Package org.cleartk.classifier.feature.extractor.simple

Examples of org.cleartk.classifier.feature.extractor.simple.CharacterCategoryPatternExtractor


    // define chunking
    this.timeChunking = new BIOChunking<BaseToken, TimeMention>(BaseToken.class, TimeMention.class);

    CombinedExtractor allExtractors = new CombinedExtractor(
        new CoveredTextExtractor(),
        new CharacterCategoryPatternExtractor(PatternType.REPEATS_MERGED),
        new CharacterCategoryPatternExtractor(PatternType.ONE_PER_CHAR),
        new TypePathExtractor(BaseToken.class, "partOfSpeech"),
        new TimeWordTypeExtractor());

    //    CombinedExtractor parseExtractors = new CombinedExtractor(
    //        new ParseSpanFeatureExtractor()
View Full Code Here


    // define chunking
    this.timeChunking = new BIOChunking<BaseToken, TimeMention>(BaseToken.class, TimeMention.class);

    CombinedExtractor allExtractors = new CombinedExtractor(
        new CoveredTextExtractor(),
        new CharacterCategoryPatternExtractor(PatternType.REPEATS_MERGED),
        new CharacterCategoryPatternExtractor(PatternType.ONE_PER_CHAR),
        new TypePathExtractor(BaseToken.class, "partOfSpeech"),
        new TimeWordTypeExtractor());

//    CombinedExtractor parseExtractors = new CombinedExtractor(
//        new ParseSpanFeatureExtractor()
View Full Code Here

        BaseToken.class,
        EventMention.class);

    this.tokenFeatureExtractor = new CombinedExtractor(
        new CoveredTextExtractor(),
        new CharacterCategoryPatternExtractor(PatternType.ONE_PER_CHAR),
        new TypePathExtractor(BaseToken.class, "partOfSpeech"));
    this.contextFeatureExtractor = new CleartkExtractor(
        BaseToken.class,
        this.tokenFeatureExtractor,
        new Preceding(3),
View Full Code Here

  @Override
  public void initialize(UimaContext context)
      throws ResourceInitializationException {
    super.initialize(context);

    CombinedExtractor charExtractors = new CombinedExtractor(new CharacterCategoryPatternExtractor(PatternType.REPEATS_MERGED),
            new CharacterCategoryPatternExtractor(PatternType.ONE_PER_CHAR));
   
    this.wordTypes = Maps.newHashMap();
    URL url = TimeWordsExtractor.class.getResource(LOOKUP_PATH);
    try {
      for (String line : Resources.readLines(url, Charsets.US_ASCII)) {
View Full Code Here

TOP

Related Classes of org.cleartk.classifier.feature.extractor.simple.CharacterCategoryPatternExtractor

Copyright © 2018 www.massapicom. 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.