edu.stanford.nlp.international.arabic.process.StartAndEndArabicSegmenterFeatureFactory Maven / Gradle / Ivy

Show more of this group Show more artifacts with this name
Show all versions of stanford-corenlp Show documentation

Stanford CoreNLP provides a set of natural language analysis tools which can take raw English language text input and give the base forms of words, their parts of speech, whether they are names of companies, people, etc., normalize dates, times, and numeric quantities, mark up the structure of sentences in terms of phrases and word dependencies, and indicate which noun phrases refer to the same entities. It provides the foundational building blocks for higher level text understanding applications.

There is a newer version: 4.5.7

Show newest version

package edu.stanford.nlp.international.arabic.process;

import java.util.Collection;

import edu.stanford.nlp.ling.CoreLabel;
import edu.stanford.nlp.sequences.SeqClassifierFlags;
import edu.stanford.nlp.util.PaddedList;

/**
 * Feature factory for the IOB clitic segmentation model described by
 * Green and DeNero (2012).
 * 
 * @author Spence Green
 *
 * @param 
 */
public class StartAndEndArabicSegmenterFeatureFactory extends ArabicSegmenterFeatureFactory {
  
  private static final long serialVersionUID = 6864940988019110930L;

  public void init(SeqClassifierFlags flags) {
    super.init(flags);
  }

  @Override
  protected Collection featuresCpC(PaddedList cInfo, int loc) {
    Collection features = super.featuresCpC(cInfo, loc);

    CoreLabel c = cInfo.get(loc);

    // "Wrapper" feature: identity of first and last two chars of the current word.
    // This helps detect ma+_+sh in dialect, as well as avoiding segmenting possessive
    // pronouns if the word starts with al-.
    if (c.word().length() > 3) {
      String start = c.word().substring(0, 2);
      String end = c.word().substring(c.word().length() - 2);
      if (c.index() == 2) {
        features.add(start + "_" + end + "-begin-wrap");
      }
      if (c.index() == c.word().length() - 1) {
        features.add(start + "_" + end + "-end-wrap");
      }
    }
    
    return features;
  }
}