使用标准 corenlp 包获取 corefrences

Question

我正在尝试在文本中获取共同引用。我是 corenlp 包的新手。我尝试了下面的代码，它不起作用，但我也愿意接受其他方法。

/*
 * To change this template, choose Tools | Templates
 * and open the template in the editor.
 */

package corenlp;
import edu.stanford.nlp.ling.CoreAnnotations.CollapsedCCProcessedDependenciesAnnotation;
import edu.stanford.nlp.ling.CoreAnnotations.CorefGraphAnnotation;
import edu.stanford.nlp.ling.CoreAnnotations.NamedEntityTagAnnotation;
import edu.stanford.nlp.ling.CoreAnnotations.PartOfSpeechAnnotation;
import edu.stanford.nlp.ling.CoreAnnotations.SentencesAnnotation;
import edu.stanford.nlp.ling.CoreAnnotations.TextAnnotation;
import edu.stanford.nlp.ling.CoreAnnotations.TokensAnnotation;
import edu.stanford.nlp.ling.CoreAnnotations.TreeAnnotation;
import edu.stanford.nlp.ling.CoreLabel;
import edu.stanford.nlp.pipeline.*;
import edu.stanford.nlp.trees.Tree;
import edu.stanford.nlp.trees.semgraph.SemanticGraph;
import edu.stanford.nlp.util.CoreMap;
import edu.stanford.nlp.util.IntTuple;
import edu.stanford.nlp.util.Pair;
import edu.stanford.nlp.util.Timing;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

import java.util.Properties;
/**
 *
 * @author Karthi
 */
public class Main {


        // creates a StanfordCoreNLP object, with POS tagging, lemmatization, NER, parsing, and coreference resolution
    Properties props = new Properties();
    FileInputStream in = new FileInputStream("Main.properties");

    props.load(in);
    in.close();
    StanfordCoreNLP pipeline = new StanfordCoreNLP(props);

    // read some text in the text variable
    String text = "The doctor can consult with other doctors about this patient. If that is the case, the name of the doctor and the names of the consultants have to be maintained. Otherwise, only the name of the doctor is kept. "; // Add your text here!

    // create an empty Annotation just with the given text
    Annotation document = new Annotation(text);

    // run all Annotators on this text
    pipeline.annotate(document);
    System.out.println(document);
    // these are all the sentences in this document
    // a CoreMap is essentially a Map that uses class objects as keys and has values with custom types
    List<CoreMap> sentences = (List<CoreMap>) document.get(SentencesAnnotation.class);
    System.out.println(sentences);
    for(CoreMap sentence: sentences) {
      // traversing the words in the current sentence
      // a CoreLabel is a CoreMap with additional token-specific methods
      for (CoreLabel token: sentence.get(TokensAnnotation.class)) {
        // this is the text of the token
        String word = token.get(TextAnnotation.class);
        // this is the POS tag of the token
        String pos = token.get(PartOfSpeechAnnotation.class);
        // this is the NER label of the token
        String ne = token.get(NamedEntityTagAnnotation.class);
      }

      // this is the parse tree of the current sentence
      Tree tree = sentence.get(TreeAnnotation.class);
System.out.println(tree);
      // this is the Stanford dependency graph of the current sentence
      SemanticGraph dependencies = sentence.get(CollapsedCCProcessedDependenciesAnnotation.class);
      System.out.println(dependencies);
    }

    // this is the coreference link graph
    // each link stores an arc in the graph; the first element in the Pair is the source, the second is the target
    // each node is stored as <sentence id, token id>. Both offsets start at 1!
    List<Pair<IntTuple, IntTuple>> graph = document.get(CorefGraphAnnotation.class);
    System.out.println(graph);

    }

}

这是我得到的错误：

Loading POS Model [// For POS model] ... Loading default properties from trained tagger // For POS model
Error: No such trained tagger config file found.
java.io.FileNotFoundException: \\ For POS model (The specified path is invalid)
        at java.io.FileInputStream.open(Native Method)
        at java.io.FileInputStream.<init>(FileInputStream.java:106)
        at java.io.FileInputStream.<init>(FileInputStream.java:66)
        at edu.stanford.nlp.tagger.maxent.TaggerConfig.getTaggerDataInputStream(TaggerConfig.java:741)
        at edu.stanford.nlp.tagger.maxent.TaggerConfig.<init>(TaggerConfig.java:178)
        at edu.stanford.nlp.tagger.maxent.MaxentTagger.<init>(MaxentTagger.java:228)
        at edu.stanford.nlp.pipeline.POSTaggerAnnotator.loadModel(POSTaggerAnnotator.java:57)
        at edu.stanford.nlp.pipeline.POSTaggerAnnotator.<init>(POSTaggerAnnotator.java:44)
        at edu.stanford.nlp.pipeline.StanfordCoreNLP$4.create(StanfordCoreNLP.java:441)
        at edu.stanford.nlp.pipeline.StanfordCoreNLP$4.create(StanfordCoreNLP.java:434)
        at edu.stanford.nlp.pipeline.AnnotatorPool.get(AnnotatorPool.java:62)
        at edu.stanford.nlp.pipeline.StanfordCoreNLP.construct(StanfordCoreNLP.java:309)
        at edu.stanford.nlp.pipeline.StanfordCoreNLP.<init>(StanfordCoreNLP.java:347)
        at edu.stanford.nlp.pipeline.StanfordCoreNLP.<init>(StanfordCoreNLP.java:337)
        at edu.stanford.nlp.pipeline.StanfordCoreNLP.<init>(StanfordCoreNLP.java:329)
        at corenlp.Main.main(Main.java:66)
Exception in thread "main" java.lang.RuntimeException: java.io.FileNotFoundException: \\ For POS model (The specified path is invalid)
        at edu.stanford.nlp.pipeline.StanfordCoreNLP$4.create(StanfordCoreNLP.java:443)
        at edu.stanford.nlp.pipeline.StanfordCoreNLP$4.create(StanfordCoreNLP.java:434)
        at edu.stanford.nlp.pipeline.AnnotatorPool.get(AnnotatorPool.java:62)
        at edu.stanford.nlp.pipeline.StanfordCoreNLP.construct(StanfordCoreNLP.java:309)
        at edu.stanford.nlp.pipeline.StanfordCoreNLP.<init>(StanfordCoreNLP.java:347)
        at edu.stanford.nlp.pipeline.StanfordCoreNLP.<init>(StanfordCoreNLP.java:337)
        at edu.stanford.nlp.pipeline.StanfordCoreNLP.<init>(StanfordCoreNLP.java:329)
        at corenlp.Main.main(Main.java:66)
Caused by: java.io.FileNotFoundException: \\ For POS model (The specified path is invalid)
        at java.io.FileInputStream.open(Native Method)
        at java.io.FileInputStream.<init>(FileInputStream.java:106)
        at java.io.FileInputStream.<init>(FileInputStream.java:66)
        at edu.stanford.nlp.tagger.maxent.TaggerConfig.getTaggerDataInputStream(TaggerConfig.java:741)
        at edu.stanford.nlp.tagger.maxent.MaxentTagger.readModelAndInit(MaxentTagger.java:643)
        at edu.stanford.nlp.tagger.maxent.MaxentTagger.<init>(MaxentTagger.java:268)
        at edu.stanford.nlp.tagger.maxent.MaxentTagger.<init>(MaxentTagger.java:228)
        at edu.stanford.nlp.pipeline.POSTaggerAnnotator.loadModel(POSTaggerAnnotator.java:57)
        at edu.stanford.nlp.pipeline.POSTaggerAnnotator.<init>(POSTaggerAnnotator.java:44)
        at edu.stanford.nlp.pipeline.StanfordCoreNLP$4.create(StanfordCoreNLP.java:441)
        ... 7 more
Java Result: 1

Answer 1

此错误仅意味着程序未找到其运行所需的数据模型。它们需要位于您的类路径上。如果您位于分发目录中，则可以使用如下命令来执行此操作：

java -cp stanford-corenlp-2010-11-12.jar:stanford-corenlp-models-2010-11-06.jar:xom.jar:jgrapht.jar -Xmx3g edu.stanford.nlp.pipeline.StanfordCoreNLP -annotators tokenize,ssplit,pos,lemma,ner,parse,dcoref -file input.txt

第二个 jar 包含模型。如果您使用的是 Windows，请将上面的冒号替换为分号。

Answer 2

我执行了以下操作：

• 使用上面提供的导入 Tex
• 检查 Main.properties 文件是否位于可访问路径中。正如卡蒂所说。
• 代替
  >> graph = document.get(CorefGraphAnnotation.class);
  与 Map graph = document.get(CorefChainAnnotation.class);
• 我得到的结果如下。够了吗？

{1=CHAIN1-[第 1 句中的“医生”，第 2 句中的“医生”，
第 3 句中的“医生”], 2=CHAIN2-[“其他医生对此的看法
句子 1 中的“病人”], 4=C HAIN4-[句子 1 中的“这个病人”],
5=CHAIN5-[第2句中的“那个”，第2句中的“案件”]，
7=CHAIN7-[“医生姓名和顾问姓名”中
第 2 句，第 3 句中的“仅医生姓名”]，
9=CHAIN9-[“医生和顾问的姓名”句子
2], 11=CHAIN11-[第 2 句中的“顾问姓名”],
13=CHAIN13-[第 2 句中的“顾问”]}

Answer 3

自本主题和此处的代码片段中的版本以来，文件的结构似乎略有变化： http://nlp.stanford.edu/software/corenlp.shtml

将导入替换为：

import edu.stanford.nlp.trees.semgraph.SemanticGraphCoreAnnotations.CollapsedCCProcessedDependenciesAnnotation;
import edu.stanford.nlp.dcoref.CorefCoreAnnotations.CorefChainAnnotation;
import edu.stanford.nlp.dcoref.CorefCoreAnnotations.CorefGraphAnnotation;
import edu.stanford.nlp.trees.TreeCoreAnnotations.TreeAnnotation;
import edu.stanford.nlp.trees.semgraph.SemanticGraph;
import edu.stanford.nlp.dcoref.CorefChain

这对我来说很有效;-)