edu.stanford.nlp.pipeline.CorefAnnotator 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.pipeline;

import java.util.ArrayList;
import java.util.Arrays;
import java.util.Collections;
import java.util.HashSet;
import java.util.List;
import java.util.Map;
import java.util.Properties;
import java.util.Set;

import edu.stanford.nlp.coref.CorefCoreAnnotations;
import edu.stanford.nlp.coref.CorefProperties;
import edu.stanford.nlp.coref.CorefSystem;
import edu.stanford.nlp.coref.data.CorefChain;
import edu.stanford.nlp.coref.data.CorefChain.CorefMention;
import edu.stanford.nlp.ling.CoreAnnotation;
import edu.stanford.nlp.ling.CoreAnnotations;
import edu.stanford.nlp.ling.CoreLabel;
import edu.stanford.nlp.semgraph.SemanticGraphCoreAnnotations;
import edu.stanford.nlp.trees.TreeCoreAnnotations;
import edu.stanford.nlp.util.CoreMap;
import edu.stanford.nlp.util.IntTuple;
import edu.stanford.nlp.util.Pair;
import edu.stanford.nlp.util.logging.Redwood;

/**
 * This class adds coref information to an Annotation.
 *
 * A Map from id to CorefChain is put under the annotation
 * {@link edu.stanford.nlp.coref.CorefCoreAnnotations.CorefChainAnnotation}.
 *
 * @author heeyoung
 * @author Jason Bolton
 */
public class CorefAnnotator extends TextAnnotationCreator implements Annotator  {

  /** A logger for this class */
  private static final Redwood.RedwoodChannels log = Redwood.channels(CorefAnnotator.class);

  private final CorefSystem corefSystem;

  private final Properties props;

  public CorefAnnotator(Properties props) {
    this.props = props;
    try {
      // suppress
      props.setProperty("coref.printConLLLoadingMessage","false");
      corefSystem = new CorefSystem(props);
      props.remove("coref.printConLLLoadingMessage");
    } catch (Exception e) {
      log.error("cannot create CorefAnnotator!");
      log.error(e);
      throw new RuntimeException(e);
    }
  }

  @Override
  public void annotate(Annotation annotation){
    try {
      if (!annotation.containsKey(CoreAnnotations.SentencesAnnotation.class)) {
        log.error("this coreference resolution system requires SentencesAnnotation!");
        return;
      }

      if (hasSpeakerAnnotations(annotation)) {
        annotation.set(CoreAnnotations.UseMarkedDiscourseAnnotation.class, true);
      }

      corefSystem.annotate(annotation);
    } catch (RuntimeException e) {
      throw e;
    } catch (Exception e) {
      throw new RuntimeException(e);
    }
  }

  public static List> getLinks(Map result) {
    List> links = new ArrayList<>();
    CorefChain.CorefMentionComparator comparator = new CorefChain.CorefMentionComparator();

    for (CorefChain c : result.values()) {
      List s = c.getMentionsInTextualOrder();
      for (CorefMention m1 : s) {
        for (CorefMention m2 : s) {
          if (comparator.compare(m1, m2)==1) {
            links.add(new Pair<>(m1.position, m2.position));
          }
        }
      }
    }
    return links;
  }

  private static boolean hasSpeakerAnnotations(Annotation annotation) {
    for (CoreMap sentence : annotation.get(CoreAnnotations.SentencesAnnotation.class)) {
      for (CoreLabel t : sentence.get(CoreAnnotations.TokensAnnotation.class)) {
        if (t.get(CoreAnnotations.SpeakerAnnotation.class) != null) {
          return true;
        }
      }
    }
    return false;
  }

  @SuppressWarnings("unchecked")
  @Override
  public Set> requires() {
    Set> requirements = new HashSet<>(Arrays.asList(
        CoreAnnotations.TextAnnotation.class,
        CoreAnnotations.TokensAnnotation.class,
        CoreAnnotations.CharacterOffsetBeginAnnotation.class,
        CoreAnnotations.CharacterOffsetEndAnnotation.class,
        CoreAnnotations.IndexAnnotation.class,
        CoreAnnotations.ValueAnnotation.class,
        CoreAnnotations.SentencesAnnotation.class,
        CoreAnnotations.SentenceIndexAnnotation.class,
        CoreAnnotations.PartOfSpeechAnnotation.class,
        CoreAnnotations.LemmaAnnotation.class,
        CoreAnnotations.NamedEntityTagAnnotation.class,
        CorefCoreAnnotations.CorefMentionsAnnotation.class,
        SemanticGraphCoreAnnotations.BasicDependenciesAnnotation.class,
        SemanticGraphCoreAnnotations.EnhancedDependenciesAnnotation.class
        ));
    if (CorefProperties.mdType(this.props) != CorefProperties.MentionDetectionType.DEPENDENCY) {
      requirements.add(TreeCoreAnnotations.TreeAnnotation.class);
      requirements.add(CoreAnnotations.CategoryAnnotation.class);
    }
    return Collections.unmodifiableSet(requirements);
  }

  @Override
  public Set> requirementsSatisfied() {
    return Collections.singleton(CorefCoreAnnotations.CorefChainAnnotation.class);
  }

}