Example usage for edu.stanford.nlp.ling WordTag WordTag

Introduction

In this page you can find the example usage for edu.stanford.nlp.ling WordTag WordTag.

Prototype

public WordTag(Label word, Label tag) 

Source Link

Document

Create a new WordTag from a Label.

Usage

From source file:context.core.task.stemming.LemmaTagger.java

License:Open Source License

/**
 *
 * @param sent//from  w w  w.  j  a v a 2  s .  c  o  m
 * @param language
 * @return
 */
public static List<TaggedWord> lemmatize(List<CoreLabel> sent, String language) {
    MaxentTagger tagger = getTagger(language);
    //        List<HasWord> sent = Sentence.toWordList("This is a sample text");
    List<TaggedWord> taggedSent = tagger.tagSentence(sent);
    for (TaggedWord token : taggedSent) {
        String word = token.word();
        String pos = token.tag();
        String lemma = morphology.lemmatize(new WordTag(word, pos)).lemma();
        token.setTag(lemma);
    }
    //        final List<WordLemmaTag> tagged = (List<WordLemmaTag>) tagger.tagCoreLabelsOrHasWords(sent, morphology, true);
    //        for (TaggedWord tw : taggedSent) {
    //            System.out.println(tw.word() + "\t" + tw.tag());
    //        }
    return taggedSent;
}

---

From source file:de.tudarmstadt.lt.sentiment.StanfordLemmatizer.java

License:Open Source License

@Override
public void process(JCas aJCas) throws AnalysisEngineProcessException {
    for (Token t : select(aJCas, Token.class)) {
        //This corresponds roughly to what is happening in MorphaAnnotator.
        String token = t.getCoveredText();
        String lemma;//from   w ww .ja  va2 s  .  c  o m
        if (t.getPos() != null) {
            lemma = morphology.lemmatize(new WordTag(token, t.getPos().getPosValue())).lemma();
        } else {
            lemma = morphology.stem(token);
        }
        if (lemma == null) {
            lemma = token;
        }
        Lemma l = new Lemma(aJCas, t.getBegin(), t.getEnd());
        l.setValue(lemma);
        l.addToIndexes();
        t.setLemma(l);
    }
}

---

From source file:de.tudarmstadt.ukp.dkpro.core.stanfordnlp.StanfordLemmatizer.java

License:Open Source License

@Override
public void process(JCas aJCas) throws AnalysisEngineProcessException {
    if (!"en".equals(aJCas.getDocumentLanguage())) {
        throw new AnalysisEngineProcessException(Messages.BUNDLE, Messages.ERR_UNSUPPORTED_LANGUAGE,
                new String[] { aJCas.getDocumentLanguage() });
    }//from   w  w w .  j a  v  a2  s  .c om

    for (Token t : select(aJCas, Token.class)) {
        // Only verbs are lemmatized, the other words are simply stemmed. This corresponds
        // roughly to what is happening in MorphaAnnotator.
        String token = t.getCoveredText();
        String lemma;
        if (t.getPos() instanceof V) {
            lemma = morphology.lemmatize(new WordTag(token, t.getPos().getPosValue())).lemma();
        } else {
            lemma = morphology.stem(token);
        }
        if (lemma == null) {
            lemma = token;
        }
        Lemma l = new Lemma(aJCas, t.getBegin(), t.getEnd());
        l.setValue(lemma);
        l.addToIndexes();
        t.setLemma(l);
    }
}

---