public void addStartState () { addStartState ("<START>"); }
public void addStartState () { addStartState ("<START>"); }
public void addStartState () { addStartState ("<START>"); }
private void initializeFor(InstanceList examples) { this.crf = new CRF(examples.getPipe(), null); crf.addOrderNStates(examples, new int[]{1}, null, null, null, null, false); crf.addStartState(); crf.setWeightsDimensionAsIn(examples, false); if (crfFrom != null) { crf.initializeApplicableParametersFrom(crfFrom); } }
private TransducerTrainer trainOnce(Pipe pipe, InstanceList trainData) { Stopwatch watch = Stopwatch.createStarted(); CRF crf = new CRF(pipe, null); crf.addOrderNStates(trainData, new int[]{1}, null, null, null, null, false); crf.addStartState(); log.info("Starting alignTag training..."); CRFTrainerByThreadedLabelLikelihood trainer = new CRFTrainerByThreadedLabelLikelihood(crf, 8); trainer.setGaussianPriorVariance(2); // trainer.setUseSomeUnsupportedTrick(false); trainer.train(trainData); trainer.shutdown(); watch.stop(); log.info("Align Tag CRF Training took " + watch.toString()); crf.getInputAlphabet().stopGrowth(); crf.getOutputAlphabet().stopGrowth(); return trainer; }
private TransducerTrainer trainOnce(Pipe pipe, InstanceList examples) { Stopwatch watch = Stopwatch.createStarted(); CRF crf = new CRF(pipe, null); crf.addOrderNStates(examples, new int[]{1}, null, null, null, null, false); crf.addStartState(); // crf.setWeightsDimensionAsIn(examples, false); log.info("Starting syllchain training..."); CRFTrainerByThreadedLabelLikelihood trainer = new CRFTrainerByThreadedLabelLikelihood(crf, 8); trainer.setGaussianPriorVariance(2); // trainer.setUseSomeUnsupportedTrick(false); // trainer.setAddNoFactors(true); trainer.train(examples); trainer.shutdown(); watch.stop(); log.info("SyllChain CRF Training took " + watch.toString()); crf.getInputAlphabet().stopGrowth(); crf.getOutputAlphabet().stopGrowth(); return trainer; }
private TransducerTrainer trainOnce(Pipe pipe, InstanceList examples) { Stopwatch watch = Stopwatch.createStarted(); CRF crf = new CRF(pipe, null); crf.addOrderNStates(examples, new int[]{1}, null, null, null, null, false); crf.addStartState(); crf.setWeightsDimensionAsIn(examples, true); if (initFrom != null) { crf.initializeApplicableParametersFrom(initFrom); } log.info("Starting syllchain training..."); CRFTrainerByThreadedLabelLikelihood trainer = new CRFTrainerByThreadedLabelLikelihood(crf, 8); trainer.setGaussianPriorVariance(2); trainer.setAddNoFactors(true); // trainer.setUseSomeUnsupportedTrick(true); trainer.train(examples); trainer.shutdown(); watch.stop(); log.info("SyllChain CRF Training took " + watch.toString()); crf.getInputAlphabet().stopGrowth(); crf.getOutputAlphabet().stopGrowth(); return trainer; }
private TransducerTrainer trainOnce(Pipe pipe, InstanceList trainData) { Stopwatch watch = Stopwatch.createStarted(); CRF crf = new CRF(pipe, null); crf.addOrderNStates(trainData, new int[]{1}, null, null, null, null, false); crf.addStartState(); crf.setWeightsDimensionAsIn(trainData, false); if (initFrom != null) { crf.initializeApplicableParametersFrom(initFrom); } log.info("Starting alignTag training..."); CRFTrainerByThreadedLabelLikelihood trainer = new CRFTrainerByThreadedLabelLikelihood(crf, 8); trainer.setGaussianPriorVariance(2); trainer.setAddNoFactors(true); trainer.setUseSomeUnsupportedTrick(false); trainer.train(trainData); trainer.shutdown(); watch.stop(); log.info("Syll align Tag CRF Training took " + watch.toString()); crf.getInputAlphabet().stopGrowth(); crf.getOutputAlphabet().stopGrowth(); return trainer; }
private TransducerTrainer trainOnce(Pipe pipe, InstanceList trainData) { Stopwatch watch = Stopwatch.createStarted(); CRF crf = new CRF(pipe, null); // O,O O,N -O,C- // N,O N,N N,C // C,O ?C,N? C,C Pattern forbidden = null; if (USE_ONC_CODING) { forbidden = Pattern.compile("(O,C|<START>,C|O,<END>)", Pattern.CASE_INSENSITIVE); } crf.addOrderNStates(trainData, new int[]{1}, null, null, forbidden, null, false); crf.addStartState(); crf.setWeightsDimensionAsIn(trainData); if (this.pullFrom != null) { crf.initializeApplicableParametersFrom(pullFrom); } log.info("Starting syll phone training..."); CRFTrainerByThreadedLabelLikelihood trainer = new CRFTrainerByThreadedLabelLikelihood(crf, 8); trainer.setGaussianPriorVariance(2); trainer.setAddNoFactors(false); trainer.setUseSomeUnsupportedTrick(true); trainer.train(trainData); trainer.shutdown(); watch.stop(); pipe.getAlphabet().stopGrowth(); pipe.getTargetAlphabet().stopGrowth(); log.info("Align Tag CRF Training took " + watch.toString()); return trainer; }
public void testStartState() { Pipe p = new SerialPipes(new Pipe[] { new LineGroupString2TokenSequence(), new TokenSequenceMatchDataAndTarget(Pattern .compile("^(\\S+) (.*)"), 2, 1), new TokenSequenceParseFeatureString(false), new TokenText(), new TokenSequence2FeatureVectorSequence(true, false), new Target2LabelSequence(), new PrintInputAndTarget(), }); 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); }
public void testStartState() { Pipe p = new SerialPipes(new Pipe[] { new LineGroupString2TokenSequence(), new TokenSequenceMatchDataAndTarget(Pattern .compile("^(\\S+) (.*)"), 2, 1), new TokenSequenceParseFeatureString(false), new TokenText(), new TokenSequence2FeatureVectorSequence(true, false), new Target2LabelSequence(), new PrintInputAndTarget(), }); 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); }