edu.stanford.nlp.process.WordSegmenter Maven / Gradle / Ivy

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

Stanford Parser processes raw text in English, Chinese, German, Arabic, and French, and extracts constituency parse trees.

There is a newer version: 3.9.2

Show newest version

package edu.stanford.nlp.process;

import java.io.Serializable;
import java.util.List;
import java.util.Collection;

import edu.stanford.nlp.ling.HasWord;
import edu.stanford.nlp.ling.TaggedWord;
import edu.stanford.nlp.trees.Tree;

/** An interface for segmenting strings into words
 *  (in unwordsegmented languages).
 *
 *  @author Galen Andrew
 */
public interface WordSegmenter extends Serializable {

  void initializeTraining(double numTrees);

  void train(Collection trees);

  void train(Tree trees);

  void train(List sentence);

  void finishTraining();

  void loadSegmenter(String filename);

  List segment(String s);
}