Package opennlp.tools.dictionary

Examples of opennlp.tools.dictionary.Dictionary

337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
      System.exit(1);
    }
    ParserEventTypeEnum etype = null;
    boolean fun = false;
    int ai = 0;
    Dictionary dict = null;
    AbstractModel model = null;

    while (ai < args.length && args[ai].startsWith("-")) {
      if (args[ai].equals("-build")) {
        etype = ParserEventTypeEnum.BUILD;
      }
      else if (args[ai].equals("-attach")) {
        etype = ParserEventTypeEnum.ATTACH;
      }
      else if (args[ai].equals("-chunk")) {
        etype = ParserEventTypeEnum.CHUNK;
      }
      else if (args[ai].equals("-check")) {
        etype = ParserEventTypeEnum.CHECK;
      }
      else if (args[ai].equals("-tag")) {
        etype = ParserEventTypeEnum.TAG;
      }
      else if (args[ai].equals("-fun")) {
        fun = true;
      }
      else if (args[ai].equals("-dict")) {
        ai++;
        dict = new Dictionary(new FileInputStream(args[ai]));
      }
      else if (args[ai].equals("-model")) {
        ai++;
        model = (new SuffixSensitiveGISModelReader(new File(args[ai]))).getModel();
      }
View Full Code Here
116
117
118
119
120
121
122
123
124
125
126
127
128
129
    return new BinaryGISModelReader(new DataInputStream(new GZIPInputStream(
        new FileInputStream(fileName)))).getModel();
  }

  private static Dictionary readNames(String nameFile) throws IOException {
    Dictionary names = new Dictionary();

    BufferedReader nameReader = new BufferedReader(new FileReader(nameFile));
    for (String line = nameReader.readLine(); line != null; line = nameReader.readLine()) {
      names.put(new StringList(line));
    }

    return names;
  }
View Full Code Here
28
29
30
31
32
33
34
class DictionarySerializer implements ArtifactSerializer<Dictionary> {

  public Dictionary create(InputStream in) throws IOException,
      InvalidFormatException {
    return new Dictionary(in);
  }
View Full Code Here
282
283
284
285
286
287
288
289
290
291
292
  public static ParserModel train(String languageCode, ObjectStream<Parse> parseSamples, HeadRules rules, TrainingParameters mlParams)
          throws IOException {
   
    System.err.println("Building dictionary");
   
    Dictionary mdict = buildDictionary(parseSamples, rules, mlParams);
   
    parseSamples.reset();
   
    Map<String, String> manifestInfoEntries = new HashMap<String, String>();
   
View Full Code Here
442
443
444
445
446
447
448
449
450
451
452
  throws IOException {
   
    Map<String, String> manifestInfoEntries = new HashMap<String, String>();
   
    System.err.println("Building dictionary");
    Dictionary mdict = buildDictionary(parseSamples, rules, mlParams);
   
    parseSamples.reset();
   
    // tag
    POSModel posModel = POSTaggerME.train(languageCode, new PosSampleStream(
View Full Code Here
290
291
292
293
294
295
296
297
298
299
300
301
302
   *
   * @return a dictionary of the ngrams
   */
  public Dictionary toDictionary(boolean caseSensitive) {

    Dictionary dict = new Dictionary(caseSensitive);

    for (StringList stringList : this) {
      dict.put(stringList);
    }

    return dict;
  }
View Full Code Here
37
38
39
40
41
42
43
44
45
46
47
  @Override
  protected ParserModel trainAndUpdate(ParserModel originalModel,
      ObjectStream<Parse> parseSamples, ModelUpdaterParams parameters)
      throws IOException {
   
      Dictionary mdict = ParserTrainerTool.buildDictionary(parseSamples, originalModel.getHeadRules(), parameters.getCutoff());
     
      parseSamples.reset();
     
      // TODO: training individual models should be in the chunking parser, not here
      // Training build
View Full Code Here
52
53
54
55
56
57
58
59
60
61
62
  }
 
  static Dictionary buildDictionary(ObjectStream<Parse> parseSamples, HeadRules headRules, int cutoff) {
    System.err.print("Building dictionary ...");
   
    Dictionary mdict;
    try {
      mdict = Parser.
          buildDictionary(parseSamples, headRules, cutoff);
    } catch (IOException e) {
      System.err.println("Error while building dictionary: " + e.getMessage());
View Full Code Here
28
29
30
31
32
33
34
class DictionarySerializer implements ArtifactSerializer<Dictionary> {

  public Dictionary create(InputStream in) throws IOException,
      InvalidFormatException {
    return new Dictionary(in);
  }
View Full Code Here
38
39
40
41
42
43
44
45
46
47
48
  @Override
  protected ParserModel trainAndUpdate(ParserModel originalModel,
      ObjectStream<Parse> parseSamples, ModelUpdaterParams parameters)
      throws IOException {
   
      Dictionary mdict = ParserTrainerTool.buildDictionary(parseSamples, originalModel.getHeadRules(), parameters.getCutoff());
     
      parseSamples.reset();
     
      // TODO: Maybe that should be part of the ChunkingParser ...
      // Training build
View Full Code Here
TOP

Related Classes of opennlp.tools.dictionary.Dictionary

  • io.lumify.opennlpDictionary.OpenNLPDictionaryExtractorGraphPropertyWorker
  • io.lumify.opennlpDictionary.OpenNLPDictionaryExtractorGraphPropertyWorkerTest
  • opennlp.tools.cmdline.dictionary.DictionaryBuilderTool
  • opennlp.tools.cmdline.namefind.CensusDictionaryCreatorTool
  • opennlp.tools.cmdline.parser.BuildModelUpdaterTool
  • opennlp.tools.cmdline.parser.CheckModelUpdaterTool
  • opennlp.tools.cmdline.parser.ParserTrainerTool
  • opennlp.tools.cmdline.postag.POSTaggerTrainerTool
  • opennlp.tools.cmdline.sentdetect.SentenceDetectorCrossValidatorTool
  • opennlp.tools.cmdline.sentdetect.SentenceDetectorTrainerTool
    • 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.