Stanford CoreNLP：如何仅使用名称实体（OpenIE）获得RelationTriple三元组？

Question

I'm currently searching in CoreNLP Open Information Extraction (OpenIE) for relation triples (Subject, Predicate, Object) that contains only NameEntities in the Subject and Object types . But I don't know how to get the entity type of the RelationTriple object that is a List<CoreMap> .

Below is the code from https://stanfordnlp.github.io/CoreNLP/openie.html :

import edu.stanford.nlp.ie.util.RelationTriple;
import edu.stanford.nlp.ling.CoreAnnotations;
import edu.stanford.nlp.pipeline.Annotation;
import edu.stanford.nlp.pipeline.StanfordCoreNLP;
import edu.stanford.nlp.naturalli.NaturalLogicAnnotations;
import edu.stanford.nlp.util.CoreMap;

import java.util.Collection;
import java.util.Properties;

/**
 * A demo illustrating how to call the OpenIE system programmatically.
 */
public class OpenIEDemo {

  public static void main(String[] args) throws Exception {
    // Create the Stanford CoreNLP pipeline
    Properties props = new Properties();
    props.setProperty("annotators", "tokenize,ssplit,pos,lemma,depparse,natlog,openie");
    StanfordCoreNLP pipeline = new StanfordCoreNLP(props);

    // Annotate an example document.
    Annotation doc = new Annotation("Obama was born in Hawaii. He is our president.");
    pipeline.annotate(doc);

    // Loop over sentences in the document
    for (CoreMap sentence : doc.get(CoreAnnotations.SentencesAnnotation.class)) {
      // Get the OpenIE triples for the sentence
      Collection <RelationTriple> triples = sentence.get(NaturalLogicAnnotations.RelationTriplesAnnotation.class);
      // Print the triples
      for (RelationTriple triple : triples) {
      // Here is where I get the entity type from a triple's subject or object
        System.out.println(triple.confidence + "\t" +
            triple.subjectLemmaGloss() + "\t" +
            triple.relationLemmaGloss() + "\t" +
            triple.objectLemmaGloss());
      }
    }
  }
}

If there exists some way to get the entity type from RelationTriple class I would be grateful for the help.

Answer 1

The subject and object instance variables should be lists of CoreLabl s, which have named entity information attached via the #ner() method. Something like the following should do what you want:

Collection<RelationTriple> triples = sentence.get(RelationTriplesAnnotation.class);
List<RelationTriple> withNE = triples.stream()
    // make sure the subject is entirely named entities
    .filter( triple -> 
        triple.subject.stream().noneMatch(token -> "O".equals(token.ner())))
    // make sure the object is entirely named entities
    .filter( triple -> 
        triple.object.stream().noneMatch(token -> "O".equals(token.ner())))
    // Convert the stream back to a list
    .collect(Collectors.toList());