public void testSpaceViewer () throws FileNotFoundException { Pipe pipe = TestMEMM.makeSpacePredictionPipe (); String[] data0 = { TestCRF.data[0] }; String[] data1 = { TestCRF.data[1] }; 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)); PrintStream out = new PrintStream (new FileOutputStream (htmlFile)); LatticeViewer.extraction2html (extration, extor, out); out.close(); out = new PrintStream (new FileOutputStream (latticeFile)); LatticeViewer.extraction2html (extration, extor, out, true); out.close(); }
public void testSpaceViewer () throws FileNotFoundException { Pipe pipe = TestMEMM.makeSpacePredictionPipe (); String[] data0 = { TestCRF.data[0] }; String[] data1 = { TestCRF.data[1] }; 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)); PrintStream out = new PrintStream (new FileOutputStream (htmlFile)); LatticeViewer.extraction2html (extration, extor, out); out.close(); out = new PrintStream (new FileOutputStream (latticeFile)); LatticeViewer.extraction2html (extration, extor, out, true); out.close(); }
public void testTrainStochasticGradient() { Pipe p = makeSpacePredictionPipe(); 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])); }
public void testTrainStochasticGradient() { Pipe p = makeSpacePredictionPipe(); 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])); }
.5, .5 }); CRF crf = new CRF(p, p2); crf.addFullyConnectedStatesForLabels(); CRFTrainerByLabelLikelihood crft = new CRFTrainerByLabelLikelihood(crf); if (testValueAndGradient) {
public void testSpaceViewer () throws IOException { Pipe pipe = TestMEMM.makeSpacePredictionPipe (); String[] data0 = { TestCRF.data[0] }; String[] data1 = { TestCRF.data[1] }; 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 = TestLatticeViewer.hackCrfExtor (crf); Extraction extraction = extor.extract (new ArrayIterator (data1)); if (!outputDir.exists ()) outputDir.mkdir (); DocumentViewer.writeExtraction (outputDir, extraction); }
public void testSpaceViewer () throws IOException { Pipe pipe = TestMEMM.makeSpacePredictionPipe (); String[] data0 = { TestCRF.data[0] }; String[] data1 = { TestCRF.data[1] }; 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 = TestLatticeViewer.hackCrfExtor (crf); Extraction extraction = extor.extract (new ArrayIterator (data1)); if (!outputDir.exists ()) outputDir.mkdir (); DocumentViewer.writeExtraction (outputDir, extraction); }
one.addThruPipe(new ArrayIterator(data)); CRF crf = new CRF(p, null); crf.addFullyConnectedStatesForLabels(); CRFTrainerByLabelLikelihood crft = new CRFTrainerByLabelLikelihood(crf); crf.setWeightsDimensionAsIn(one, false);
one.addThruPipe(new ArrayIterator(data)); CRF crf = new CRF(p, null); crf.addFullyConnectedStatesForLabels(); CRFTrainerByLabelLikelihood crft = new CRFTrainerByLabelLikelihood(crf); crf.setWeightsDimensionAsIn(one, false);
public void testTokenAccuracy() { Pipe p = makeSpacePredictionPipe(); 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]); TokenAccuracyEvaluator eval = new TokenAccuracyEvaluator(lists, new String[] { "Train", "Test" }); eval.evaluateInstanceList(crft, lists[1], "Test"); assertEquals(0.9409, eval.getAccuracy("Test"), 0.001); }
public void testTokenAccuracy() { Pipe p = makeSpacePredictionPipe(); 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]); TokenAccuracyEvaluator eval = new TokenAccuracyEvaluator(lists, new String[] { "Train", "Test" }); eval.evaluateInstanceList(crft, lists[1], "Test"); assertEquals(0.9409, eval.getAccuracy("Test"), 0.001); }
crf.addFullyConnectedStatesForLabels(); CRFTrainerByLabelLikelihood crft = new CRFTrainerByLabelLikelihood(crf); crft.trainIncremental(training);
crf.addFullyConnectedStatesForLabels(); CRFTrainerByLabelLikelihood crft = new CRFTrainerByLabelLikelihood(crf); crft.trainIncremental(training);
public void train(TextBlock textBlock) throws Exception { InstanceList trainingData = new InstanceList(getPipes()); for (TextSentence textSentence : textBlock) { Instance textInstance = new TextInstance(textSentence, getTargetAlphabet()); trainingData.addThruPipe(textInstance); } if (crf == null) { crf = new CRF(getPipes(), null); crf.addFullyConnectedStatesForLabels(); crf.setWeightsDimensionAsIn(trainingData, false); CRFOptimizableByLabelLikelihood optLabel = new CRFOptimizableByLabelLikelihood(crf, trainingData); Optimizable.ByGradientValue[] opts = new Optimizable.ByGradientValue[] { optLabel }; crfTrainer = new CRFTrainerByValueGradients(crf, opts); crfTrainer.setMaxResets(0); } crfTrainer.train(trainingData, Integer.MAX_VALUE); }
crf1.addFullyConnectedStatesForLabels(); CRFTrainerByLabelLikelihood crft1 = new CRFTrainerByLabelLikelihood( crf1); crf2.addFullyConnectedStatesForLabels();
crf1.addFullyConnectedStatesForLabels(); CRFTrainerByLabelLikelihood crft1 = new CRFTrainerByLabelLikelihood( crf1); crf2.addFullyConnectedStatesForLabels();
crf.addFullyConnectedStatesForLabels (); CRFTrainerByLabelLikelihood crft = new CRFTrainerByLabelLikelihood (crf); TokenAccuracyEvaluator eval = new TokenAccuracyEvaluator (new InstanceList[] {training, testing}, new String[] {"Training", "Testing"});
crf.addFullyConnectedStatesForLabels (); CRFTrainerByLabelLikelihood crft = new CRFTrainerByLabelLikelihood (crf); TokenAccuracyEvaluator eval = new TokenAccuracyEvaluator (new InstanceList[] {training, testing}, new String[] {"Training", "Testing"});
public void testXis() { 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()) { Transducer.State dest = it.nextState(); double xi = lattice.getXiProbability(ip, state, dest); xiSum += xi; } assertEquals(gamma, xiSum, 1e-5); } } }
public void testXis() { 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()) { Transducer.State dest = it.nextState(); double xi = lattice.getXiProbability(ip, state, dest); xiSum += xi; } assertEquals(gamma, xiSum, 1e-5); } } }