Package edu.stanford.nlp.ling

Examples of edu.stanford.nlp.ling.CoreLabel.word()

120
121
122
123
124
125
126
127
128
129
130
  protected List<ParserConstraint> constraints = null;

  private CoreLabel getCoreLabel(int labelIndex) {
    if (originalCoreLabels[labelIndex] != null) {
      CoreLabel terminalLabel = originalCoreLabels[labelIndex];
      if (terminalLabel.value() == null && terminalLabel.word() != null) {
        terminalLabel.setValue(terminalLabel.word());
      }
      return terminalLabel;
    }
View Full Code Here
121
122
123
124
125
126
127
128
129
130
131
  private CoreLabel getCoreLabel(int labelIndex) {
    if (originalCoreLabels[labelIndex] != null) {
      CoreLabel terminalLabel = originalCoreLabels[labelIndex];
      if (terminalLabel.value() == null && terminalLabel.word() != null) {
        terminalLabel.setValue(terminalLabel.word());
      }
      return terminalLabel;
    }

    String wordStr = wordIndex.get(words[labelIndex]);
View Full Code Here
315
316
317
318
319
320
321
322
323
324
325
      extentTokens.add(initCoreLabel("was"));
      final int ADDED_WORDS = 2;
      for (int i = m.startIndex; i < endIdx; i++) {
        // Add everything except separated dashes! The separated dashes mess with the parser too badly.
        CoreLabel label = tokens.get(i);
        if ( ! "-".equals(label.word())) {
          extentTokens.add(tokens.get(i));
        } else {
          approximateness++;
        }
      }
View Full Code Here
324
325
326
327
328
329
330
331
332
333
334
        String NERType = token.get(CoreAnnotations.NamedEntityTagAnnotation.class);
        String currentType = token.get(CoreAnnotations.AnswerAnnotation.class);

        if (
            currentType != null ||
            (exact != null && ! (ignoreCase ? exact.equalsIgnoreCase(token.word()) : exact.equals(token.word()))) ||
            ! (entry.overwritableTypes.contains(NERType) || myLabels.contains(NERType))  ||
            ! pattern.matcher(token.word()).matches()  // last, as this is likely the expensive operation
            ) {
          failed = true;
          break;
View Full Code Here
324
325
326
327
328
329
330
331
332
333
334
        String NERType = token.get(CoreAnnotations.NamedEntityTagAnnotation.class);
        String currentType = token.get(CoreAnnotations.AnswerAnnotation.class);

        if (
            currentType != null ||
            (exact != null && ! (ignoreCase ? exact.equalsIgnoreCase(token.word()) : exact.equals(token.word()))) ||
            ! (entry.overwritableTypes.contains(NERType) || myLabels.contains(NERType))  ||
            ! pattern.matcher(token.word()).matches()  // last, as this is likely the expensive operation
            ) {
          failed = true;
          break;
View Full Code Here
326
327
328
329
330
331
332
333
334
335
336
        if (
            currentType != null ||
            (exact != null && ! (ignoreCase ? exact.equalsIgnoreCase(token.word()) : exact.equals(token.word()))) ||
            ! (entry.overwritableTypes.contains(NERType) || myLabels.contains(NERType))  ||
            ! pattern.matcher(token.word()).matches()  // last, as this is likely the expensive operation
            ) {
          failed = true;
          break;
        }
      }
View Full Code Here
319
320
321
322
323
324
325
326
327
328
329
    if (tokens.isEmpty()) {
      return "";
    }

    CoreLabel lastToken = tokens.get(0);
    StringBuilder buffer = new StringBuilder(lastToken.word());

    for (int i = 1; i < tokens.size(); i++) {
      CoreLabel currentToken = tokens.get(i);
      int numSpaces = currentToken.beginPosition() - lastToken.endPosition();
      if (numSpaces < 0) {
View Full Code Here
328
329
330
331
332
333
334
335
336
337
338
      int numSpaces = currentToken.beginPosition() - lastToken.endPosition();
      if (numSpaces < 0) {
        numSpaces = 0;
      }

      buffer.append(repeat(' ', numSpaces)).append(currentToken.word());
      lastToken = currentToken;
    }

    return buffer.toString();
  }
View Full Code Here
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
      // HasWord but only the value field is populated. This can happen if legacy code uses
      // LabeledScoredTreeFactory but passes in a StringLabel to e.g. newLeaf().
      if (lab instanceof HasWord) {
        if(lab instanceof CoreLabel) {
          CoreLabel cl = (CoreLabel) lab;
          if(cl.word() == null)
            cl.setWord(cl.value());
          y.add((X) cl);
        } else {
          y.add((X) lab);
        }
View Full Code Here
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
  protected String recoverOriginalText(List<CoreLabel> tokens, CoreNLPProtos.Sentence sentence) {
    StringBuilder text = new StringBuilder();
    CoreLabel last = null;
    if (tokens.size() > 0) {
      CoreLabel token = tokens.get(0);
      if (token.originalText() != null) { text.append(token.originalText()); } else { text.append(token.word()); }
      last = tokens.get(0);
    }
    for (int i = 1; i < tokens.size(); ++i) {
      CoreLabel token = tokens.get(i);
      if (token.before() != null) {
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. All rights reserved.
All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.