Package opennlp.tools.dictionary

Examples of opennlp.tools.dictionary.Dictionary

80
81
82
83
84
85
86
87
88
89
90
      eos = params.getEosChars().toCharArray();

    SentenceModel model;

    try {
      Dictionary dict = loadDict(params.getAbbDict());
      SentenceDetectorFactory sdFactory = SentenceDetectorFactory.create(
          params.getFactory(), params.getLang(), true, dict, eos);
      model = SentenceDetectorME.train(params.getLang(), sampleStream,
          sdFactory, mlParams);
    } catch (IOException e) {
View Full Code Here
160
161
162
163
164
165
166
167
168
169
170
      if (this.factory == null) {
        this.factory = POSTaggerFactory.create(this.factoryClassName, null,
            null);
      }

      Dictionary ngramDict = this.factory.getDictionary();
      if (ngramDict == null) {
        if(this.ngramCutoff != null) {
          System.err.print("Building ngram dictionary ... ");
          ngramDict = POSTaggerME.buildNGramDictionary(trainingSampleStream,
              this.ngramCutoff);
View Full Code Here
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
          if (dict == null) {
            ss = new POSSampleSequenceStream(new WordTagSampleStream(
                new InputStreamReader(new FileInputStream(inFile))));
          }
          else {
            POSContextGenerator cg = new DefaultPOSContextGenerator(new Dictionary(new FileInputStream(dict)));

            ss = new POSSampleSequenceStream(new WordTagSampleStream((
                new InputStreamReader(new FileInputStream(inFile)))),
                cg);
          }
        }
        else {
          if (dict == null) {

            ss = new POSSampleSequenceStream(new WordTagSampleStream((
                new InputStreamReader(new FileInputStream(inFile), encoding))));
          }
          else {
            POSContextGenerator cg = new DefaultPOSContextGenerator(new Dictionary(new FileInputStream(dict)));

            ss = new POSSampleSequenceStream(new WordTagSampleStream((
                new InputStreamReader(new FileInputStream(inFile), encoding))), cg);
          }
        }
        mod = new SimplePerceptronSequenceTrainer().trainModel(iterations, ss, cutoff, true);
        System.out.println("Saving the model as: " + outFile);
        new SuffixSensitivePerceptronModelWriter(mod, outFile).persist();
      }
      else {
        POSSampleEventStream es;
        if (encoding == null) {
          if (dict == null) {
            es = new POSSampleEventStream(new WordTagSampleStream((
                new InputStreamReader(new FileInputStream(inFile)))));
          }
          else {
            POSContextGenerator cg = new DefaultPOSContextGenerator(new Dictionary(new FileInputStream(dict)));

            es = new POSSampleEventStream(new WordTagSampleStream((
                new InputStreamReader(new FileInputStream(inFile)))),
                cg);
          }
        }
        else {
          if (dict == null) {

            es = new POSSampleEventStream(new WordTagSampleStream((
                new InputStreamReader(new FileInputStream(inFile), encoding))));
          }
          else {
            POSContextGenerator cg = new DefaultPOSContextGenerator(new Dictionary(new FileInputStream(dict)));

            es = new POSSampleEventStream(new WordTagSampleStream((
                new InputStreamReader(new FileInputStream(inFile), encoding))), cg);
          }
        }
View Full Code Here
293
294
295
296
297
298
299
300
301
    }

    System.out.println("Saving the dictionary");

    ngramModel.cutoff(cutoff, Integer.MAX_VALUE);
    Dictionary dictionary = ngramModel.toDictionary(true);

    dictionary.serialize(new FileOutputStream(dict));
  }
View Full Code Here
59
60
61
62
63
64
65
66
67
68
69
  @Test
  public void testPOSTaggerWithCustomFactory() throws IOException {
    DummyPOSDictionary posDict = new DummyPOSDictionary(
        POSDictionary.create(POSDictionaryTest.class
            .getResourceAsStream("TagDictionaryCaseSensitive.xml")));
    Dictionary dic = POSTaggerME.buildNGramDictionary(createSampleStream(), 0);

    POSModel posModel = trainPOSModel(ModelType.MAXENT,
        new DummyPOSTaggerFactory(dic, posDict));

    POSTaggerFactory factory = posModel.getFactory();
View Full Code Here
86
87
88
89
90
91
92
93
94
95
96
 
  @Test
  public void testPOSTaggerWithDefaultFactory() throws IOException {
    POSDictionary posDict = POSDictionary.create(POSDictionaryTest.class
            .getResourceAsStream("TagDictionaryCaseSensitive.xml"));
    Dictionary dic = POSTaggerME.buildNGramDictionary(createSampleStream(), 0);

    POSModel posModel = trainPOSModel(ModelType.MAXENT,
        new POSTaggerFactory(dic, posDict));

    POSTaggerFactory factory = posModel.getFactory();
View Full Code Here
46
47
48
49
50
51
52
53
54
55
56
57
  public String getShortDescription() {
    return "trainer for the learnable tokenizer";
  }

  static Dictionary loadDict(File f) throws IOException {
    Dictionary dict = null;
    if (f != null) {
      CmdLineUtil.checkInputFile("abb dict", f);
      dict = new Dictionary(new FileInputStream(f));
    }
    return dict;
  }
View Full Code Here
79
80
81
82
83
84
85
86
87
88
89
    File modelOutFile = params.getModel();
    CmdLineUtil.checkOutputFile("tokenizer model", modelOutFile);

    TokenizerModel model;
    try {
      Dictionary dict = loadDict(params.getAbbDict());

      TokenizerFactory tokFactory = TokenizerFactory.create(
          params.getFactory(), params.getLang(), dict,
          params.getAlphaNumOpt(), null);
      model = opennlp.tools.tokenize.TokenizerME.train(sampleStream,
View Full Code Here
60
61
62
63
64
65
66
67
68
69
70
    if (params.getMisclassified()) {
      listener = new TokenEvaluationErrorListener();
    }
   
    try {
      Dictionary dict = TokenizerTrainerTool.loadDict(params.getAbbDict());

      TokenizerFactory tokFactory = TokenizerFactory.create(
          params.getFactory(), params.getLang(), dict,
          params.getAlphaNumOpt(), null);
      validator = new opennlp.tools.tokenize.TokenizerCrossValidator(mlParams,
View Full Code Here
67
68
69
70
71
72
73
74
75
76
77
    }

    File modelOutFile = params.getModel();
    CmdLineUtil.checkOutputFile("pos tagger model", modelOutFile);

    Dictionary ngramDict = null;
   
    Integer ngramCutoff = params.getNgram();
   
    if (ngramCutoff != null) {
      System.err.print("Building ngram dictionary ... ");
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.