如何在java中使用StanfordCorenlp包提取三元组？

我想要一个代码片段，它可以使用java中的Stanford CoreNLP包输入一个句子或一组句子，并输出或提取三元组（主语、谓语和宾语）

您是否在寻找OpenIE三元组，或更结构化的关系三元组（例如，对于

per:city_of_birth

）？对于前者，OpenIE系统很可能就是您想要的：。从那里的示例复制：

import edu.stanford.nlp.ie.util.RelationTriple;
import edu.stanford.nlp.simple.*;

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

  public static void main(String[] args) throws Exception {
    // Create a CoreNLP document
    Document doc = new Document("Obama was born in Hawaii. He is our president.");

    // Iterate over the sentences in the document
    for (Sentence sent : doc.sentences()) {
      // Iterate over the triples in the sentence
      for (RelationTriple triple : sent.openieTriples()) {
        // Print the triple
        System.out.println(triple.confidence + "\t" +
            triple.subjectLemmaGloss() + "\t" +
            triple.relationLemmaGloss() + "\t" +
            triple.objectLemmaGloss());
      }
    }
  }
}

或者，使用注释器API：

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) {
        System.out.println(triple.confidence + "\t" +
            triple.subjectLemmaGloss() + "\t" +
            triple.relationLemmaGloss() + "\t" +
            triple.objectLemmaGloss());
      }
    }
  }
}

导入edu.stanford.nlp.ie.util.RelationTriple；
导入edu.stanford.nlp.ling.core注释；
导入edu.stanford.nlp.pipeline.Annotation；
导入edu.stanford.nlp.pipeline.StanfordCoreNLP；
导入edu.stanford.nlp.naturalli.naturallogicanotations；
导入edu.stanford.nlp.util.CoreMap；
导入java.util.Collection；
导入java.util.Properties；
/**
*演示如何以编程方式调用OpenIE系统。
*/
公共类OpenIEDemo{
公共静态void main（字符串[]args）引发异常{
//创建斯坦福CoreNLP管道
Properties props=新属性（）；
props.setProperty（“注释器”、“标记化、ssplit、pos、引理、depparse、natlog、openie”）；
StanfordCoreNLP管道=新的StanfordCoreNLP（道具）；
//为示例文档添加注释。
注释doc=新注释（“奥巴马出生在夏威夷，他是我们的总统。”）；
管道注释（doc）；
//在文档中循环句子
for（CoreMap语句：doc.get（coreanotations.SentencesAnnotation.class））{
//获取句子的OpenIE三元组
集合三元组=句子.get（NaturalLogicAnnotations.RelationTriplesAnnotation.class）；
//打印三份
for（关系三重：三重）{
System.out.println（三重信心+“\t”+
triple.subjectLemmaGloss（）+“\t”+
triple.relationLemmaGloss（）+“\t”+
triple.objectLemmaGloss（））；
}
}
}
}

您是在寻找OpenIE三元组，还是更多的结构化关系三元组（例如，对于

per:city\u of\u Borth

）之类的东西？对于前者，OpenIE系统很可能就是您想要的：。从那里的示例复制：

import edu.stanford.nlp.ie.util.RelationTriple;
import edu.stanford.nlp.simple.*;

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

  public static void main(String[] args) throws Exception {
    // Create a CoreNLP document
    Document doc = new Document("Obama was born in Hawaii. He is our president.");

    // Iterate over the sentences in the document
    for (Sentence sent : doc.sentences()) {
      // Iterate over the triples in the sentence
      for (RelationTriple triple : sent.openieTriples()) {
        // Print the triple
        System.out.println(triple.confidence + "\t" +
            triple.subjectLemmaGloss() + "\t" +
            triple.relationLemmaGloss() + "\t" +
            triple.objectLemmaGloss());
      }
    }
  }
}

或者，使用注释器API：

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) {
        System.out.println(triple.confidence + "\t" +
            triple.subjectLemmaGloss() + "\t" +
            triple.relationLemmaGloss() + "\t" +
            triple.objectLemmaGloss());
      }
    }
  }
}

导入edu.stanford.nlp.ie.util.RelationTriple；
导入edu.stanford.nlp.ling.core注释；
导入edu.stanford.nlp.pipeline.Annotation；
导入edu.stanford.nlp.pipeline.StanfordCoreNLP；
导入edu.stanford.nlp.naturalli.naturallogicanotations；
导入edu.stanford.nlp.util.CoreMap；
导入java.util.Collection；
导入java.util.Properties；
/**
*演示如何以编程方式调用OpenIE系统。
*/
公共类OpenIEDemo{
公共静态void main（字符串[]args）引发异常{
//创建斯坦福CoreNLP管道
Properties props=新属性（）；
props.setProperty（“注释器”、“标记化、ssplit、pos、引理、depparse、natlog、openie”）；
StanfordCoreNLP管道=新的StanfordCoreNLP（道具）；
//为示例文档添加注释。
注释doc=新注释（“奥巴马出生在夏威夷，他是我们的总统。”）；
管道注释（doc）；
//在文档中循环句子
for（CoreMap语句：doc.get（coreanotations.SentencesAnnotation.class））{
//获取句子的OpenIE三元组
集合三元组=句子.get（NaturalLogicAnnotations.RelationTriplesAnnotation.class）；
//打印三份
for（关系三重：三重）{
System.out.println（三重信心+“\t”+
triple.subjectLemmaGloss（）+“\t”+
triple.relationLemmaGloss（）+“\t”+
triple.objectLemmaGloss（））；
}
}
}
}