从注释文档中获取Stanford Dependencies表示（Java）

Question

我正在尝试检索句子的斯坦福依赖关系表示。像这样：

nsubj(makes-8, Bell-1)
nsubj(distributes-10, Bell-1)
vmod(Bell-1, based-3)

我正在使用带有ddeparse注释器的coreNLP管道。以下代码以类似但不友好的格式生成输出。

private void printDepParse(Annotation document) {
        List<CoreMap> sentences = document.get(SentencesAnnotation.class);

        IoUtils.prln("---Dependencies---");

        for(CoreMap sentence: sentences) {
            // this is the Stanford dependency graph of the current sentence
            SemanticGraph dependencies = sentence.get(BasicDependenciesAnnotation.class);
            IoUtils.prln(dependencies.toString());
        }

        IoUtils.prln("---End Dependencies---");
    }

产生类似的东西：

-> fed/VBD (root)
  -> Jimmy/NNP (nsubj)
  -> dog/NN (xcomp)
    -> Billy/NNP (nsubj)
    -> the/DT (det)
  -> ./. (punct)

是否有一种简单的方法可以产生前者，更普遍接受的格式？

Answer 1

要获得Stanford Dependencies表示，您需要使用GrammaticalStructures类。这应该有效：

     for (CoreMap sentence: sentences) {                         
            Tree tree = sentence.get(TreeAnnotation.class);             
            TreebankLanguagePack tlp = new PennTreebankLanguagePack();

            GrammaticalStructureFactory gsf = tlp.grammaticalStructureFactory();
            GrammaticalStructure gs = gsf.newGrammaticalStructure(tree);

            Collection<TypedDependency> tdl = gs.typedDependenciesCCprocessed();

            System.out.println(tdl);
     }