
157
158
159
      doc = document.substring(0, document.length() - 1);
    } else {
      doc = document.toString();
    }

    return new SentenceSample(doc,
        sentences.toArray(new Span[sentences.size()]));
  }
View Full Code Here
147
148
149
150
151
152
153
    for (AnnotationFS sentenceAnnotation : sentenceIndex) {
      sentSpans[i++] = new Span(sentenceAnnotation.getBegin(), sentenceAnnotation.getEnd());
    }

    // TODO: The line cleaning should be done more carefully
    sentenceSamples.add(new SentenceSample(cas.getDocumentText().replace('\n', ' '), sentSpans));
  }
View Full Code Here
TOP

Related Classes of opennlp.tools.sentdetect.SentenceSample

  • opennlp.tools.formats.AbstractToSentenceSampleStream
  • opennlp.tools.formats.ad.ADSentenceSampleStream
  • opennlp.tools.formats.ad.ADSentenceSampleStreamTest
  • opennlp.tools.formats.convert.AbstractToSentenceSampleStream
  • opennlp.tools.tokenize.Detokenizer.DetokenizationOperation
  • opennlp.tools.util.Span
  • opennlp.uima.sentdetect.SentenceDetectorTrainer
    • 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.