Examples with Parser edu.illinois.cs.cogcomp.lbjava.parse.Parser used on opensource projects

Example 1 with Parser

use of edu.illinois.cs.cogcomp.lbjava.parse.Parser in project cogcomp-nlp by CogComp.

the class LearningCurveMultiDataset method getLearningCurve.

/**
     * use fixedNumIterations=-1 if you want to use the automatic convergence criterion
     * <p>
     * NB: assuming column format
     */
public static void getLearningCurve(Vector<Data> trainDataSet, Vector<Data> testDataSet, int fixedNumIterations) throws Exception {
    double bestF1Level1 = -1;
    int bestRoundLevel1 = 0;
    // Get the directory name (<configname>.model is appended in LbjTagger/Parameters.java:139)
    String modelPath = ParametersForLbjCode.currentParameters.pathToModelFile;
    String modelPathDir = modelPath.substring(0, modelPath.lastIndexOf("/"));
    if (IOUtils.exists(modelPathDir)) {
        if (!IOUtils.isDirectory(modelPathDir)) {
            String msg = "ERROR: " + NAME + ".getLearningCurve(): model directory '" + modelPathDir + "' already exists as a (non-directory) file.";
            logger.error(msg);
            throw new IOException(msg);
        } else
            logger.warn(NAME + ".getLearningCurve(): writing to existing model path '" + modelPathDir + "'...");
    } else {
        IOUtils.mkdir(modelPathDir);
    }
    NETaggerLevel1.Parameters paramLevel1 = new NETaggerLevel1.Parameters();
    paramLevel1.baseLTU = new SparseAveragedPerceptron(ParametersForLbjCode.currentParameters.learningRatePredictionsLevel1, 0, ParametersForLbjCode.currentParameters.thicknessPredictionsLevel1);
    logger.info("Level 1 classifier learning rate = " + ParametersForLbjCode.currentParameters.learningRatePredictionsLevel1 + ", thickness = " + ParametersForLbjCode.currentParameters.thicknessPredictionsLevel1);
    NETaggerLevel1 tagger1 = new NETaggerLevel1(paramLevel1, modelPath + ".level1", modelPath + ".level1.lex");
    tagger1.forget();
    for (int dataId = 0; dataId < trainDataSet.size(); dataId++) {
        Data trainData = trainDataSet.elementAt(dataId);
        if (ParametersForLbjCode.currentParameters.featuresToUse.containsKey("PredictionsLevel1")) {
            PredictionsAndEntitiesConfidenceScores.getAndMarkEntities(trainData, NEWord.LabelToLookAt.GoldLabel);
            TwoLayerPredictionAggregationFeatures.setLevel1AggregationFeatures(trainData, true);
        }
    }
    // preextract the L1 test and train data.
    String path = ParametersForLbjCode.currentParameters.pathToModelFile;
    String trainPathL1 = path + ".level1.prefetchedTrainData";
    File deleteme = new File(trainPathL1);
    if (deleteme.exists())
        deleteme.delete();
    String testPathL1 = path + ".level1.prefetchedTestData";
    deleteme = new File(testPathL1);
    if (deleteme.exists())
        deleteme.delete();
    logger.info("Pre-extracting the training data for Level 1 classifier, saving to " + trainPathL1);
    BatchTrainer bt1train = prefetchAndGetBatchTrainer(tagger1, trainDataSet, trainPathL1);
    logger.info("Pre-extracting the testing data for Level 1 classifier, saving to " + testPathL1);
    BatchTrainer bt1test = prefetchAndGetBatchTrainer(tagger1, testDataSet, testPathL1);
    Parser testParser1 = bt1test.getParser();
    for (int i = 0; (fixedNumIterations == -1 && i < 200 && i - bestRoundLevel1 < 10) || (fixedNumIterations > 0 && i <= fixedNumIterations); ++i) {
        bt1train.train(1);
        testParser1.reset();
        TestDiscrete simpleTest = new TestDiscrete();
        simpleTest.addNull("O");
        TestDiscrete.testDiscrete(simpleTest, tagger1, null, testParser1, true, 0);
        double f1Level1 = simpleTest.getOverallStats()[2];
        if (f1Level1 > bestF1Level1) {
            bestF1Level1 = f1Level1;
            bestRoundLevel1 = i;
            tagger1.save();
        }
        logger.info(i + " rounds.  Best so far for Level1 : (" + bestRoundLevel1 + ")=" + bestF1Level1);
    }
    logger.info("Level 1; best round : " + bestRoundLevel1 + "\tbest F1 : " + bestF1Level1);
    // trash the l2 prefetch data
    String trainPathL2 = path + ".level2.prefetchedTrainData";
    deleteme = new File(trainPathL2);
    if (deleteme.exists())
        deleteme.delete();
    String testPathL2 = path + ".level2.prefetchedTestData";
    deleteme = new File(testPathL1);
    if (deleteme.exists())
        deleteme.delete();
    NETaggerLevel2.Parameters paramLevel2 = new NETaggerLevel2.Parameters();
    paramLevel2.baseLTU = new SparseAveragedPerceptron(ParametersForLbjCode.currentParameters.learningRatePredictionsLevel2, 0, ParametersForLbjCode.currentParameters.thicknessPredictionsLevel2);
    NETaggerLevel2 tagger2 = new NETaggerLevel2(paramLevel2, ParametersForLbjCode.currentParameters.pathToModelFile + ".level2", ParametersForLbjCode.currentParameters.pathToModelFile + ".level2.lex");
    tagger2.forget();
    // Previously checked if PatternFeatures was in featuresToUse.
    if (ParametersForLbjCode.currentParameters.featuresToUse.containsKey("PredictionsLevel1")) {
        logger.info("Level 2 classifier learning rate = " + ParametersForLbjCode.currentParameters.learningRatePredictionsLevel2 + ", thickness = " + ParametersForLbjCode.currentParameters.thicknessPredictionsLevel2);
        double bestF1Level2 = -1;
        int bestRoundLevel2 = 0;
        logger.info("Pre-extracting the training data for Level 2 classifier, saving to " + trainPathL2);
        BatchTrainer bt2train = prefetchAndGetBatchTrainer(tagger2, trainDataSet, trainPathL2);
        logger.info("Pre-extracting the testing data for Level 2 classifier, saving to " + testPathL2);
        BatchTrainer bt2test = prefetchAndGetBatchTrainer(tagger2, testDataSet, testPathL2);
        Parser testParser2 = bt2test.getParser();
        for (int i = 0; (fixedNumIterations == -1 && i < 200 && i - bestRoundLevel2 < 10) || (fixedNumIterations > 0 && i <= fixedNumIterations); ++i) {
            logger.info("Learning level 2 classifier; round " + i);
            bt2train.train(1);
            logger.info("Testing level 2 classifier;  on prefetched data, round: " + i);
            testParser2.reset();
            TestDiscrete simpleTest = new TestDiscrete();
            simpleTest.addNull("O");
            TestDiscrete.testDiscrete(simpleTest, tagger2, null, testParser2, true, 0);
            double f1Level2 = simpleTest.getOverallStats()[2];
            if (f1Level2 > bestF1Level2) {
                bestF1Level2 = f1Level2;
                bestRoundLevel2 = i;
                tagger2.save();
            }
            logger.info(i + " rounds.  Best so far for Level2 : (" + bestRoundLevel2 + ") " + bestF1Level2);
        }
        // trash the l2 prefetch data
        deleteme = new File(trainPathL2);
        if (deleteme.exists())
            deleteme.delete();
        deleteme = new File(testPathL1);
        if (deleteme.exists())
            deleteme.delete();
        logger.info("Level1: bestround=" + bestRoundLevel1 + "\t F1=" + bestF1Level1 + "\t Level2: bestround=" + bestRoundLevel2 + "\t F1=" + bestF1Level2);
    }
    /*
         * This will override the models forcing to save the iteration we're interested in- the
         * fixedNumIterations iteration, the last one. But note - both layers will be saved for this
         * iteration. If the best performance for one of the layers came before the final iteration,
         * we're in a small trouble- the performance will decrease
         */
    if (fixedNumIterations > -1) {
        tagger1.save();
        tagger2.save();
    }
}

Example 2 with Parser

use of edu.illinois.cs.cogcomp.lbjava.parse.Parser in project cogcomp-nlp by CogComp.

the class BIOTester method TrainModel.

public static void TrainModel(String corpus) throws InvalidPortException, InvalidEndpointException, DatastoreException, IOException, JWNLException {
    if (corpus.equals("ACE")) {
        Parser train_parser_nam = new BIOReader(getPath("all", "ACE", 0), "ACE05-TRAIN", "NAM", false);
        Parser train_parser_nom = new BIOReader(getPath("all", "ACE", 0), "ACE05-TRAIN", "NOM", false);
        Parser train_parser_pro = new BIOReader(getPath("all", "ACE", 0), "ACE05-TRAIN", "PRO", false);
        train_nam_classifier(train_parser_nam, "models/ACE_NAM");
        train_nom_classifier(train_parser_nom, "models/ACE_NOM");
        train_pro_classifier(train_parser_pro, "models/ACE_PRO");
    } else if (corpus.equals("ERE")) {
        Parser train_parser_nam = new BIOReader(getPath("all", "ERE", 0), "ACE05-TRAIN", "NAM", false);
        Parser train_parser_nom = new BIOReader(getPath("all", "ERE", 0), "ACE05-TRAIN", "NOM", false);
        Parser train_parser_pro = new BIOReader(getPath("all", "ERE", 0), "ACE05-TRAIN", "PRO", false);
        train_nam_classifier(train_parser_nam, "models/ERE_NAM");
        train_nom_classifier(train_parser_nom, "models/ERE_NOM");
        train_pro_classifier(train_parser_pro, "models/ERE_PRO");
    }
}

Example 3 with Parser

use of edu.illinois.cs.cogcomp.lbjava.parse.Parser in project cogcomp-nlp by CogComp.

the class ExtentTester method testSimpleExtent.

public static void testSimpleExtent() throws InvalidPortException, InvalidEndpointException, IOException, JWNLException, DatastoreException {
    int true_labeled = 0;
    int true_predicted = 0;
    int true_correct = 0;
    int false_labeled = 0;
    int false_predicted = 0;
    int false_correct = 0;
    for (int i = 0; i < 5; i++) {
        ExtentReader train_parser = new ExtentReader("data/partition_with_dev/train/" + i);
        extent_classifier classifier = train_extent_classifier(train_parser);
        extentLabel output = new extentLabel();
        Parser test_parser = new ExtentReader("data/partition_with_dev/eval/" + i);
        for (Object example = test_parser.next(); example != null; example = test_parser.next()) {
            String pTag = classifier.discreteValue(example);
            String gTag = output.discreteValue(example);
            if (pTag.equals("true")) {
                true_predicted++;
            } else {
                false_predicted++;
            }
            if (gTag.equals("true")) {
                true_labeled++;
            } else {
                false_labeled++;
            }
            if (pTag.equals(gTag)) {
                if (pTag.equals("true")) {
                    true_correct++;
                } else {
                    false_correct++;
                }
            }
        }
    }
    System.out.println("Total Labeled True: " + true_labeled);
    System.out.println("Total Predicted True: " + true_predicted);
    System.out.println("Total Correct True: " + true_correct);
    double p = (double) true_correct / (double) true_predicted;
    double r = (double) true_correct / (double) true_labeled;
    double f = 2 * p * r / (p + r);
    System.out.println("True Precision: " + p);
    System.out.println("True Recall: " + r);
    System.out.println("True F1: " + f);
    System.out.println("Total Labeled False: " + false_labeled);
    System.out.println("Total Predicted False: " + false_predicted);
    System.out.println("Total Correct False: " + false_correct);
    p = (double) false_correct / (double) false_predicted;
    r = (double) false_correct / (double) false_labeled;
    f = 2 * p * r / (p + r);
    System.out.println("False Precision: " + p);
    System.out.println("False Recall: " + r);
    System.out.println("False F1: " + f);
}

Example 4 with Parser

use of edu.illinois.cs.cogcomp.lbjava.parse.Parser in project cogcomp-nlp by CogComp.

the class Main method train.

public void train() {
    if (!IOUtils.exists(modelsDir))
        IOUtils.mkdir(modelsDir);
    Learner classifier = new PrepSRLClassifier(modelName + ".lc", modelName + ".lex");
    Parser trainDataReader = new PrepSRLDataReader(dataDir, "train");
    BatchTrainer trainer = new BatchTrainer(classifier, trainDataReader, 1000);
    trainer.train(20);
    classifier.save();
    trainDataReader.close();
}

Example 5 with Parser

use of edu.illinois.cs.cogcomp.lbjava.parse.Parser in project cogcomp-nlp by CogComp.

the class Main method test.

public void test() {
    ConstrainedPrepSRLClassifier classifier = new ConstrainedPrepSRLClassifier();
    Parser testDataReader = new PrepSRLDataReader(dataDir, "test");
    TestDiscrete tester = new TestDiscrete();
    TestDiscrete.testDiscrete(tester, classifier, new PrepSRLClassifier.Label(), testDataReader, true, 100);
    testDataReader.close();
}