Example usage for edu.stanford.nlp.process WordToSentenceProcessor WordToSentenceProcessor

Introduction

In this page you can find the example usage for edu.stanford.nlp.process WordToSentenceProcessor WordToSentenceProcessor.

Prototype

public WordToSentenceProcessor() 

Source Link

Document

Create a WordToSentenceProcessor using a sensible default list of tokens for sentence ending for English/Latin writing systems.

Usage

From source file:edu.iastate.airl.semtus.parser.Parser.java

License:Open Source License

/**
 * Get sentences from words/*from w ww.  j a  v  a2  s .  c o m*/
 *
 * @param theseWords
 *            words
 * @return list of sentences
 */
static public List<Sentence<Word>> getSentences(List<Word> theseWords) {
    WordToSentenceProcessor<Word, String, Word> thisSentenceProcessor = new WordToSentenceProcessor<Word, String, Word>();
    List<List<Word>> theseProtoSentences = thisSentenceProcessor.process(theseWords);
    List<Sentence<Word>> theseSentences = new ArrayList<Sentence<Word>>();
    for (List<Word> thisProtoSentence : theseProtoSentences)
        theseSentences.add(new Sentence<Word>(thisProtoSentence));
    return theseSentences;
}

---

From source file:wikiminer.Article.java

public void createPhrases() {
    //// Tokenize
    List<CoreLabel> tokens = new ArrayList<>();
    PTBTokenizer<CoreLabel> tokenizer = new PTBTokenizer<>(new StringReader(text), new CoreLabelTokenFactory(),
            "");/*from   w ww  .j  av a  2  s. com*/
    while (tokenizer.hasNext()) {
        tokens.add(tokenizer.next());
    }
    //// Split sentences from tokens
    List<List<CoreLabel>> sentences = new WordToSentenceProcessor<CoreLabel>().process(tokens);
    //// Join back together
    int end;
    int start = 0;
    for (List<CoreLabel> sentence : sentences) {
        end = sentence.get(sentence.size() - 1).endPosition();
        phrases.add(new Phrase(text.substring(start, end).trim()));
        start = end;
    }

    /*Reader reader = new StringReader(text);
    DocumentPreprocessor dp = new DocumentPreprocessor(reader);
            
    for (List<HasWord> sentence : dp) {
    String out = Sentence.listToString(sentence);
    //replace -LRB- and -RRB- with opening and closing brackets
    out = out.replace("-LRB-", "(");
    out = out.replace("-RRB-", ")");
    Phrase line = new Phrase(out);
    phrases.add(line);
    System.out.println(line.getText());
    }*/
}

---