nlp - 如何使用 stanford NLP 解析标记词

Question

我有一个以下列格式存储在 txt 文件中的标记句子列表：

We_PRP 've_VBP just_RB wrapped_VBN up_RP with_IN the_DT boys_NNS of_IN Block_NNP B_NNP

现在我想解析句子，我发现了以下代码：

String filename = "tt.txt";
    // This option shows loading and sentence-segmenting and tokenizing
    // a file using DocumentPreprocessor.
    TreebankLanguagePack tlp = new PennTreebankLanguagePack();
    GrammaticalStructureFactory gsf = tlp.grammaticalStructureFactory();
    // You could also create a tokenizer here (as below) and pass it
    // to DocumentPreprocessor
    for (List<HasWord> sentence : new DocumentPreprocessor(filename)) {
        Tree parse = lp.apply(sentence);
        parse.pennPrint();
        System.out.println();

        GrammaticalStructure gs = gsf.newGrammaticalStructure(parse);
        Collection tdl = gs.typedDependenciesCCprocessed();
        System.out.println(tdl);
        System.out.println();
    }

解析结果很长，我想知道问题出在这一行 new DocumentPreprocessor(filename) 它实际上重新标记了我的句子，有什么方法可以跳过标记步骤？

Answer 1

你可以在Parser FAQ中找到答案，我试过了，它对我有用

// set up grammar and options as appropriate
LexicalizedParser lp = LexicalizedParser.loadModel(grammar, options);
String[] sent3 = { "It", "can", "can", "it", "." };
// Parser gets tag of second "can" wrong without help                    
String[] tag3 = { "PRP", "MD", "VB", "PRP", "." };                             
List sentence3 = new ArrayList();
for (int i = 0; i < sent3.length; i++) {
  sentence3.add(new TaggedWord(sent3[i], tag3[i]));
}
Tree parse = lp.parse(sentence3);
parse.pennPrint();