Example usage for edu.stanford.nlp.ling TaggedWord setTag

Introduction

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

Prototype

public void setTag(String tag) 

Source Link

Usage

From source file:at.illecker.storm.commons.preprocessor.Preprocessor.java

License:Apache License

private TaggedWord pretagToken(String token, boolean tokenIsHashTag, boolean tokenIsUser, boolean tokenIsURL) {
    TaggedWord preTaggedToken = new TaggedWord(token);
    if (tokenIsHashTag) {
        preTaggedToken.setTag("HT");
    } else if (tokenIsUser) {
        preTaggedToken.setTag("USR");
    } else if (tokenIsURL) {
        preTaggedToken.setTag("URL");
    } else if (StringUtils.isRetweet(token)) {
        preTaggedToken.setTag("RT");
    } else if (m_nameEntities.isNameEntity(token)) {
        if (LOGGING) {
            LOG.info("NameEntity labelled for " + token);
        }/*w ww  . ja  v a  2s. c o  m*/
        preTaggedToken.setTag("NNP");
    } else if ((m_interjections.isInterjection(token)) || (StringUtils.isEmoticon(token))) {
        if (LOGGING) {
            LOG.info("Interjection or Emoticon labelled for " + token);
        }
        preTaggedToken.setTag("UH");
    }
    return preTaggedToken;
}

---

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

License:Open Source License

/**
 *
 * @param sent/*from   w  w w .j av 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:it.cnr.jatecs.nlp.patterns.Parser.java

License:Open Source License

/**
 * L'idea  che un inciso sia una frase che inizia con un pronome e sta tra due ,
 *///from w ww . ja va  2  s  .  c  o  m
private Vector<ArrayList<TaggedWord>> findAppositives(ArrayList<TaggedWord> sentence) {
    boolean foundFirst = false;
    ArrayList<TaggedWord> mainSentence = new ArrayList<TaggedWord>();
    ArrayList<TaggedWord> temp = new ArrayList<TaggedWord>();
    Vector<ArrayList<TaggedWord>> sentences = new Vector<ArrayList<TaggedWord>>();
    for (Iterator<TaggedWord> iterator = sentence.iterator(); iterator.hasNext();) {
        TaggedWord taggedWord = (TaggedWord) iterator.next();
        //Trattamento speciale delle foreign word
        if (taggedWord.tag().startsWith("FW"))
            taggedWord.setTag("NN");
        if (foundFirst) {
            if (taggedWord.tag().equals(",")) {
                foundFirst = false;
                sentences.add(temp);
                temp = new ArrayList<TaggedWord>();
            } else
                temp.add(taggedWord);
        } else if (taggedWord.tag().equals(",") && iterator.hasNext()) {
            taggedWord = (TaggedWord) iterator.next();
            if (taggedWord.tag().startsWith("W") || taggedWord.tag().startsWith("PRP")) {
                foundFirst = true;
                temp.add(taggedWord);
            } else {
                mainSentence.add(new TaggedWord(",", ","));
                mainSentence.add(taggedWord);
            }
        } else
            mainSentence.add(taggedWord);
    }
    if (foundFirst) {
        mainSentence.add(new TaggedWord(",", ","));
        mainSentence.addAll(temp);
    }
    sentences.add(mainSentence);
    return sentences;
}

---