Package opennlp.tools.util

Examples of opennlp.tools.util.HashSumEventStream

246
247
248
249
250
251
252
253
254
255
256
257
258
259
      // TODO: Fix the EventStream to throw exceptions when training goes wrong
      EventStream eventStream = new SDEventStream(samples,
          factory.createSentenceContextGenerator(languageCode),
          factory.createEndOfSentenceScanner(languageCode));
     
      HashSumEventStream hses = new HashSumEventStream(eventStream);
      GISModel sentModel = GIS.trainModel(hses, iterations, cutoff);

      manifestInfoEntries.put(BaseModel.TRAINING_EVENTHASH_PROPERTY,
          hses.calculateHashSum().toString(16));
     
      return new SentenceModel(languageCode, sentModel,
          useTokenEnd, abbreviations, manifestInfoEntries);
    }
View Full Code Here
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
    ModelUtil.addCutoffAndIterations(manifestInfoEntries, cut, iterations);
   
    // build
    System.err.println("Training builder");
    opennlp.model.EventStream bes = new ParserEventStream(parseSamples, rules, ParserEventTypeEnum.BUILD, mdict);
    HashSumEventStream hsbes = new HashSumEventStream(bes);
    AbstractModel buildModel = train(hsbes, iterations, cut);
    manifestInfoEntries.put("Training-Builder-Eventhash",
        hsbes.calculateHashSum().toString(16));
   
    parseSamples.reset();
   
    // tag
    POSModel posModel = POSTaggerME.train(languageCode, new PosSampleStream(parseSamples),
        ModelType.MAXENT, null, null, cut, iterations);
   
    parseSamples.reset();
   
    // chunk
    ChunkerModel chunkModel = ChunkerME.train(languageCode,
        new ChunkSampleStream(parseSamples), cut, iterations,
        new ChunkContextGenerator());
   
    parseSamples.reset();
   
    // check
    System.err.println("Training checker");
    opennlp.model.EventStream kes = new ParserEventStream(parseSamples, rules, ParserEventTypeEnum.CHECK);
    HashSumEventStream hskes = new HashSumEventStream(kes);
    AbstractModel checkModel = train(hskes, iterations, cut);
    manifestInfoEntries.put("Training-Checker-Eventhash",
        hskes.calculateHashSum().toString(16));
   
    // TODO: Remove cast for HeadRules
    return new ParserModel(languageCode, buildModel, checkModel,
        posModel, chunkModel, (opennlp.tools.parser.lang.en.HeadRules) rules,
        ParserType.CHUNKING, manifestInfoEntries);
View Full Code Here
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
   
    Map<String, String> manifestInfoEntries = new HashMap<String, String>();
    ModelUtil.addCutoffAndIterations(manifestInfoEntries, cutoff, iterations);
   
    EventStream es = new ChunkerEventStream(in, contextGenerator);
    HashSumEventStream hses = new HashSumEventStream(es);
   
    AbstractModel maxentModel = opennlp.maxent.GIS.trainModel(iterations,
        new TwoPassDataIndexer(hses, cutoff));
   
    manifestInfoEntries.put(BaseModel.TRAINING_EVENTHASH_PROPERTY,
        hses.calculateHashSum().toString(16));
   
    return new ChunkerModel(lang, maxentModel, manifestInfoEntries);
  }
View Full Code Here
339
340
341
342
343
344
345
346
347
348
349
350
351
352
     else
       featureGenerator = createFeatureGenerator();
    
     EventStream eventStream = new NameFinderEventStream(samples, type,
         new DefaultNameContextGenerator(featureGenerator));
     HashSumEventStream hses = new HashSumEventStream(eventStream);
     AbstractModel nameFinderModel = GIS.trainModel(iterations, new TwoPassDataIndexer(hses, cutoff));
    
     manifestInfoEntries.put(BaseModel.TRAINING_EVENTHASH_PROPERTY,
         hses.calculateHashSum().toString(16));
    
     return new TokenNameFinderModel(languageCode, nameFinderModel,
         resources, manifestInfoEntries);
   }
View Full Code Here
TOP

Related Classes of opennlp.tools.util.HashSumEventStream

  • opennlp.model.Event
  • opennlp.tools.chunker.ChunkerME
  • opennlp.tools.ml.model.Event
  • opennlp.tools.namefind.NameFinderME
  • opennlp.tools.parser.chunking.Parser
  • org.apache.ctakes.core.sentence.SentenceDetectorCtakes
  • java.math.BigInteger
    • 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.