0

我制作了一个类来使用 Tregex 提取子树。我使用了“TregexPattern.java”中的一些代码片段，因为我不想让程序使用控制台命令。

一般来说，有一个句子树，我想提取某个子树（没有用户交互）。

到目前为止我所做的如下：

package edu.stanford.nlp.trees.tregex;
import edu.stanford.nlp.ling.StringLabelFactory;
import edu.stanford.nlp.trees.*;
import java.io.*;
import java.util.*;
public abstract class Test {
    abstract TregexMatcher matcher(Tree root, Tree tree, Map<String, Tree> namesToNodes, VariableStrings variableStrings);
    public TregexMatcher matcher(Tree t) {
        return matcher(t, t, new HashMap<String, Tree>(), new VariableStrings());
    }
    public static void main(String[] args) throws ParseException, IOException {
        String encoding = "UTF-8";
        TregexPattern p = TregexPattern.compile("NP < NN & <<DT"); //"/^MWV/" or "NP < (NP=np < NNS)"
        TreeReader r = new PennTreeReader(new StringReader("(VP (VP (VBZ Try) (NP (NP (DT this) (NN wine)) (CC and) (NP (DT these) (NNS snails)))) (PUNCT .))"), new LabeledScoredTreeFactory(new StringLabelFactory()));
        Tree t = r.readTree();
        treebank = new MemoryTreebank();
        treebank.add(t);
        TRegexTreeVisitor vis = new TRegexTreeVisitor(p, encoding);
        **treebank.apply(vis);  //line 26**
        if (TRegexTreeVisitor.printMatches) {
            System.out.println("There were " + vis.numMatches() + " matches in total.");
        }
    }
    private static Treebank treebank; // used by main method, must be accessible
    static class TRegexTreeVisitor implements TreeVisitor {
        private static boolean printNumMatchesToStdOut = false;
        static boolean printNonMatchingTrees = false;
        static boolean printSubtreeCode = false;
        static boolean printTree = false;
        static boolean printWholeTree = false;
        static boolean printMatches = true;
        static boolean printFilename = false;
        static boolean oneMatchPerRootNode = false;
        static boolean reportTreeNumbers = false;
        static TreePrint tp;
        PrintWriter pw;
        int treeNumber = 0;
        TregexPattern p;
        //String[] handles;
        int numMatches;
        TRegexTreeVisitor(TregexPattern p, String encoding) {
            this.p = p;
            //this.handles = handles;
            try {
                pw = new PrintWriter(new OutputStreamWriter(System.out, encoding), true);
            } catch (UnsupportedEncodingException e) {
                System.err.println("Error -- encoding " + encoding + " is unsupported.  Using ASCII print writer instead.");
                pw = new PrintWriter(System.out, true);
            }
            // tp.setPrintWriter(pw);
        }
        public void visitTree(Tree t) {
            treeNumber++;
            if (printTree) {
                pw.print(treeNumber + ":");
                pw.println("Next tree read:");
                tp.printTree(t, pw);
            }
            TregexMatcher match = p.matcher(t);
            if (printNonMatchingTrees) {
                if (match.find()) {
                    numMatches++;
                } else {
                    tp.printTree(t, pw);
                }
                return;
            }
            Tree lastMatchingRootNode = null;
            while (match.find()) {
                if (oneMatchPerRootNode) {
                    if (lastMatchingRootNode == match.getMatch()) {
                        continue;
                    } else {
                        lastMatchingRootNode = match.getMatch();
                    }
                }
                numMatches++;
                if (printFilename && treebank instanceof DiskTreebank) {
                    DiskTreebank dtb = (DiskTreebank) treebank;
                    pw.print("# ");
                    pw.println(dtb.getCurrentFile());
                }
                if (printSubtreeCode) {
                    pw.println(treeNumber + ":" + match.getMatch().nodeNumber(t));
                }
                if (printMatches) {
                    if (reportTreeNumbers) {
                        pw.print(treeNumber + ": ");
                    }
                    if (printTree) {
                        pw.println("Found a full match:");
                    }
                    if (printWholeTree) {
                        tp.printTree(t, pw);
                    } else {
                        **tp.printTree(match.getMatch(), pw);  //line 108**
                    }
                    // pw.println();  // TreePrint already puts a blank line in
                } // end if (printMatches)
            } // end while match.find()
        } // end visitTree
        public int numMatches() {
            return numMatches;
        }
    } // end class TRegexTreeVisitor
}

但它给出了以下错误：

Exception in thread "main" java.lang.NullPointerException
        at edu.stanford.nlp.trees.tregex.Test$TRegexTreeVisitor.visitTree(Test.java:108)
        at edu.stanford.nlp.trees.MemoryTreebank.apply(MemoryTreebank.java:376)
        at edu.stanford.nlp.trees.tregex.Test.main(Test.java:26)
Java Result: 1

有什么修改或想法吗？

4

1 回答 1

1

NullPointerException 通常是软件错误的指标。

我过去也有同样的任务。句子是用依赖解析器解析的。我决定将生成的解析树放入 XML(DOM) 并对其执行 XPath 查询。

为了提高性能，您不需要将 xml 放入 String，只需将所有 XML 结构作为 DOM 保存在内存中（例如http://www.ibm.com/developerworks/xml/library/x-domjava/）。

使用 XPath 查询树状数据结构给了我以下好处：

  1. 轻松加载/保存/传输句子解析结果。
  2. XPath 的强大语法/功能。
  3. 很多人都知道 XPath（每个人都可以自定义您的查询）。
  4. XML 和 XPath 是跨平台的。
  5. XPath 和 XML/DOM 库的大量稳定实现。
  6. 能够使用 XSLT。
  7. 与现有的基于 XML 的管道集成XSLT+XPath -> XSD -> 执行操作 （例如，用户已经指定了他们的电子邮件地址并在自由文本投诉中的某处指定了如何处理它）。
于 2011-07-12T09:15:32.593 回答