Eu quero fazer um trabalho muito simples: dada uma string contendo pronomes, eu quero resolvê-los.

por exemplo, eu quero transformar a frase "Maria tem um cordeirinho. Ela é fofa". em "Maria tem um cordeirinho. Maria é fofa".

Eu tentei usar o Stanford CoreNLP. No entanto, parece que não consigo fazer o analisador iniciar. Eu importei todos os jars incluídos em meu projeto usando o Eclipse e aloquei 3GB para a JVM (-Xmx3g).

O erro é muito estranho:

Exceção no encadeamento "main" java.lang.NoSuchMethodError: edu.stanford.nlp.parser.lexparser.LexicalizedParser.loadModel (Lava / lang / String; [Ljava / lang / String;) Ledu / stanford / nlp / parser / lexparser / LexicalizedParser;

Eu não entendo de onde vem esse L, eu acho que é a raiz do meu problema ... Isso é meio estranho. Eu tentei entrar nos arquivos de origem, mas não há nenhuma referência errada lá.

Código:

import edu.stanford.nlp.semgraph.SemanticGraphCoreAnnotations.CollapsedCCProcessedDependenciesAnnotation;
import edu.stanford.nlp.dcoref.CorefCoreAnnotations.CorefChainAnnotation;
import edu.stanford.nlp.dcoref.CorefCoreAnnotations.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.trees.TreeCoreAnnotations.TreeAnnotation;
import edu.stanford.nlp.ling.CoreLabel;
import edu.stanford.nlp.dcoref.CorefChain;
import edu.stanford.nlp.pipeline.*;
import edu.stanford.nlp.trees.Tree;
import edu.stanford.nlp.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.Map;

import java.util.Properties;

public class Coref {

/**
 * @param args the command line arguments
 */
public static void main(String[] args) throws IOException, ClassNotFoundException {
    // creates a StanfordCoreNLP object, with POS tagging, lemmatization, NER, parsing, and coreference resolution 
    Properties props = new Properties();
    props.put("annotators", "tokenize, ssplit, pos, lemma, ner, parse, dcoref");
    StanfordCoreNLP pipeline = new StanfordCoreNLP(props);

    // read some text in the text variable
    String text = "Mary has a little lamb. She is very cute."; // 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);

    // 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 = document.get(SentencesAnnotation.class);

    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);
    }

    // This is the coreference link graph
    // Each chain stores a set of mentions that link to each other,
    // along with a method for getting the most representative mention
    // Both sentence and token offsets start at 1!
    Map<Integer, CorefChain> graph = 
      document.get(CorefChainAnnotation.class);
    System.out.println(graph);
  }
}

Rastreio de pilha completa:

Adicionando anotador tokenize Adicionando anotador ssplit Adicionando anotador pos Carregando POS modelo [edu / stanford / nlp / modelos / pos-tagger / english-left3words / english-left3words-distsim.tagger] ... Carregando propriedades padrão de treinado tagger edu / stanford / nlp / models / pos-tagger / portuguese-left3words / portugues-left3words-distsim.tagger Lendo o modelo do Tag do POS do edu / stanford / NLP / modera / pos-tagger / english-left3words / english-left3words-distsim.tagger ... feito [2,1 seg]. feito [2,2 segundos]. Adicionando anotador lema Adicionando anotador ner Carregando classificador de edu / stanford / nlp / modelos / ner / english.all.3class.distsim.crf.ser.gz ... feito [4.0 seg]. Classificador de carregamento de edu / stanford / nlp / models / ner / portugues.muc.distsim.crf.ser.gz ... feito [3,0 seg]. Classificador de carregamento de edu / stanford / nlp / modelos / ner / english.conll.distsim.crf.ser.gz ... feito [3,3 seg]. Adicionando análise de anotador Exceção no encadeamento "main" java.lang.NoSuchMethodError: edu.stanford.nlp.parser.lexparser.LexicalizedParser.loadModel (Lava / lang / String; [Ljava / lang / String;) Ledu / stanford / nlp / analisador / lexparser / LexicalizedParser; em edu.stanford.nlp.pipeline.ParserAnnotator.loadModel (ParserAnnotator.java:115) em edu.stanford.nlp.pipeline.ParserAnnotator. (ParserAnnotator.java:64) em edu.stanford.nlp.pipeline.StanfordCoreNLP $ 12.create (StanfordCoreNLP.java:603) em edu.stanford.nlp.pipeline.StanfordCoreNLP $ 12.create (StanfordCoreNLP.java:585) em edu.stanford.nlp.pipeline.AnnotatorPool.get (AnnotatorPool.java:62) em edu.stanford .nlp.pipeline.StanfordCoreNLP.construct (StanfordCoreNLP.java:329) em edu.stanford.nlp.pipeline.StanfordCoreNLP. (StanfordCoreNLP.java:196) em edu.stanford.nlp.pipeline.StanfordCoreNLP. (StanfordCoreNLP.java:186 em edu.stanford.nlp.pipeline.StanfordCoreNLP. (StanfordCoreNLP.java:178) em Coref.main (Coref.java:41)