Examples with TextClassificationOutcome org.dkpro.tc.api.type.TextClassificationOutcome used on opensource projects

Example 1 with TextClassificationOutcome

use of org.dkpro.tc.api.type.TextClassificationOutcome in project dkpro-tc by dkpro.

the class LinewiseTextReader method getNext.

public void getNext(JCas aJCas) throws IOException, CollectionException {
    DocumentMetaData md = new DocumentMetaData(aJCas);
    md.setDocumentTitle("");
    md.setDocumentId("" + (instanceId++));
    md.setLanguage(language);
    md.addToIndexes();
    String[] split = nextLine.split("\t");
    String documentText = split[1];
    String label = split[0];
    documentText = checkUnescapeHtml(documentText);
    documentText = checkUnescapeJava(documentText);
    aJCas.setDocumentText(documentText);
    TextClassificationOutcome outcome = new TextClassificationOutcome(aJCas);
    outcome.setOutcome(label);
    outcome.addToIndexes();
    checkSetSentence(aJCas);
}

Example 2 with TextClassificationOutcome

use of org.dkpro.tc.api.type.TextClassificationOutcome in project dkpro-tc by dkpro.

the class CRFSuiteSaveAndLoadModelTest method loadModelArowParameters.

@Test
public void loadModelArowParameters() throws Exception {
    Map<String, Object> config = new HashMap<>();
    config.put(DIM_CLASSIFICATION_ARGS, new Object[] { new CrfSuiteAdapter(), CrfSuiteAdapter.ALGORITHM_ADAPTIVE_REGULARIZATION_OF_WEIGHT_VECTOR, "-p", "max_iterations=2" });
    config.put(DIM_DATA_WRITER, new CrfSuiteAdapter().getDataWriterClass().getName());
    config.put(DIM_FEATURE_USE_SPARSE, new WekaAdapter().useSparseFeatures());
    Dimension<Map<String, Object>> mlas = Dimension.createBundle("config", config);
    // create a model
    File modelFolder = folder.newFolder();
    ParameterSpace pSpace = getParameterSpace(mlas);
    executeSaveModelIntoTemporyFolder(pSpace, modelFolder);
    JCas jcas = JCasFactory.createJCas();
    jcas.setDocumentText("This is an example text. It has 2 sentences.");
    jcas.setDocumentLanguage("en");
    AnalysisEngine tokenizer = AnalysisEngineFactory.createEngine(BreakIteratorSegmenter.class);
    AnalysisEngine tcAnno = AnalysisEngineFactory.createEngine(TcAnnotator.class, TcAnnotator.PARAM_TC_MODEL_LOCATION, modelFolder.getAbsolutePath(), TcAnnotator.PARAM_NAME_SEQUENCE_ANNOTATION, Sentence.class.getName(), TcAnnotator.PARAM_NAME_UNIT_ANNOTATION, Token.class.getName());
    tokenizer.process(jcas);
    tcAnno.process(jcas);
    List<TextClassificationOutcome> outcomes = new ArrayList<>(JCasUtil.select(jcas, TextClassificationOutcome.class));
    // 9 token + 2 punctuation marks
    assertEquals(11, outcomes.size());
    for (TextClassificationOutcome o : outcomes) {
        assertTrue(postags.contains(o.getOutcome()));
    }
}

Example 3 with TextClassificationOutcome

use of org.dkpro.tc.api.type.TextClassificationOutcome in project dkpro-tc by dkpro.

the class BrownCorpusReader method getNext.

@Override
public void getNext(CAS cas) throws IOException, CollectionException {
    super.getNext(cas);
    JCas jcas;
    try {
        jcas = cas.getJCas();
    } catch (CASException e) {
        throw new CollectionException(e);
    }
    for (Sentence sentence : JCasUtil.select(jcas, Sentence.class)) {
        TextClassificationSequence sequence = new TextClassificationSequence(jcas, sentence.getBegin(), sentence.getEnd());
        sequence.addToIndexes();
        for (Token token : JCasUtil.selectCovered(jcas, Token.class, sentence)) {
            TextClassificationTarget unit = new TextClassificationTarget(jcas, token.getBegin(), token.getEnd());
            // will add the token content as a suffix to the ID of this unit
            unit.setSuffix(token.getCoveredText());
            unit.addToIndexes();
            TextClassificationOutcome outcome = new TextClassificationOutcome(jcas, token.getBegin(), token.getEnd());
            outcome.setOutcome(getTextClassificationOutcome(jcas, unit));
            outcome.addToIndexes();
        }
    }
}

Example 4 with TextClassificationOutcome

use of org.dkpro.tc.api.type.TextClassificationOutcome in project dkpro-tc by dkpro.

the class ReutersCorpusReader method getNext.

@Override
public void getNext(CAS aCAS) throws IOException, CollectionException {
    super.getNext(aCAS);
    JCas jcas;
    try {
        jcas = aCAS.getJCas();
    } catch (CASException e) {
        throw new CollectionException();
    }
    for (String outcomeValue : getTextClassificationOutcomes(jcas)) {
        TextClassificationOutcome outcome = new TextClassificationOutcome(jcas);
        outcome.setOutcome(outcomeValue);
        outcome.addToIndexes();
    }
}

Example 5 with TextClassificationOutcome

use of org.dkpro.tc.api.type.TextClassificationOutcome in project dkpro-tc by dkpro.

the class MultiLabelOutcomeAnnotator method process.

@Override
public void process(JCas jcas) throws AnalysisEngineProcessException {
    try {
        for (String outcomeValue : getTextClassificationOutcomes(jcas)) {
            TextClassificationOutcome outcome = new TextClassificationOutcome(jcas);
            outcome.setOutcome(outcomeValue);
            outcome.addToIndexes();
        }
    } catch (CollectionException e) {
        throw new AnalysisEngineProcessException(e);
    }
}