All Downloads are FREE. Search and download functionalities are using the official Maven repository.

edu.stanford.nlp.trees.TreeLemmatizer Maven / Gradle / Ivy

Go to download

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.trees;

import java.util.List;

import edu.stanford.nlp.ling.HasLemma;
import edu.stanford.nlp.ling.HasTag;
import edu.stanford.nlp.ling.Label;
import edu.stanford.nlp.ling.TaggedWord;
import edu.stanford.nlp.process.Morphology;

public class TreeLemmatizer implements TreeTransformer {

  @Override
  public Tree transformTree(Tree t) {
    Morphology morphology = new Morphology();

    List tagged = null;
    int index = 0;

    for (Tree leaf : t.getLeaves()) {
      Label label = leaf.label();
      if (label == null) {
        continue;
      }

      String tag;
      if (!(label instanceof HasTag) || ((HasTag) label).tag() == null) {
        if (tagged == null) {
          tagged = t.taggedYield();
        }
        tag = tagged.get(index).tag();
      } else {
        tag = ((HasTag) label).tag();
      }

      if (!(label instanceof HasLemma)) {
        throw new IllegalArgumentException("Got a tree with labels which do not support lemma");
      }
      ((HasLemma) label).setLemma(morphology.lemma(label.value(), tag, true));
      ++index;
    }
    return t;
  }

}




© 2015 - 2024 Weber Informatics LLC | Privacy Policy