private static void testTransAndUntrans(
     CharacterLevelTagExtender e, Treebank tb, PrintWriter pw) {
   for (Tree tree : tb) {
     Tree oldTree = tree.treeSkeletonCopy();
     e.transformTree(tree);
     CharacterLevelTagExtender.untransformTree(tree);
     if (!tree.equals(oldTree)) {
       pw.println("NOT EQUAL AFTER UNTRANSFORMATION!!!");
       pw.println();
       oldTree.pennPrint(pw);
       pw.println();
       tree.pennPrint(pw);
       pw.println("------------------");
     }
   }
 }
예제 #2
0
  public static void fillInParseAnnotations(
      boolean verbose, boolean buildGraphs, CoreMap sentence, Tree tree) {
    // make sure all tree nodes are CoreLabels
    // TODO: why isn't this always true? something fishy is going on
    ParserAnnotatorUtils.convertToCoreLabels(tree);

    // index nodes, i.e., add start and end token positions to all nodes
    // this is needed by other annotators down stream, e.g., the NFLAnnotator
    tree.indexSpans(0);

    sentence.set(TreeAnnotation.class, tree);
    if (verbose) {
      System.err.println("Tree is:");
      tree.pennPrint(System.err);
    }

    if (buildGraphs) {
      // generate the dependency graph
      SemanticGraph deps = generateCollapsedDependencies(tree);
      SemanticGraph uncollapsedDeps = generateUncollapsedDependencies(tree);
      SemanticGraph ccDeps = generateCCProcessedDependencies(tree);
      if (verbose) {
        System.err.println("SDs:");
        System.err.println(deps.toString("plain"));
      }
      sentence.set(SemanticGraphCoreAnnotations.CollapsedDependenciesAnnotation.class, deps);
      sentence.set(SemanticGraphCoreAnnotations.BasicDependenciesAnnotation.class, uncollapsedDeps);
      sentence.set(
          SemanticGraphCoreAnnotations.CollapsedCCProcessedDependenciesAnnotation.class, ccDeps);
    }

    setMissingTags(sentence, tree);
  }
예제 #3
0
 /**
  * Returns the List of dependencies for a binarized Tree. In this tree, one of the two children
  * always equals the head. The dependencies are in terms of the original tag set not the reduced
  * (projected) tag set.
  *
  * @param tree A tree to be analyzed as dependencies
  * @return The list of dependencies in the tree (int format)
  */
 public static List<IntDependency> treeToDependencyList(
     Tree tree, Index<String> wordIndex, Index<String> tagIndex) {
   List<IntDependency> depList = new ArrayList<IntDependency>();
   treeToDependencyHelper(tree, depList, 0, wordIndex, tagIndex);
   if (DEBUG) {
     System.out.println("----------------------------");
     tree.pennPrint();
     System.out.println(depList);
   }
   return depList;
 }
  private static void testParseAndRemovePeriods() {
    String testSentence = "Now is the time for all good men to come to the aid of their country.";

    CoreNlpParser parser = new CoreNlpParser();
    List<Tree> results = parser.getTextAnnotatedTree(testSentence);
    for (Tree tree : results) {
      tree.pennPrint();
    }

    System.out.println("\n");
  }
  /** For testing: loads a treebank and prints the trees. */
  public static void main(String[] args) {
    TreebankLangParserParams tlpp = new ChineseTreebankParserParams();
    System.out.println("Default encoding is: " + tlpp.diskTreebank().encoding());

    if (args.length < 2) {
      printlnErr(
          "Usage: edu.stanford.nlp.parser.lexparser.ChineseTreebankParserParams treesPath fileRange");
    } else {
      Treebank m = tlpp.diskTreebank();
      m.loadPath(args[0], new NumberRangesFileFilter(args[1], false));

      for (Tree t : m) {
        t.pennPrint(tlpp.pw());
      }
      System.out.println("There were " + m.size() + " trees.");
    }
  }
예제 #6
0
  public LinkedList<String> getKeyWrodsFromSentenceTest(String string) {

    LinkedList<String> list = new LinkedList<String>();

    String[] sent = string.split(" ");
    List<HasWord> sentence = new ArrayList<HasWord>();
    for (String word : sent) {
      sentence.add(new Word(word));
    }

    Tree parse = lp.parse(sentence);
    parse.pennPrint();
    GrammaticalStructure gs = gsf.newGrammaticalStructure(parse);

    List<TypedDependency> tdl = gs.typedDependenciesCCprocessed();
    System.out.println(tdl);

    System.out.println();

    System.out.println("The words of the sentence:");
    for (Label lab : parse.yield()) {
      if (lab instanceof CoreLabel) {
        System.out.println(((CoreLabel) lab).toString(CoreLabel.OutputFormat.VALUE_MAP));
      } else {
        System.out.println(lab);
      }
    }
    System.out.println();
    System.out.println("tagged");
    System.out.println(parse.taggedYield());

    List<CoreLabel> temp = parse.taggedLabeledYield();
    for (Label l : temp) {
      String[] sss = l.toString().split("-");
      String type = sss[0];
      System.out.println(sss[0] + "  " + sss[1] + "    " + sent[Integer.parseInt(sss[1])]);
    }

    for (Iterator<String> ite = list.iterator(); ite.hasNext(); ) System.out.println(ite.next());
    return list;
  }
예제 #7
0
  public static void main(String[] args) {
    Options op = new Options(new EnglishTreebankParserParams());
    // op.tlpParams may be changed to something else later, so don't use it till
    // after options are parsed.

    System.out.println(StringUtils.toInvocationString("FactoredParser", args));

    String path = "/u/nlp/stuff/corpora/Treebank3/parsed/mrg/wsj";
    int trainLow = 200, trainHigh = 2199, testLow = 2200, testHigh = 2219;
    String serializeFile = null;

    int i = 0;
    while (i < args.length && args[i].startsWith("-")) {
      if (args[i].equalsIgnoreCase("-path") && (i + 1 < args.length)) {
        path = args[i + 1];
        i += 2;
      } else if (args[i].equalsIgnoreCase("-train") && (i + 2 < args.length)) {
        trainLow = Integer.parseInt(args[i + 1]);
        trainHigh = Integer.parseInt(args[i + 2]);
        i += 3;
      } else if (args[i].equalsIgnoreCase("-test") && (i + 2 < args.length)) {
        testLow = Integer.parseInt(args[i + 1]);
        testHigh = Integer.parseInt(args[i + 2]);
        i += 3;
      } else if (args[i].equalsIgnoreCase("-serialize") && (i + 1 < args.length)) {
        serializeFile = args[i + 1];
        i += 2;
      } else if (args[i].equalsIgnoreCase("-tLPP") && (i + 1 < args.length)) {
        try {
          op.tlpParams = (TreebankLangParserParams) Class.forName(args[i + 1]).newInstance();
        } catch (ClassNotFoundException e) {
          System.err.println("Class not found: " + args[i + 1]);
          throw new RuntimeException(e);
        } catch (InstantiationException e) {
          System.err.println("Couldn't instantiate: " + args[i + 1] + ": " + e.toString());
          throw new RuntimeException(e);
        } catch (IllegalAccessException e) {
          System.err.println("illegal access" + e);
          throw new RuntimeException(e);
        }
        i += 2;
      } else if (args[i].equals("-encoding")) {
        // sets encoding for TreebankLangParserParams
        op.tlpParams.setInputEncoding(args[i + 1]);
        op.tlpParams.setOutputEncoding(args[i + 1]);
        i += 2;
      } else {
        i = op.setOptionOrWarn(args, i);
      }
    }
    // System.out.println(tlpParams.getClass());
    TreebankLanguagePack tlp = op.tlpParams.treebankLanguagePack();

    op.trainOptions.sisterSplitters =
        new HashSet<String>(Arrays.asList(op.tlpParams.sisterSplitters()));
    //    BinarizerFactory.TreeAnnotator.setTreebankLang(tlpParams);
    PrintWriter pw = op.tlpParams.pw();

    op.testOptions.display();
    op.trainOptions.display();
    op.display();
    op.tlpParams.display();

    // setup tree transforms
    Treebank trainTreebank = op.tlpParams.memoryTreebank();
    MemoryTreebank testTreebank = op.tlpParams.testMemoryTreebank();
    // Treebank blippTreebank = ((EnglishTreebankParserParams) tlpParams).diskTreebank();
    // String blippPath = "/afs/ir.stanford.edu/data/linguistic-data/BLLIP-WSJ/";
    // blippTreebank.loadPath(blippPath, "", true);

    Timing.startTime();
    System.err.print("Reading trees...");
    testTreebank.loadPath(path, new NumberRangeFileFilter(testLow, testHigh, true));
    if (op.testOptions.increasingLength) {
      Collections.sort(testTreebank, new TreeLengthComparator());
    }

    trainTreebank.loadPath(path, new NumberRangeFileFilter(trainLow, trainHigh, true));
    Timing.tick("done.");

    System.err.print("Binarizing trees...");
    TreeAnnotatorAndBinarizer binarizer;
    if (!op.trainOptions.leftToRight) {
      binarizer =
          new TreeAnnotatorAndBinarizer(
              op.tlpParams, op.forceCNF, !op.trainOptions.outsideFactor(), true, op);
    } else {
      binarizer =
          new TreeAnnotatorAndBinarizer(
              op.tlpParams.headFinder(),
              new LeftHeadFinder(),
              op.tlpParams,
              op.forceCNF,
              !op.trainOptions.outsideFactor(),
              true,
              op);
    }

    CollinsPuncTransformer collinsPuncTransformer = null;
    if (op.trainOptions.collinsPunc) {
      collinsPuncTransformer = new CollinsPuncTransformer(tlp);
    }
    TreeTransformer debinarizer = new Debinarizer(op.forceCNF);
    List<Tree> binaryTrainTrees = new ArrayList<Tree>();

    if (op.trainOptions.selectiveSplit) {
      op.trainOptions.splitters =
          ParentAnnotationStats.getSplitCategories(
              trainTreebank,
              op.trainOptions.tagSelectiveSplit,
              0,
              op.trainOptions.selectiveSplitCutOff,
              op.trainOptions.tagSelectiveSplitCutOff,
              op.tlpParams.treebankLanguagePack());
      if (op.trainOptions.deleteSplitters != null) {
        List<String> deleted = new ArrayList<String>();
        for (String del : op.trainOptions.deleteSplitters) {
          String baseDel = tlp.basicCategory(del);
          boolean checkBasic = del.equals(baseDel);
          for (Iterator<String> it = op.trainOptions.splitters.iterator(); it.hasNext(); ) {
            String elem = it.next();
            String baseElem = tlp.basicCategory(elem);
            boolean delStr = checkBasic && baseElem.equals(baseDel) || elem.equals(del);
            if (delStr) {
              it.remove();
              deleted.add(elem);
            }
          }
        }
        System.err.println("Removed from vertical splitters: " + deleted);
      }
    }
    if (op.trainOptions.selectivePostSplit) {
      TreeTransformer myTransformer =
          new TreeAnnotator(op.tlpParams.headFinder(), op.tlpParams, op);
      Treebank annotatedTB = trainTreebank.transform(myTransformer);
      op.trainOptions.postSplitters =
          ParentAnnotationStats.getSplitCategories(
              annotatedTB,
              true,
              0,
              op.trainOptions.selectivePostSplitCutOff,
              op.trainOptions.tagSelectivePostSplitCutOff,
              op.tlpParams.treebankLanguagePack());
    }

    if (op.trainOptions.hSelSplit) {
      binarizer.setDoSelectiveSplit(false);
      for (Tree tree : trainTreebank) {
        if (op.trainOptions.collinsPunc) {
          tree = collinsPuncTransformer.transformTree(tree);
        }
        // tree.pennPrint(tlpParams.pw());
        tree = binarizer.transformTree(tree);
        // binaryTrainTrees.add(tree);
      }
      binarizer.setDoSelectiveSplit(true);
    }
    for (Tree tree : trainTreebank) {
      if (op.trainOptions.collinsPunc) {
        tree = collinsPuncTransformer.transformTree(tree);
      }
      tree = binarizer.transformTree(tree);
      binaryTrainTrees.add(tree);
    }
    if (op.testOptions.verbose) {
      binarizer.dumpStats();
    }

    List<Tree> binaryTestTrees = new ArrayList<Tree>();
    for (Tree tree : testTreebank) {
      if (op.trainOptions.collinsPunc) {
        tree = collinsPuncTransformer.transformTree(tree);
      }
      tree = binarizer.transformTree(tree);
      binaryTestTrees.add(tree);
    }
    Timing.tick("done."); // binarization
    BinaryGrammar bg = null;
    UnaryGrammar ug = null;
    DependencyGrammar dg = null;
    // DependencyGrammar dgBLIPP = null;
    Lexicon lex = null;
    Index<String> stateIndex = new HashIndex<String>();

    // extract grammars
    Extractor<Pair<UnaryGrammar, BinaryGrammar>> bgExtractor =
        new BinaryGrammarExtractor(op, stateIndex);
    // Extractor bgExtractor = new SmoothedBinaryGrammarExtractor();//new BinaryGrammarExtractor();
    // Extractor lexExtractor = new LexiconExtractor();

    // Extractor dgExtractor = new DependencyMemGrammarExtractor();

    if (op.doPCFG) {
      System.err.print("Extracting PCFG...");
      Pair<UnaryGrammar, BinaryGrammar> bgug = null;
      if (op.trainOptions.cheatPCFG) {
        List<Tree> allTrees = new ArrayList<Tree>(binaryTrainTrees);
        allTrees.addAll(binaryTestTrees);
        bgug = bgExtractor.extract(allTrees);
      } else {
        bgug = bgExtractor.extract(binaryTrainTrees);
      }
      bg = bgug.second;
      bg.splitRules();
      ug = bgug.first;
      ug.purgeRules();
      Timing.tick("done.");
    }
    System.err.print("Extracting Lexicon...");
    Index<String> wordIndex = new HashIndex<String>();
    Index<String> tagIndex = new HashIndex<String>();
    lex = op.tlpParams.lex(op, wordIndex, tagIndex);
    lex.train(binaryTrainTrees);
    Timing.tick("done.");

    if (op.doDep) {
      System.err.print("Extracting Dependencies...");
      binaryTrainTrees.clear();
      Extractor<DependencyGrammar> dgExtractor =
          new MLEDependencyGrammarExtractor(op, wordIndex, tagIndex);
      // dgBLIPP = (DependencyGrammar) dgExtractor.extract(new
      // ConcatenationIterator(trainTreebank.iterator(),blippTreebank.iterator()),new
      // TransformTreeDependency(tlpParams,true));

      // DependencyGrammar dg1 = dgExtractor.extract(trainTreebank.iterator(), new
      // TransformTreeDependency(op.tlpParams, true));
      // dgBLIPP=(DependencyGrammar)dgExtractor.extract(blippTreebank.iterator(),new
      // TransformTreeDependency(tlpParams));

      // dg = (DependencyGrammar) dgExtractor.extract(new
      // ConcatenationIterator(trainTreebank.iterator(),blippTreebank.iterator()),new
      // TransformTreeDependency(tlpParams));
      // dg=new DependencyGrammarCombination(dg1,dgBLIPP,2);
      dg =
          dgExtractor.extract(
              binaryTrainTrees); // uses information whether the words are known or not, discards
      // unknown words
      Timing.tick("done.");
      // System.out.print("Extracting Unknown Word Model...");
      // UnknownWordModel uwm = (UnknownWordModel)uwmExtractor.extract(binaryTrainTrees);
      // Timing.tick("done.");
      System.out.print("Tuning Dependency Model...");
      dg.tune(binaryTestTrees);
      // System.out.println("TUNE DEPS: "+tuneDeps);
      Timing.tick("done.");
    }

    BinaryGrammar boundBG = bg;
    UnaryGrammar boundUG = ug;

    GrammarProjection gp = new NullGrammarProjection(bg, ug);

    // serialization
    if (serializeFile != null) {
      System.err.print("Serializing parser...");
      LexicalizedParser.saveParserDataToSerialized(
          new ParserData(lex, bg, ug, dg, stateIndex, wordIndex, tagIndex, op), serializeFile);
      Timing.tick("done.");
    }

    // test: pcfg-parse and output

    ExhaustivePCFGParser parser = null;
    if (op.doPCFG) {
      parser = new ExhaustivePCFGParser(boundBG, boundUG, lex, op, stateIndex, wordIndex, tagIndex);
    }

    ExhaustiveDependencyParser dparser =
        ((op.doDep && !op.testOptions.useFastFactored)
            ? new ExhaustiveDependencyParser(dg, lex, op, wordIndex, tagIndex)
            : null);

    Scorer scorer =
        (op.doPCFG ? new TwinScorer(new ProjectionScorer(parser, gp, op), dparser) : null);
    // Scorer scorer = parser;
    BiLexPCFGParser bparser = null;
    if (op.doPCFG && op.doDep) {
      bparser =
          (op.testOptions.useN5)
              ? new BiLexPCFGParser.N5BiLexPCFGParser(
                  scorer, parser, dparser, bg, ug, dg, lex, op, gp, stateIndex, wordIndex, tagIndex)
              : new BiLexPCFGParser(
                  scorer,
                  parser,
                  dparser,
                  bg,
                  ug,
                  dg,
                  lex,
                  op,
                  gp,
                  stateIndex,
                  wordIndex,
                  tagIndex);
    }

    Evalb pcfgPE = new Evalb("pcfg  PE", true);
    Evalb comboPE = new Evalb("combo PE", true);
    AbstractEval pcfgCB = new Evalb.CBEval("pcfg  CB", true);

    AbstractEval pcfgTE = new TaggingEval("pcfg  TE");
    AbstractEval comboTE = new TaggingEval("combo TE");
    AbstractEval pcfgTEnoPunct = new TaggingEval("pcfg nopunct TE");
    AbstractEval comboTEnoPunct = new TaggingEval("combo nopunct TE");
    AbstractEval depTE = new TaggingEval("depnd TE");

    AbstractEval depDE =
        new UnlabeledAttachmentEval("depnd DE", true, null, tlp.punctuationWordRejectFilter());
    AbstractEval comboDE =
        new UnlabeledAttachmentEval("combo DE", true, null, tlp.punctuationWordRejectFilter());

    if (op.testOptions.evalb) {
      EvalbFormatWriter.initEVALBfiles(op.tlpParams);
    }

    // int[] countByLength = new int[op.testOptions.maxLength+1];

    // Use a reflection ruse, so one can run this without needing the
    // tagger.  Using a function rather than a MaxentTagger means we
    // can distribute a version of the parser that doesn't include the
    // entire tagger.
    Function<List<? extends HasWord>, ArrayList<TaggedWord>> tagger = null;
    if (op.testOptions.preTag) {
      try {
        Class[] argsClass = {String.class};
        Object[] arguments = new Object[] {op.testOptions.taggerSerializedFile};
        tagger =
            (Function<List<? extends HasWord>, ArrayList<TaggedWord>>)
                Class.forName("edu.stanford.nlp.tagger.maxent.MaxentTagger")
                    .getConstructor(argsClass)
                    .newInstance(arguments);
      } catch (Exception e) {
        System.err.println(e);
        System.err.println("Warning: No pretagging of sentences will be done.");
      }
    }

    for (int tNum = 0, ttSize = testTreebank.size(); tNum < ttSize; tNum++) {
      Tree tree = testTreebank.get(tNum);
      int testTreeLen = tree.yield().size();
      if (testTreeLen > op.testOptions.maxLength) {
        continue;
      }
      Tree binaryTree = binaryTestTrees.get(tNum);
      // countByLength[testTreeLen]++;
      System.out.println("-------------------------------------");
      System.out.println("Number: " + (tNum + 1));
      System.out.println("Length: " + testTreeLen);

      // tree.pennPrint(pw);
      // System.out.println("XXXX The binary tree is");
      // binaryTree.pennPrint(pw);
      // System.out.println("Here are the tags in the lexicon:");
      // System.out.println(lex.showTags());
      // System.out.println("Here's the tagnumberer:");
      // System.out.println(Numberer.getGlobalNumberer("tags").toString());

      long timeMil1 = System.currentTimeMillis();
      Timing.tick("Starting parse.");
      if (op.doPCFG) {
        // System.err.println(op.testOptions.forceTags);
        if (op.testOptions.forceTags) {
          if (tagger != null) {
            // System.out.println("Using a tagger to set tags");
            // System.out.println("Tagged sentence as: " +
            // tagger.processSentence(cutLast(wordify(binaryTree.yield()))).toString(false));
            parser.parse(addLast(tagger.apply(cutLast(wordify(binaryTree.yield())))));
          } else {
            // System.out.println("Forcing tags to match input.");
            parser.parse(cleanTags(binaryTree.taggedYield(), tlp));
          }
        } else {
          // System.out.println("XXXX Parsing " + binaryTree.yield());
          parser.parse(binaryTree.yieldHasWord());
        }
        // Timing.tick("Done with pcfg phase.");
      }
      if (op.doDep) {
        dparser.parse(binaryTree.yieldHasWord());
        // Timing.tick("Done with dependency phase.");
      }
      boolean bothPassed = false;
      if (op.doPCFG && op.doDep) {
        bothPassed = bparser.parse(binaryTree.yieldHasWord());
        // Timing.tick("Done with combination phase.");
      }
      long timeMil2 = System.currentTimeMillis();
      long elapsed = timeMil2 - timeMil1;
      System.err.println("Time: " + ((int) (elapsed / 100)) / 10.00 + " sec.");
      // System.out.println("PCFG Best Parse:");
      Tree tree2b = null;
      Tree tree2 = null;
      // System.out.println("Got full best parse...");
      if (op.doPCFG) {
        tree2b = parser.getBestParse();
        tree2 = debinarizer.transformTree(tree2b);
      }
      // System.out.println("Debinarized parse...");
      // tree2.pennPrint();
      // System.out.println("DepG Best Parse:");
      Tree tree3 = null;
      Tree tree3db = null;
      if (op.doDep) {
        tree3 = dparser.getBestParse();
        // was: but wrong Tree tree3db = debinarizer.transformTree(tree2);
        tree3db = debinarizer.transformTree(tree3);
        tree3.pennPrint(pw);
      }
      // tree.pennPrint();
      // ((Tree)binaryTrainTrees.get(tNum)).pennPrint();
      // System.out.println("Combo Best Parse:");
      Tree tree4 = null;
      if (op.doPCFG && op.doDep) {
        try {
          tree4 = bparser.getBestParse();
          if (tree4 == null) {
            tree4 = tree2b;
          }
        } catch (NullPointerException e) {
          System.err.println("Blocked, using PCFG parse!");
          tree4 = tree2b;
        }
      }
      if (op.doPCFG && !bothPassed) {
        tree4 = tree2b;
      }
      // tree4.pennPrint();
      if (op.doDep) {
        depDE.evaluate(tree3, binaryTree, pw);
        depTE.evaluate(tree3db, tree, pw);
      }
      TreeTransformer tc = op.tlpParams.collinizer();
      TreeTransformer tcEvalb = op.tlpParams.collinizerEvalb();
      if (op.doPCFG) {
        // System.out.println("XXXX Best PCFG was: ");
        // tree2.pennPrint();
        // System.out.println("XXXX Transformed best PCFG is: ");
        // tc.transformTree(tree2).pennPrint();
        // System.out.println("True Best Parse:");
        // tree.pennPrint();
        // tc.transformTree(tree).pennPrint();
        pcfgPE.evaluate(tc.transformTree(tree2), tc.transformTree(tree), pw);
        pcfgCB.evaluate(tc.transformTree(tree2), tc.transformTree(tree), pw);
        Tree tree4b = null;
        if (op.doDep) {
          comboDE.evaluate((bothPassed ? tree4 : tree3), binaryTree, pw);
          tree4b = tree4;
          tree4 = debinarizer.transformTree(tree4);
          if (op.nodePrune) {
            NodePruner np = new NodePruner(parser, debinarizer);
            tree4 = np.prune(tree4);
          }
          // tree4.pennPrint();
          comboPE.evaluate(tc.transformTree(tree4), tc.transformTree(tree), pw);
        }
        // pcfgTE.evaluate(tree2, tree);
        pcfgTE.evaluate(tcEvalb.transformTree(tree2), tcEvalb.transformTree(tree), pw);
        pcfgTEnoPunct.evaluate(tc.transformTree(tree2), tc.transformTree(tree), pw);

        if (op.doDep) {
          comboTE.evaluate(tcEvalb.transformTree(tree4), tcEvalb.transformTree(tree), pw);
          comboTEnoPunct.evaluate(tc.transformTree(tree4), tc.transformTree(tree), pw);
        }
        System.out.println("PCFG only: " + parser.scoreBinarizedTree(tree2b, 0));

        // tc.transformTree(tree2).pennPrint();
        tree2.pennPrint(pw);

        if (op.doDep) {
          System.out.println("Combo: " + parser.scoreBinarizedTree(tree4b, 0));
          // tc.transformTree(tree4).pennPrint(pw);
          tree4.pennPrint(pw);
        }
        System.out.println("Correct:" + parser.scoreBinarizedTree(binaryTree, 0));
        /*
        if (parser.scoreBinarizedTree(tree2b,true) < parser.scoreBinarizedTree(binaryTree,true)) {
          System.out.println("SCORE INVERSION");
          parser.validateBinarizedTree(binaryTree,0);
        }
        */
        tree.pennPrint(pw);
      } // end if doPCFG

      if (op.testOptions.evalb) {
        if (op.doPCFG && op.doDep) {
          EvalbFormatWriter.writeEVALBline(
              tcEvalb.transformTree(tree), tcEvalb.transformTree(tree4));
        } else if (op.doPCFG) {
          EvalbFormatWriter.writeEVALBline(
              tcEvalb.transformTree(tree), tcEvalb.transformTree(tree2));
        } else if (op.doDep) {
          EvalbFormatWriter.writeEVALBline(
              tcEvalb.transformTree(tree), tcEvalb.transformTree(tree3db));
        }
      }
    } // end for each tree in test treebank

    if (op.testOptions.evalb) {
      EvalbFormatWriter.closeEVALBfiles();
    }

    // op.testOptions.display();
    if (op.doPCFG) {
      pcfgPE.display(false, pw);
      System.out.println("Grammar size: " + stateIndex.size());
      pcfgCB.display(false, pw);
      if (op.doDep) {
        comboPE.display(false, pw);
      }
      pcfgTE.display(false, pw);
      pcfgTEnoPunct.display(false, pw);
      if (op.doDep) {
        comboTE.display(false, pw);
        comboTEnoPunct.display(false, pw);
      }
    }
    if (op.doDep) {
      depTE.display(false, pw);
      depDE.display(false, pw);
    }
    if (op.doPCFG && op.doDep) {
      comboDE.display(false, pw);
    }
    // pcfgPE.printGoodBad();
  }
예제 #8
0
  public void evaluate(Tree guess, Tree gold, PrintWriter pw, double weight) {
    if (DEBUG) {
      log.info("Evaluating gold tree:");
      gold.pennPrint(System.err);
      log.info("and guess tree");
      guess.pennPrint(System.err);
    }
    Set<?> dep1 = makeObjects(guess);
    Set<?> dep2 = makeObjects(gold);
    final double curPrecision = precision(dep1, dep2);
    final double curRecall = precision(dep2, dep1);
    curF1 =
        (curPrecision > 0.0 && curRecall > 0.0
            ? 2.0 / (1.0 / curPrecision + 1.0 / curRecall)
            : 0.0);
    precision += curPrecision * weight;
    recall += curRecall * weight;
    f1 += curF1 * weight;
    num += weight;

    precision2 += dep1.size() * curPrecision * weight;
    pnum2 += dep1.size() * weight;

    recall2 += dep2.size() * curRecall * weight;
    rnum2 += dep2.size() * weight;

    if (curF1 > 0.9999) {
      exact += 1.0;
    }
    if (pw != null) {
      pw.print(" P: " + ((int) (curPrecision * 10000)) / 100.0);
      if (runningAverages) {
        pw.println(
            " (sent ave "
                + ((int) (precision * 10000 / num)) / 100.0
                + ") (evalb "
                + ((int) (precision2 * 10000 / pnum2)) / 100.0
                + ")");
      }
      pw.print(" R: " + ((int) (curRecall * 10000)) / 100.0);
      if (runningAverages) {
        pw.print(
            " (sent ave "
                + ((int) (recall * 10000 / num)) / 100.0
                + ") (evalb "
                + ((int) (recall2 * 10000 / rnum2)) / 100.0
                + ")");
      }
      pw.println();
      double cF1 = 2.0 / (rnum2 / recall2 + pnum2 / precision2);
      pw.print(str + " F1: " + ((int) (curF1 * 10000)) / 100.0);
      if (runningAverages) {
        pw.print(
            " (sent ave "
                + ((int) (10000 * f1 / num)) / 100.0
                + ", evalb "
                + ((int) (10000 * cF1)) / 100.0
                + ")   Exact: "
                + ((int) (10000 * exact / num)) / 100.0);
      }
      //      pw.println(" N: " + getNum());
      pw.println(" N: " + num);
    }
    /*
      Sentence s = guess.yield();
      for (Object obj : s) {
        if (curF1 < 0.7) {
          badwords.incrementCount(obj);
        } else {
          goodwords.incrementCount(obj);
        }
      }
    */
  }
  /**
   * for testing -- CURRENTLY BROKEN!!!
   *
   * @param args input dir and output filename
   * @throws IOException
   */
  public static void main(String[] args) throws IOException {
    if (args.length != 3) {
      throw new RuntimeException("args: treebankPath trainNums testNums");
    }

    ChineseTreebankParserParams ctpp = new ChineseTreebankParserParams();
    ctpp.charTags = true;
    // TODO: these options are getting clobbered by reading in the
    // parser object (unless it's a text file parser?)
    Options op = new Options(ctpp);
    op.doDep = false;
    op.testOptions.maxLength = 90;

    LexicalizedParser lp;
    try {
      FileFilter trainFilt = new NumberRangesFileFilter(args[1], false);

      lp = LexicalizedParser.trainFromTreebank(args[0], trainFilt, op);
      try {
        String filename = "chineseCharTagPCFG.ser.gz";
        System.err.println("Writing parser in serialized format to file " + filename + ' ');
        System.err.flush();
        ObjectOutputStream out = IOUtils.writeStreamFromString(filename);

        out.writeObject(lp);
        out.close();
        System.err.println("done.");
      } catch (IOException ioe) {
        ioe.printStackTrace();
      }
    } catch (IllegalArgumentException e) {
      lp = LexicalizedParser.loadModel(args[1], op);
    }

    FileFilter testFilt = new NumberRangesFileFilter(args[2], false);
    MemoryTreebank testTreebank = ctpp.memoryTreebank();
    testTreebank.loadPath(new File(args[0]), testFilt);
    PrintWriter pw =
        new PrintWriter(new OutputStreamWriter(new FileOutputStream("out.chi"), "GB18030"), true);
    WordCatEquivalenceClasser eqclass = new WordCatEquivalenceClasser();
    WordCatEqualityChecker eqcheck = new WordCatEqualityChecker();
    EquivalenceClassEval eval = new EquivalenceClassEval(eqclass, eqcheck);
    //    System.out.println("Preterminals:" + preterminals);
    System.out.println("Testing...");
    for (Tree gold : testTreebank) {
      Tree tree;
      try {
        tree = lp.parseTree(gold.yieldHasWord());
        if (tree == null) {
          System.out.println("Failed to parse " + gold.yieldHasWord());
          continue;
        }
      } catch (Exception e) {
        e.printStackTrace();
        continue;
      }
      gold = gold.firstChild();
      pw.println(Sentence.listToString(gold.preTerminalYield()));
      pw.println(Sentence.listToString(gold.yield()));
      gold.pennPrint(pw);

      pw.println(tree.preTerminalYield());
      pw.println(tree.yield());
      tree.pennPrint(pw);
      //      Collection allBrackets = WordCatConstituent.allBrackets(tree);
      //      Collection goldBrackets = WordCatConstituent.allBrackets(gold);
      //      eval.eval(allBrackets, goldBrackets);
      eval.displayLast();
    }
    System.out.println();
    System.out.println();
    eval.display();
  }