Package cc.mallet.fst

Examples of cc.mallet.fst.CRF

732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
    Pipe p2 = new TestCRF2String();

    InstanceList instances = new InstanceList(p);
    instances.addThruPipe(new ArrayIterator(data));
    InstanceList[] lists = instances.split(new double[] { .5, .5 });
    CRF crf = new CRF(p, p2);
    crf.addFullyConnectedStatesForLabels();
    crf.setWeightsDimensionAsIn(lists[0], false);
    CRFTrainerByStochasticGradient crft = new CRFTrainerByStochasticGradient(
        crf, 0.0001);
    System.out.println("Training Accuracy before training = "
        + crf.averageTokenAccuracy(lists[0]));
    System.out.println("Testing  Accuracy before training = "
        + crf.averageTokenAccuracy(lists[1]));
    System.out.println("Training...");
    // either fixed learning rate or selected on a sample
    crft.setLearningRateByLikelihood(lists[0]);
    // crft.setLearningRate(0.01);
    crft.train(lists[0], 100);
    crf.print();
    System.out.println("Training Accuracy after training = "
        + crf.averageTokenAccuracy(lists[0]));
    System.out.println("Testing  Accuracy after training = "
        + crf.averageTokenAccuracy(lists[1]));
  }
View Full Code Here
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
    // first do normal training for getting weights
    InstanceList instances = new InstanceList(p);
    instances.addThruPipe(new ArrayIterator(data));
    InstanceList[] lists = instances.split(new double[] { .5, .5 });
    CRF crf = new CRF(p, p2);
    crf.addFullyConnectedStatesForLabels();
    crf.setWeightsDimensionAsIn(lists[0], false);
    CRFTrainerByStochasticGradient crft = new CRFTrainerByStochasticGradient(
        crf, 0.0001);
    System.out.println("Training Accuracy before training = "
        + crf.averageTokenAccuracy(lists[0]));
    System.out.println("Testing  Accuracy before training = "
        + crf.averageTokenAccuracy(lists[1]));
    System.out.println("Training...");
    // either fixed learning rate or selected on a sample
    crft.setLearningRateByLikelihood(lists[0]);
    // crft.setLearningRate(0.01);
    crft.train(lists[0], 100);
    crf.print();
    System.out.println("Training Accuracy after training = "
        + crf.averageTokenAccuracy(lists[0]));
    System.out.println("Testing  Accuracy after training = "
        + crf.averageTokenAccuracy(lists[1]));

    // now check the speeds of SumLatticeDefault vs SumLatticeScaling
    long totalTimeDefault = 0, totalTimeScaling = 0;
    for (int iter = 0; iter < 10000; iter++) {
      for (int ii = 0; ii < lists[1].size(); ii++) {
View Full Code Here
853
854
855
856
857
858
859
860
861
862
863
864
    InstanceList instances = new InstanceList(p);
    instances.addThruPipe(new ArrayIterator(data));
    InstanceList[] lists = instances.split(new Random(777), new double[] {
        .5, .5 });

    CRF crf = new CRF(p.getDataAlphabet(), p.getTargetAlphabet());
    crf.addFullyConnectedStatesForLabels();
    CRFTrainerByLabelLikelihood crft = new CRFTrainerByLabelLikelihood(crf);
    crft.setUseSparseWeights(true);

    crft.trainIncremental(lists[0]);
View Full Code Here
54
55
56
57
58
59
60
61
62
63
64
65
    InstanceList training = new InstanceList (pipe);
    training.addThruPipe (new ArrayIterator (data0));
    InstanceList testing = new InstanceList (pipe);
    testing.addThruPipe (new ArrayIterator (data1));

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

    CRFExtractor extor = hackCrfExtor (crf);
    Extraction extration = extor.extract (new ArrayIterator (data1));
View Full Code Here
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
        new TokenSequence2FeatureVectorSequence(),
        new PrintInputAndTarget(), });
    InstanceList one = new InstanceList(p);
    String[] data = new String[] { "ABCDE", };
    one.addThruPipe(new ArrayIterator(data));
    CRF crf = new CRF(p, null);
    crf.addFullyConnectedStatesForThreeQuarterLabels(one);
    CRFTrainerByLabelLikelihood crft = new CRFTrainerByLabelLikelihood(crf);
    crf.setWeightsDimensionAsIn(one, false);
    Optimizable mcrf = crft.getOptimizableCRF(one);
    double[] params = new double[mcrf.getNumParameters()];
    for (int i = 0; i < params.length; i++) {
      params[i] = i;
    }
    mcrf.setParameters(params);
    crf.print();
  }
View Full Code Here
104
105
106
107
108
109
110
111
112
113
114
115
    InstanceList training = new InstanceList (pipe);
    training.addThruPipe (new ArrayIterator (data0));
    InstanceList testing = new InstanceList (pipe);
    testing.addThruPipe (new ArrayIterator (data1));

    CRF crf = new CRF (pipe, null);
    crf.addFullyConnectedStatesForLabels ();
    CRFTrainerByLabelLikelihood crft = new CRFTrainerByLabelLikelihood (crf);
    TokenAccuracyEvaluator eval = new TokenAccuracyEvaluator (new InstanceList[] {training, testing}, new String[] {"Training", "Testing"});
    for (int i = 0; i < 5; i++) {
      crft.train (training, 1);
      eval.evaluate(crft);
View Full Code Here
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
        new TokenSequence2FeatureVectorSequence(),
        new PrintInputAndTarget(), });
    InstanceList one = new InstanceList(p);
    String[] data = new String[] { "ABCDE", };
    one.addThruPipe(new ArrayIterator(data));
    CRF crf = new CRF(p, null);
    crf.addFullyConnectedStatesForLabels();
    CRFTrainerByLabelLikelihood crft = new CRFTrainerByLabelLikelihood(crf);
    crf.setWeightsDimensionAsIn(one, false);
    Optimizable.ByGradientValue mcrf = crft.getOptimizableCRF(one);
    double[] params = new double[mcrf.getNumParameters()];
    for (int i = 0; i < params.length; i++) {
      params[i] = i;
    }
    mcrf.setParameters(params);

    StringWriter out = new StringWriter();
    crf.print(new PrintWriter(out, true));
    System.out.println("------------- CRF1 -------------");
    crf.print();

    // Make a copy of this CRF
    CRF crf2 = new CRF(crf);

    StringWriter out2 = new StringWriter();
    crf2.print(new PrintWriter(out2, true));
    System.out.println("------------- CRF2 -------------");
    crf2.print();

    assertEquals(out.toString(), out2.toString());

    double val1 = mcrf.getValue();
    CRFTrainerByLabelLikelihood crft2 = new CRFTrainerByLabelLikelihood(
View Full Code Here
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
    InstanceList data = new InstanceList(p);
    data.addThruPipe(new LineGroupIterator(new StringReader(toy), Pattern
        .compile("\n"), true));

    CRF crf = new CRF(p, null);
    crf.print();
    crf.addStatesForLabelsConnectedAsIn(data);
    crf.addStartState();
    CRFTrainerByLabelLikelihood crft = new CRFTrainerByLabelLikelihood(crf);

    Optimizable.ByGradientValue maxable = crft.getOptimizableCRF(data);
    assertEquals(-1.3862, maxable.getValue(), 1e-4);

    crf = new CRF(p, null);
    crf
        .addOrderNStates(data, new int[] { 1 }, null, "A", null, null,
            false);
    crf.print();
    crft = new CRFTrainerByLabelLikelihood(crf);

    maxable = crft.getOptimizableCRF(data);
    assertEquals(-3.09104245335831, maxable.getValue(), 1e-4);
  }
View Full Code Here
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
    InstanceList instances = new InstanceList(p);
    instances.addThruPipe(new ArrayIterator(data));

    // Test that dense observations wights aren't added for
    // "default-feature" edges.
    CRF crf1 = new CRF(p, null);
    crf1.addOrderNStates(instances, new int[] { 0 }, null, "start", null,
        null, true);
    CRFTrainerByLabelLikelihood crft1 = new CRFTrainerByLabelLikelihood(
        crf1);
    crft1.setUseSparseWeights(false);
    crft1.train(instances, 1); // Set weights dimension
    int nParams1 = crft1.getOptimizableCRF(instances).getNumParameters();

    CRF crf2 = new CRF(p, null);
    crf2.addOrderNStates(instances, new int[] { 0, 1 }, new boolean[] {
        false, true }, "start", null, null, true);
    CRFTrainerByLabelLikelihood crft2 = new CRFTrainerByLabelLikelihood(
        crf2);
    crft2.setUseSparseWeights(false);
    crft2.train(instances, 1); // Set weights dimension
View Full Code Here
265
266
267
268
269
270
271
272
273
274
275
276
277
278
  }
 
  public static CRF getCRF(InstanceList training, int[] orders, String defaultLabel, String forbidden, String allowed, boolean connected) {
    Pattern forbiddenPat = Pattern.compile(forbidden);
    Pattern allowedPat = Pattern.compile(allowed);
    CRF crf = new CRF(training.getPipe(), (Pipe)null);
    String startName = crf.addOrderNStates(training, orders, null,
        defaultLabel, forbiddenPat, allowedPat, connected);
    for (int i = 0; i < crf.numStates(); i++)
      crf.getState(i).setInitialWeight (Transducer.IMPOSSIBLE_WEIGHT);
    crf.getState(startName).setInitialWeight(0.0);
    crf.setWeightsDimensionDensely();
    return crf;
  }
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.