Package opennlp.tools.dictionary

Examples of opennlp.tools.dictionary.Dictionary

42
43
44
45
46
47
48
49
50
51
52
  @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
88
89
90
91
92
93
94
95
96
97
98
      mlParams.put(TrainingParameters.CUTOFF_PARAM,
          Integer.toString(params.getCutoff()));
    }

    try {
      Dictionary abbreviations = SentenceDetectorTrainerTool.loadDict(params
          .getAbbDict());
      validator = new SDCrossValidator(params.getLang(), mlParams,
          abbreviations, errorListener);
     
      validator.evaluate(sampleStream, params.getFolds());
View Full Code Here
67
68
69
70
71
72
73
74
75
76
77
78
    return new SentenceSampleStream(lineStream);
  }
 
  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
104
105
106
107
108
109
110
111
112
113
114
    ObjectStream<SentenceSample> sampleStream =
        openSampleData("Training", trainingDataInFile, params.getEncoding());

    SentenceModel model;
    try {
      Dictionary dict = loadDict(params.getAbbDict());
      if (mlParams == null) {
        model = SentenceDetectorME.train(params.getLang(), sampleStream, true, dict,
            params.getCutoff(), params.getIterations());
      }
      else {
View Full Code Here
93
94
95
96
97
98
99
100
101
102
103
    CmdLineUtil.checkOutputFile("pos tagger model", modelOutFile);
    ObjectStream<POSSample> sampleStream = openSampleData("Training", trainingDataInFile,
        params.getEncoding());
   
   
    Dictionary ngramDict = null;
   
    Integer ngramCutoff = params.getNgram();
   
    if (ngramCutoff != null) {
      System.err.print("Building ngram dictionary ... ");
View Full Code Here
41
42
43
44
45
46
47
48
49
50
51
  @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
84
85
86
87
88
89
90
91
92
93
94
  }
 
  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
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
195
196
197
198
199
200
201
202
203
204
205
206
207
        System.exit(1);
      }
      ai++;
    }
    HeadRules rules = new opennlp.tools.parser.lang.en.HeadRules(args[ai++]);
    Dictionary dict = null;
    if (ai < args.length) {
      dict = new Dictionary(new FileInputStream(args[ai++]),true);
    }
    if (fun) {
      Parse.useFunctionTags(true);
    }
    opennlp.model.EventStream es = new ParserEventStream(new ParseSampleStream(new PlainTextByLineStream(new java.io.InputStreamReader(System.in))), rules, etype, dict);
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.