如何从CoreNLPParser中提取短语？

Question

看到截图了吗

从图像解析器中可以看到，它返回NP，VP，PP，NP。我希望能够访问不同深度的所有短语。例如，in depth=1有两个短语NP和VP，in depth=2有一些其他短语，in depth=3有一些其他短语。如何使用python访问属于depth=n的短语？

Answer 1

package edu.stanford.nlp.examples;

import edu.stanford.nlp.pipeline.*;
import edu.stanford.nlp.trees.*;

import java.util.*;
import java.util.stream.*;

public class ConstituencyParserExample {

    public static void main(String[] args) {
        String text = "The little lamb climbed the big mountain.";
        // set up pipeline properties
        Properties props = new Properties();
        // set the list of annotators to run
        props.setProperty("annotators", "tokenize,ssplit,pos,lemma,parse");
        // build pipeline
        StanfordCoreNLP pipeline = new StanfordCoreNLP(props);
        // create a document object
        CoreDocument document = new CoreDocument(text);
        // annnotate the document
        pipeline.annotate(document);
        int maxDepth = 5;
        for (CoreSentence sentence : document.sentences()) {
            Set<Constituent> constituents = sentence.constituencyParse().constituents(
                    new LabeledScoredConstituentFactory(), maxDepth).stream().filter(
                            x -> x.label().value().equals("NP")).collect(Collectors.toSet());
            for (Constituent constituent : constituents) {
                System.out.println("---");
                System.out.println("label: "+constituent.label().value());
                System.out.println(sentence.tokens().subList(constituent.start(), constituent.end()+1));
            }
        }
    }
}