edu.stanford.nlp.pipeline.RelationExtractorAnnotator Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of stanford-corenlp Show documentation
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.
package edu.stanford.nlp.pipeline;
import edu.stanford.nlp.util.logging.Redwood;
import java.util.*;
import edu.stanford.nlp.ie.machinereading.BasicRelationExtractor;
import edu.stanford.nlp.ie.machinereading.Extractor;
import edu.stanford.nlp.ie.machinereading.MachineReading;
import edu.stanford.nlp.ie.machinereading.domains.roth.RothCONLL04Reader;
import edu.stanford.nlp.ie.machinereading.domains.roth.RothEntityExtractor;
import edu.stanford.nlp.ie.machinereading.structure.EntityMention;
import edu.stanford.nlp.ie.machinereading.structure.MachineReadingAnnotations;
import edu.stanford.nlp.ie.machinereading.structure.MachineReadingAnnotations.RelationMentionsAnnotation;
import edu.stanford.nlp.ie.machinereading.structure.RelationMention;
import edu.stanford.nlp.ling.CoreAnnotation;
import edu.stanford.nlp.ling.CoreAnnotations;
import edu.stanford.nlp.ling.CoreAnnotations.SentencesAnnotation;
import edu.stanford.nlp.semgraph.SemanticGraphCoreAnnotations;
import edu.stanford.nlp.trees.TreeCoreAnnotations;
import edu.stanford.nlp.util.ArraySet;
import edu.stanford.nlp.util.CoreMap;
import edu.stanford.nlp.util.StringUtils;
/**
* Annotating relations between entities produced by the NER system.
* @author Sonal Gupta ([email protected])
*
*/
public class RelationExtractorAnnotator implements Annotator {
/** A logger for this class */
private static Redwood.RedwoodChannels log = Redwood.channels(RelationExtractorAnnotator.class);
MachineReading mr;
private static boolean verbose = false;
public RelationExtractorAnnotator(Properties props){
verbose = Boolean.parseBoolean(props.getProperty("sup.relation.verbose", "false"));
String relationModel = props.getProperty("sup.relation.model", DefaultPaths.DEFAULT_SUP_RELATION_EX_RELATION_MODEL);
try {
Extractor entityExtractor = new RothEntityExtractor();
BasicRelationExtractor relationExtractor = BasicRelationExtractor.load(relationModel);
log.info("Loading relation model from " + relationModel);
mr = MachineReading.makeMachineReadingForAnnotation(new RothCONLL04Reader(), entityExtractor, relationExtractor, null, null,
null, true, verbose);
} catch(Exception e){
e.printStackTrace();
throw new RuntimeException(e);
}
}
@Override
public void annotate(Annotation annotation) {
// extract entities and relations
Annotation output = mr.annotate(annotation);
// transfer entities/relations back to the original annotation
List outputSentences = output.get(SentencesAnnotation.class);
List origSentences = annotation.get(SentencesAnnotation.class);
for(int i = 0; i < outputSentences.size(); i ++){
CoreMap outSent = outputSentences.get(i);
CoreMap origSent = origSentences.get(i);
// set entities
List entities = outSent.get(MachineReadingAnnotations.EntityMentionsAnnotation.class);
origSent.set(MachineReadingAnnotations.EntityMentionsAnnotation.class, entities);
if(verbose && entities != null){
log.info("Extracted the following entities:");
for(EntityMention e: entities){
log.info("\t" + e);
}
}
// set relations
List relations = outSent.get(MachineReadingAnnotations.RelationMentionsAnnotation.class);
origSent.set(MachineReadingAnnotations.RelationMentionsAnnotation.class, relations);
if(verbose && relations != null){
log.info("Extracted the following relations:");
for(RelationMention r: relations){
if(! r.getType().equals(RelationMention.UNRELATED)){
log.info(r);
}
}
}
}
}
@Override
public Set> requires() {
return Collections.unmodifiableSet(new ArraySet<>(Arrays.asList(
CoreAnnotations.TokensAnnotation.class,
CoreAnnotations.SentencesAnnotation.class,
CoreAnnotations.PartOfSpeechAnnotation.class,
CoreAnnotations.NamedEntityTagAnnotation.class,
TreeCoreAnnotations.TreeAnnotation.class,
SemanticGraphCoreAnnotations.BasicDependenciesAnnotation.class,
SemanticGraphCoreAnnotations.CollapsedDependenciesAnnotation.class,
SemanticGraphCoreAnnotations.CollapsedCCProcessedDependenciesAnnotation.class
)));
}
@Override
public Set> requirementsSatisfied() {
return Collections.unmodifiableSet(new ArraySet<>(Arrays.asList(
MachineReadingAnnotations.EntityMentionsAnnotation.class,
RelationMentionsAnnotation.class
)));
}
public static void main(String[] args){
try{
Properties props = StringUtils.argsToProperties(args);
props.setProperty("annotators", "tokenize,ssplit,lemma,pos,parse,ner");
StanfordCoreNLP pipeline = new StanfordCoreNLP();
String sentence = "Barack Obama lives in America. Obama works for the Federal Goverment.";
Annotation doc = new Annotation(sentence);
pipeline.annotate(doc);
RelationExtractorAnnotator r = new RelationExtractorAnnotator(props);
r.annotate(doc);
for(CoreMap s: doc.get(CoreAnnotations.SentencesAnnotation.class)){
System.out.println("For sentence " + s.get(CoreAnnotations.TextAnnotation.class));
List rls = s.get(RelationMentionsAnnotation.class);
for(RelationMention rl: rls){
System.out.println(rl.toString());
}
}
}catch(Exception e){
e.printStackTrace();
}
}
}