Examples of ExtractTrainingData

uk.ac.cam.ch.wwmm.oscar3.models.ExtractTrainingData
Extracts and holds useful data from hand-annotated text. @author ptc24

Examples of uk.ac.cam.ch.wwmm.oscar3.models.ExtractTrainingData

    String normWord = StringTools.normaliseName(word);
    if (!word.equals(normWord)) {
      contextable.add(makeWordFeature(normWord));
    }


    ExtractTrainingData etd = ExtractTrainingData.getInstance();
    makeWordFeatures(word, normWord, bigramable, etd);
    makeReactionFeatures(word, bigramable, contextable, etd);


    String wts = StringTools.removeTerminalS(normWord);
    contextable.add(WITHOUT_TERMINAL_S_FEATURE + wts);

View Full Code Here

Examples of uk.ac.cam.ch.wwmm.oscar3.models.ExtractTrainingData

  // I'm sure there's a nice analytic way of doing this. Ah well...
  public static void main(String[] args) {
    List<Double> positiveExamples = new ArrayList<Double>();
    List<Double> negativeExamples = new ArrayList<Double>();
    
    ExtractTrainingData etd1 = ExtractTrainingData.getInstance();
    List<File> sbFiles = new ArrayList<File>();
    sbFiles.addAll(FileTools.getFilesFromDirectoryByName(new File("/home/ptc24/newows/goodrsc"), "scrapbook.xml"));
    ExtractTrainingData etd2 = new ExtractTrainingData(sbFiles);
    Set<String> chem = new HashSet<String>(etd2.chemicalWords);
    //chem.removeAll(etd1.chemicalWords);
    for(String w : chem) {
      if(!NGramBuilder.getInstance().chemSet.contains(NGram.parseWord(w))) {
        double score = NGram.getInstance().testWord(w);

View Full Code Here

Examples of uk.ac.cam.ch.wwmm.oscar3.models.ExtractTrainingData


  /**
   * @param args
   */
  public static void main(String[] args) throws Exception {
    ExtractTrainingData etd1 = ExtractTrainingData.getInstance();
    List<File> sbFiles = new ArrayList<File>();
    sbFiles.addAll(FileTools.getFilesFromDirectoryByName(new File("/home/ptc24/newows/goodrsc"), "scrapbook.xml"));
    ExtractTrainingData etd2 = new ExtractTrainingData(sbFiles);
    Set<String> chem = new HashSet<String>(etd2.chemicalWords);
    //chem.removeAll(etd1.chemicalWords);
    for(String w : chem) {
      if(!NGramBuilder.getInstance().chemSet.contains(NGram.parseWord(w))) {
        double score = NGram.getInstance().testWord(w);

View Full Code Here

Examples of uk.ac.cam.ch.wwmm.oscar3.models.ExtractTrainingData

    }
    readCollection(goodUDW, false);
  }
  
  private void readExtractedTrainingData() {
    ExtractTrainingData etd = ExtractTrainingData.getInstance();
    readCollection(etd.chemicalWords, true);
    readCollection(etd.nonChemicalWords, false);  
  }

View Full Code Here

TOP

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.