Examples with TextAnnotation edu.illinois.cs.cogcomp.core.datastructures.textannotation.TextAnnotation used on opensource projects

Example 56 with TextAnnotation

use of edu.illinois.cs.cogcomp.core.datastructures.textannotation.TextAnnotation in project cogcomp-nlp by CogComp.

the class TestCorlex method test.

public final void test() throws EdisonException {
    log.debug("Corlex Feature Extractor");
    // Using the first TA and a constituent between span of 30-40 as a test
    TextAnnotation ta = tas.get(1);
    View TOKENS = ta.getView("TOKENS");
    log.debug("Got tokens FROM TextAnnotation");
    CorelexFeatureExtractor testInstance = new CorelexFeatureExtractor(true);
    Set<Feature> feats = testInstance.getWordFeatures(ta, 1);
    String[] expected_outputs = { "atr" };
    if (feats == null) {
        log.debug("Feats are returning NULL.");
    }
    log.debug("Printing Set of Features");
    for (Feature f : feats) {
        log.debug(f.getName());
        assertTrue(ArrayUtils.contains(expected_outputs, f.getName()));
    }
}

Example 57 with TextAnnotation

use of edu.illinois.cs.cogcomp.core.datastructures.textannotation.TextAnnotation in project cogcomp-nlp by CogComp.

the class TestLabelOneBefore method test.

public final void test() throws Exception {
    logger.info("LabelOneBefore Feature Extractor");
    // Using the first TA and a constituent between span of 30-40 as a test
    TextAnnotation ta = tas.get(2);
    View TOKENS = ta.getView("TOKENS");
    logger.info("GOT TOKENS FROM TEXTAnn");
    List<Constituent> testlist = TOKENS.getConstituentsCoveringSpan(0, 20);
    for (Constituent c : testlist) {
        logger.info(c.getSurfaceForm());
    }
    logger.info("Testlist size is " + testlist.size());
    // Constituent test = testlist.get(1);
    // logger.info("The constituent we are extracting features from
    // in this test is: " + test.getSurfaceForm());
    POSBaseLineCounter posBaseLine = new POSBaseLineCounter("posBaseLine");
    posBaseLine.buildTable(TestPosHelper.corpus);
    POSMikheevCounter posMikheev = new POSMikheevCounter("posMikheev");
    posMikheev.buildTable(TestPosHelper.corpus);
    LabelOneBefore l1bPOS = new LabelOneBefore("l1bPOS");
    LabelOneBefore l1bPOSBaseLine = new LabelOneBefore("l1bPOSBaseLine", posBaseLine);
    LabelOneBefore l1bPOSMikheev = new LabelOneBefore("l1bPOSMikheev", posMikheev);
    // Test when using POS View
    ArrayList<Set<Feature>> featslist = new ArrayList<>();
    for (Constituent test : testlist) featslist.add(l1bPOS.getFeatures(test));
    if (featslist.isEmpty()) {
        logger.info("Feats list is returning NULL.");
    }
    logger.info("\n" + "Test when using POS View");
    logger.info("Printing list of Feature set");
    for (Set<Feature> feats : featslist) {
        for (Feature f : feats) logger.info(f.getName());
    }
    // Test when using POS baseline Counting
    featslist.clear();
    for (Constituent test : testlist) featslist.add(l1bPOSBaseLine.getFeatures(test));
    if (featslist.isEmpty()) {
        logger.info("Feats list is returning NULL.");
    }
    logger.info("\n" + "Test when using POS baseline Counting");
    logger.info("Printing list of Feature set");
    for (Set<Feature> feats : featslist) {
        for (Feature f : feats) logger.info(f.getName());
    }
    // Test when using POS Mikheev Counting
    featslist.clear();
    for (Constituent test : testlist) featslist.add(l1bPOSMikheev.getFeatures(test));
    if (featslist.isEmpty()) {
        logger.info("Feats list is returning NULL.");
    }
    logger.info("\n" + "Test when using POS Mikheev Counting");
    logger.info("Printing list of Feature set");
    for (Set<Feature> feats : featslist) {
        for (Feature f : feats) logger.info(f.getName());
    }
    logger.info("GOT FEATURES YES!");
}

Example 58 with TextAnnotation

use of edu.illinois.cs.cogcomp.core.datastructures.textannotation.TextAnnotation in project cogcomp-nlp by CogComp.

the class TestPOSBaseLineFeatureExtractor method test.

@Test
public final void test() throws Exception {
    logger.info("POSBaseLine Feature Extractor");
    // Using the first TA and a constituent between span of 30-40 as a test
    TextAnnotation ta = tas.get(2);
    View TOKENS = ta.getView("TOKENS");
    logger.info("GOT TOKENS FROM TEXTAnn");
    List<Constituent> testlist = TOKENS.getConstituentsCoveringSpan(0, 20);
    for (Constituent c : testlist) {
        logger.info(c.getSurfaceForm());
    }
    logger.info("Testlist size is " + testlist.size());
    // Constituent test = testlist.get(1);
    // logger.info("The constituent we are extracting features from
    // in this test is: " + test.getSurfaceForm());
    // logger.info(TestPOSBaseLineFeatureExtractor.class.getProtectionDomain().getCodeSource().getLocation());
    // logger.info(System.getProperty("user.dir"));
    POSBaseLineFeatureExtractor posBaseLine = new POSBaseLineFeatureExtractor("posBaseLine", "test_corpus", TestPosHelper.corpus);
    ArrayList<Set<Feature>> featslist = new ArrayList<>();
    for (Constituent test : testlist) featslist.add(posBaseLine.getFeatures(test));
    if (featslist.isEmpty()) {
        logger.info("Feats list is returning NULL.");
    }
    logger.info("Printing list of Feature set");
    for (Set<Feature> feats : featslist) {
        for (Feature f : feats) logger.info(f.getName());
    }
    /*
         * Set<Feature> feats = posBaseLine.getFeatures(test);
         * 
         * if (feats == null) { logger.info("Feats are returning NULL."); }
         * 
         * logger.info("Printing Set of Features");
         * 
         * for (Feature f : feats) { logger.info(f.getName()); }
         */
    logger.info("GOT FEATURES YES!");
}

Example 59 with TextAnnotation

use of edu.illinois.cs.cogcomp.core.datastructures.textannotation.TextAnnotation in project cogcomp-nlp by CogComp.

the class TestPOSMikheevFeatureExtractor method test.

@Test
public final void test() throws Exception {
    POSMikheevFeatureExtractor posMikheev = new POSMikheevFeatureExtractor("posMikheev", "test_corpus", TestPosHelper.corpus);
    logger.info("POSMikheev Feature Extractor");
    logger.info("Only print the features with known tags");
    // Using the first TA and a constituent between span of 30-40 as a test
    int i = 0;
    for (TextAnnotation ta : tas) {
        ArrayList<String> outFeatures = new ArrayList<>();
        View TOKENS = ta.getView("TOKENS");
        for (Constituent TOKEN : TOKENS) {
            Set<Feature> feats = posMikheev.getFeatures(TOKEN);
            if (feats.isEmpty()) {
                logger.info("Feats list is returning NULL.");
            }
            for (Feature f : feats) if (!f.getName().contains("UNKNOWN")) {
                outFeatures.add(f.getName());
            }
        }
        if (!outFeatures.isEmpty()) {
            logger.info("-------------------------------------------------------");
            logger.info("Text Annotation: " + i);
            logger.info("Text Features: ");
            for (String out : outFeatures) logger.info(out);
            logger.info("-------------------------------------------------------");
        }
        i++;
    }
    logger.info("GOT FEATURES YES!");
}

Example 60 with TextAnnotation

use of edu.illinois.cs.cogcomp.core.datastructures.textannotation.TextAnnotation in project cogcomp-nlp by CogComp.

the class TestPOSWindowTwo method test.

@Test
public final void test() throws EdisonException {
    log.debug("POSWindowTwo Feature Extractor");
    // Using the first TA and a constituent between span of 30-40 as a test
    TextAnnotation ta = tas.get(2);
    View TOKENS = ta.getView("TOKENS");
    List<Constituent> testlist = TOKENS.getConstituentsCoveringSpan(0, 20);
    for (Constituent c : testlist) {
        log.debug(c.getSurfaceForm());
    }
    Constituent test = testlist.get(1);
    log.debug("The constituent we are extracting features from in this test is: " + test.getSurfaceForm());
    POSWindowTwo POSW = new POSWindowTwo("POSWindowTwo");
    log.debug("Startspan is " + test.getStartSpan() + " and Endspan is " + test.getEndSpan());
    Set<Feature> feats = POSW.getFeatures(test);
    String[] expected_outputs = { "POSWindowTwo:0(DT)", "POSWindowTwo:1(VBZ)", "POSWindowTwo:2(DT)", "POSWindowTwo:3(NN)" };
    if (feats == null) {
        log.debug("Feats are returning NULL.");
    }
    log.debug("Printing Set of Features");
    for (Feature f : feats) {
        assert (ArrayUtils.contains(expected_outputs, f.getName()));
    }
// System.exit(0);
}