Package cc.mallet.fst

Examples of cc.mallet.fst.CRF

395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
      }
    } else
      testFile = new FileReader(new File(args[restArgs]));

    Pipe p = null;
    CRF crf = null;
    TransducerEvaluator eval = null;
    if (continueTrainingOption.value || !trainOption.value) {
      if (modelOption.value == null)
      {
        commandOptions.printUsage(true);
        throw new IllegalArgumentException("Missing model file option");
      }
      ObjectInputStream s =
        new ObjectInputStream(new FileInputStream(modelOption.value));
      crf = (CRF) s.readObject();
      s.close();
      p = crf.getInputPipe();
    }
    else {
      p = new SimpleTaggerSentence2FeatureVectorSequence();
      p.getTargetAlphabet().lookupIndex(defaultOption.value);
    }
View Full Code Here
91
92
93
94
95
96
97
98
99
100
101
      else {
        constraints2.add(constraint);
      }
    }
   
    CRF crf = (CRF)transducer;
   
    double dotEx = this.runForward(crf, constraints1, constraints2, gammas, xis, reverseTrans, fvs);
    this.runBackward(crf, gammas, xis, reverseTrans, reverseTransIndices, fvs, dotEx, gradient);
    //check(constraints,gammas,xis,fvs);
  }
View Full Code Here
383
384
385
386
387
388
389
390
391
392
393
    Sequence predicted = docextr.getPredictedLabels ();

    ExtorInfo info = new ExtorInfo (input, predicted, target, desc, idx);

    if (showLattice == true) {
      CRF crf = extor.getCrf();
      // xxx perhaps the next two lines could be a transducer method???
      Instance carrier = extor.getFeaturePipe().pipe(new Instance (input, null, null, null));
      info.fvs = (FeatureVectorSequence) carrier.getData ();
      info.lattice = new MaxLatticeDefault (crf, (Sequence) carrier.getData(), null);
      info.bestStates = info.lattice.bestOutputSequence();
View Full Code Here
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
    Pipe p = makeSpacePredictionPipe();

    InstanceList instances = new InstanceList(p);
    instances.addThruPipe(new ArrayIterator(data));

    CRF crf1 = new CRF(p, null);
    crf1.addFullyConnectedStatesForLabels();
    CRFTrainerByLabelLikelihood crft1 = new CRFTrainerByLabelLikelihood(
        crf1);
    crft1.train(instances, 10); // Let's get some parameters

    Instance inst = instances.get(0);
    Sequence input = (Sequence) inst.getData();
    SumLatticeDefault lattice = new SumLatticeDefault(crf1, input,
        (Sequence) inst.getTarget(), null, true);
    for (int ip = 0; ip < lattice.length() - 1; ip++) {
      for (int i = 0; i < crf1.numStates(); i++) {
        Transducer.State state = crf1.getState(i);
        Transducer.TransitionIterator it = state.transitionIterator(
            input, ip);
        double gamma = lattice.getGammaProbability(ip, state);
        double xiSum = 0;
        while (it.hasNext()) {
View Full Code Here
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
    training.addThruPipe(new ArrayIterator(data)); // This used to be
    // MEMM.data, but I
    // don't know why -akm
    // 12/2007

    CRF crf = new CRF(p, null);
    crf.addFullyConnectedStatesForLabels();
    CRFTrainerByLabelLikelihood crft = new CRFTrainerByLabelLikelihood(crf);
    crft.trainIncremental(training);

    // Check that the notstart state is used at test time
    Sequence input = (Sequence) training.get(0).getData();
    Sequence output = new MaxLatticeDefault(crf, input)
        .bestOutputSequence();

    boolean notstartFound = false;
    for (int i = 0; i < output.size(); i++) {
      if (output.get(i).toString().equals("notstart")) {
        notstartFound = true;
      }
    }
    System.err.println(output.toString());
    assertTrue(notstartFound);

    // Now add -infinite weight onto a transition, and make sure that it's
    // honored.
    CRF.State state = crf.getState("notstart");
    int widx = crf.getWeightsIndex("BadBad");
    int numFeatures = crf.getInputAlphabet().size();
    SparseVector w = new SparseVector(new double[numFeatures]);
    w.setAll(Double.NEGATIVE_INFINITY);
    crf.setWeights(widx, w);

    state.addWeight(0, "BadBad");
    state.addWeight(1, "BadBad");

    // Verify that this effectively prevents the notstart state from being
View Full Code Here
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
  private static String oldCrfFile = "test/edu/umass/cs/mallet/base/fst/crf.cnl03.ser.gz";
  private static String testString = "John NNP B-NP O\nDoe NNP I-NP O\nsaid VBZ B-VP O\nhi NN B-NP O\n";

  public void skiptestOldCrf() {
    CRF crf = (CRF) FileUtils.readObject(new File(oldCrfFile));
    Instance inst = crf.getInputPipe().instanceFrom(
        new Instance(testString, null, null, null));
    Sequence output = crf.transduce((Sequence) inst.getData());
    String std = output.toString();
    assertEquals(" B-PER I-PER O O", std);
  }
View Full Code Here
TOP

Related Classes of cc.mallet.fst.CRF

  • cc.mallet.extract.CRFExtractor
  • cc.mallet.extract.LatticeViewer
  • cc.mallet.extract.test.TestDocumentViewer
  • cc.mallet.extract.test.TestLatticeViewer
  • cc.mallet.fst.semi_supervised.GELattice
  • cc.mallet.fst.semi_supervised.tui.SimpleTaggerWithConstraints
  • cc.mallet.fst.tests.TestCRF
  • cc.mallet.pipe.Noop
  • cc.mallet.types.Alphabet
  • cc.mallet.types.FeatureInducer
    • 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.