Package opennlp.tools.sentdetect

Examples of opennlp.tools.sentdetect.SentenceModel

323
324
325
326
327
328
329
330
331
332
333
                type,language),e);
        }
    }
    private SentenceModel getSentenceModel(String language) {
        try {
            SentenceModel model = openNLP.getSentenceModel(language);
            if(model != null){
                return model;
            } else {
                throw new IllegalStateException(String.format(
                    "Unable to built Model for extracting sentences from '%s' " +
View Full Code Here
298
299
300
301
302
303
304
305
306
307
308
        if(!config.enableSentenceDetector){
            return null;
        }
        if(sentenceDetector == null && !sentenceDetectorNotAvailable){
            try {
                SentenceModel sentModel = openNLP.getSentenceModel(language);
                if(sentModel != null){
                    sentenceDetector = new SentenceDetectorME(sentModel);
                } else {
                    log.debug("No Sentence Detection Model for language '{}'",language);
                    sentenceDetectorNotAvailable = true;
View Full Code Here
55
56
57
58
59
60
61
62
63
64
65
    if (encoding == null) {
      System.out.println(getHelp());
      throw new TerminateToolException(1);
    }
   
    SentenceModel model = new SentenceModelLoader().load(new File(CmdLineUtil.getParameter("-model", args)));
   
    File trainingDataInFile = new File(CmdLineUtil.getParameter("-data", args));
    CmdLineUtil.checkInputFile("Training Data", trainingDataInFile);
   
    opennlp.tools.sentdetect.SentenceDetectorEvaluator evaluator =
View Full Code Here
79
80
81
82
83
84
85
86
87
88
89
    CmdLineUtil.checkOutputFile("sentence detector model", modelOutFile);
    ObjectStream<SentenceSample> sampleStream =
        openSampleData("Training", trainingDataInFile, parameters.getEncoding());
   
    SentenceModel model;
    try {
      model = SentenceDetectorME.train(parameters.getLanguage(), sampleStream, true, null,
          parameters.getCutoff(), parameters.getNumberOfIterations());
    } catch (IOException e) {
      CmdLineUtil.printTrainingIoError(e);
View Full Code Here
86
87
88
89
90
91
92
93
94
95
96
    int numParses = 5;

    // the sentence detector and tokenizer constructors
    // take paths to their respective models
    SentenceDetectorME sdetector = new SentenceDetectorME(
        new SentenceModel(new FileInputStream(
            "models/en-sent.bin")));
    Tokenizer tokenizer = new TokenizerME(new TokenizerModel(
        new FileInputStream("models/en-token.bin")));

    // the parser takes the path to the parser models
View Full Code Here
69
70
71
72
73
74
75
   * @throws IOException
   */
  public ApacheExtractor() throws IOException {
    nameFinder = new NameFinderME(new TokenNameFinderModel(ApacheExtractor.class.getResourceAsStream(pathToNERModel)));
    tokenizer = new TokenizerME(new TokenizerModel(ApacheExtractor.class.getResourceAsStream(pathToTokenizerModel)));
        sentenceDetector = new SentenceDetectorME(new SentenceModel(ApacheExtractor.class.getResourceAsStream(pathToSentenceDetectorModel)));
  }
View Full Code Here
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
    }
   
   
    private SentenceDetector getSentenceDetector(String language) {
        try {
            SentenceModel model = openNLP.getSentenceModel(language);
            if(model != null) {
                log.debug("Sentence Detection Model {} for lanugage '{}' version: {}",
                    new Object[]{model.getClass().getSimpleName(),
                                 model.getLanguage(),
                                 model.getVersion() != null ? model.getVersion() : "undefined"});
                return new SentenceDetectorME(model);
            }
        } catch (Exception e) {
        }
        log.debug("Sentence Detection Model for Language '{}' not available.", language);
View Full Code Here
TOP

Related Classes of opennlp.tools.sentdetect.SentenceModel

  • com.bericotech.clavin.extractor.ApacheExtractor
  • com.tamingtext.frankenstein.Frankenstein
  • com.tamingtext.sentences.SentenceDetectionTest
  • com.tamingtext.texttamer.solr.NameFilterTest
  • com.tamingtext.util.SentenceDetectorFactory
  • edu.washington.cs.knowitall.util.DefaultObjects
  • functionality.Models
  • ivory.lsh.bitext.PreprocessHelper
  • kpi.asoiu.parsers.ParseText
  • net.sf.nlpshell.Main
    • 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.