使用opennlp进行依存句法分析

序

本文主要研究下如何使用opennlp进行依存句法分析

Parser

opennlp主要使用Parser来进行依存句法分析，其模型为ParserModel

@Test
    public void testParserTool() throws IOException {
        try (InputStream modelInputStream = this.getClass().getClassLoader().getResourceAsStream("chunker/en-parser-chunking.bin")) {
            ParserModel model = new ParserModel(modelInputStream);
            Parser parser = ParserFactory.create(model);
            String sentence = "The cow jumped over the moon";
            // Used to demonstrate difference between NER and Parser
            // sentence = "He was the last person to see Fred.";

            Parse parses[] = ParserTool.parseLine(sentence, parser, 3);
            for (Parse parse : parses) {
                parse.show();
            }
        } catch (IOException ex) {
            ex.printStackTrace();
        }
    }

这里使用en-parser-chunking.bin这个训练好的模型来进行分析

第一句输出以下

(TOP (PP (S (NP (DT The) (NN cow)) (PP (VP (VBD jumped) (PRT (RP over))))) (NP (DT the) (NN moon))))
(TOP (NP (NP (DT The) (NN cow)) (PP (S (VP (VBN jumped) (PP (IN over) (NP (DT the) (NN moon))))))))
(TOP (NP (NP (DT The) (NN cow)) (SBAR (S (VP (VBN jumped) (PP (IN over) (NP (DT the) (NN moon))))))))

第二句输出以下

(TOP (FRAG (FRAG (S (NP (PRP He)) (VP (VBD was) (NP (NP (DT the) (JJ last) (NN person)) (SBAR (S (VP (TO to) (VP (VB see))))))))) (: Fred.)))
(TOP (S (S (NP (PRP He)) (VP (VBD was) (NP (NP (DT the) (JJ last) (NN person)) (PP (VP (TO to) (VP (VB see))))))) (: Fred.)))
(TOP (S (FRAG (S (NP (PRP He)) (VP (VBD was) (NP (NP (DT the) (JJ last) (NN person)) (SBAR (S (VP (TO to) (VP (VB see))))))))) (: Fred.)))

小结

opennlp也支持依存句法分析，不过根节点的表示，stanford nlp使用的是ROOT，而opennlp使用的是TOP。

doc

• tools.parser.parsing