Package edu.stanford.nlp.trees

Examples of edu.stanford.nlp.trees.TreeReader

137
138
139
140
141
142
143
144
145
146
147
148
     * @see edu.jhu.hltcoe.sp.data.depparse.AgigaSentence#getStanfordContituencyTree()
     */
    public Tree getStanfordContituencyTree() {
        TreeFactory tf = new LabeledScoredTreeFactory();
        StringReader r = new StringReader(getParseText());
        TreeReader tr = new PennTreeReader(r, tf);
        try {
            return tr.readTree();
        } catch (IOException e) {
            throw new RuntimeException("Error: IOException should not be thrown by StringReader");
        }
    }
View Full Code Here
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
    Set<String> uniquePOSSequences = Generics.newHashSet();
   
    try {
      BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(treeFile), "UTF-8"));
      TreeReaderFactory trf = new FrenchTreeReaderFactory();
      TreeReader tr = trf.newTreeReader(br);

      final TregexPattern pMWE = TregexPattern.compile("/^MW/");
      for(Tree t; (t = tr.readTree()) != null;) {
        //Count MWE statistics
        TregexMatcher m = pMWE.matcher(t);
        while(m.findNextMatchingNode()) {
          Tree match = m.getMatch();
          String label = match.value();
          List<CoreLabel> yield = match.taggedLabeledYield();
          StringBuilder termYield = new StringBuilder();
          StringBuilder posYield = new StringBuilder();
          for(CoreLabel cl : yield) {
            termYield.append(cl.word()).append(" ");
            posYield.append(cl.tag()).append(" ");
          }
          mweLabelToString.incrementCount(label, termYield.toString().trim());
          uniquePOSSequences.add(posYield.toString().trim());
        }
      }
      tr.close(); //Closes the underlying reader
     
      System.out.printf("Type\t#Type\t#Single\t%%Single\t%%Total%n");
     
      double nMWEs = mweLabelToString.totalCount();
      int nAllSingletons = 0;
View Full Code Here
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
    String inputFile = args[0];
    File treeFile = new File(inputFile);
    try {
      TreeReaderFactory trf = new HebrewTreeReaderFactory();
      BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(treeFile), tlp.getEncoding()));
      TreeReader tr = trf.newTreeReader(br);

      PrintWriter pwDev = new PrintWriter(new PrintStream(new FileOutputStream(inputFile + ".clean.dev"),false,tlp.getEncoding()));
      PrintWriter pwTrain = new PrintWriter(new PrintStream(new FileOutputStream(inputFile + ".clean.train"),false,tlp.getEncoding()));
      PrintWriter pwTest = new PrintWriter(new PrintStream(new FileOutputStream(inputFile + ".clean.test"),false,tlp.getEncoding()));

      int numTrees = 0;
      for(Tree t; ((t = tr.readTree()) != null); numTrees++) {
        if(numTrees < 483)
          pwDev.println(t.toString());
        else if(numTrees >= 483 && numTrees < 5724)
          pwTrain.println(t.toString());
        else
          pwTest.println(t.toString());
      }

      tr.close();
      pwDev.close();
      pwTrain.close();
      pwTest.close();

      System.err.printf("Processed %d trees.%n",numTrees);
View Full Code Here
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
    TreebankLanguagePack tlp = new HebrewTreebankLanguagePack();
    File treeFile = new File(args[0]);
    try {
      TreeReaderFactory trf = new HebrewTreeReaderFactory();
      BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(treeFile), tlp.getEncoding()));
      TreeReader tr = trf.newTreeReader(br);

      int numTrees = 0;
      for(Tree t; ((t = tr.readTree()) != null); numTrees++)
        System.out.println(t.toString());

      tr.close();
      System.err.printf("Processed %d trees.%n",numTrees);

    } catch (UnsupportedEncodingException e) {
      e.printStackTrace();
    } catch (FileNotFoundException e) {
View Full Code Here
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
      TwoDimensionalCounter<String, String> unigramTagger) {

    try {
      BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(treeFile), "UTF-8"));
      TreeReaderFactory trf = new FrenchTreeReaderFactory();
      TreeReader tr = trf.newTreeReader(br);

      PrintWriter pw = new PrintWriter(new PrintStream(new FileOutputStream(new File(treeFile + ".fixed")),false,"UTF-8"));

      int nTrees = 0;
      for(Tree t; (t = tr.readTree()) != null;nTrees++) {
        traverseAndFix(t, pretermLabel, unigramTagger);
        pw.println(t.toString());
      }
      pw.close();
      tr.close();

      System.out.println("Processed " +nTrees+ " trees");

    } catch (UnsupportedEncodingException e) {
      e.printStackTrace();
View Full Code Here
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
      new TwoDimensionalCounter<String,String>();

    try {
      BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(treeFile), "UTF-8"));
      TreeReaderFactory trf = new FrenchTreeReaderFactory();
      TreeReader tr = trf.newTreeReader(br);

      for(Tree t; (t = tr.readTree()) != null;) {
        countMWEStatistics(t, unigramTagger,
                           labelPreterm, pretermLabel, labelTerm, termLabel);
      }
      tr.close(); //Closes the underlying reader

      System.out.println("Generating {MWE Type -> Terminal}");
      printCounter(labelTerm, "label_term.csv");

      System.out.println("Generating {Terminal -> MWE Type}");
View Full Code Here
43
44
45
46
47
48
49
50
51
52
53
54
55
56
    Tree t;
    for (File file : fileList) {
      Reader in =
        new BufferedReader(new InputStreamReader(new FileInputStream(file),
                                                 SpanishTreebankLanguagePack.STB_ENCODING));
      TreeReader tr = trf.newTreeReader(in);

      // Tree reading will implicitly perform tree normalization for us
      while ((t = tr.readTree()) != null) {
        // Update tagger with this tree
        List<CoreLabel> yield = t.taggedLabeledYield();
        for (CoreLabel leafLabel : yield) {
          if (leafLabel.tag().equals(SpanishTreeNormalizer.MW_TAG))
            continue;
View Full Code Here
49
50
51
52
53
54
55
56
57
58
59
    this.noNormalization = noNormalization;
    this.retainPPClr = retainPPClr;
  }

  public TreeReader newTreeReader(Reader in) {
    TreeReader tr = null;
    if(noNormalization) {
      tr = new PennTreeReader(in, new LabeledScoredTreeFactory(), new TreeNormalizer(), new ArabicTreebankTokenizer(in));
    } else
      tr = new PennTreeReader(in, new LabeledScoredTreeFactory(), new ArabicTreeNormalizer(retainNPTmp,retainPRD,changeNoLabels, retainNPSbj, retainPPClr), new ArabicTreebankTokenizer(in));
View Full Code Here
498
499
500
501
502
503
504
505
506
507
508
509
510
    for (final File file : fileList) {
      pool.execute(new Runnable() {
          public void run() {
            try {
              Reader in = new BufferedReader(new InputStreamReader(new FileInputStream(file), "ISO-8859-1"));
              TreeReader tr = trf.newTreeReader(file.getPath(), in);
              process(file, tr, posPattern, wordPattern, plainPrint);
              tr.close();
            } catch (FileNotFoundException e) {
              e.printStackTrace();
            } catch (IOException e) {
              e.printStackTrace();
            }
View Full Code Here
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
    TreebankLanguagePack tlp = new NegraPennLanguagePack();
    TreeReaderFactory trf = new NegraPennTreeReaderFactory(2,false,false,tlp);

    try {
      TreeReader tr = trf.newTreeReader(IOUtils.readerFromString(args[0], tlp.getEncoding()));

      for (Tree t; (t = tr.readTree()) != null; ) {
        t.pennPrint();
      }

      tr.close();

    } catch (UnsupportedEncodingException e) {
      e.printStackTrace();
    } catch (FileNotFoundException e) {
      e.printStackTrace();
View Full Code Here
TOP

Related Classes of edu.stanford.nlp.trees.TreeReader

  • edu.jhu.agiga.StanfordAgigaSentence
  • edu.stanford.nlp.international.arabic.pipeline.ATBCorrector
  • edu.stanford.nlp.international.arabic.pipeline.MWETreeVisitorExternal
  • edu.stanford.nlp.international.french.pipeline.FTBCorrector
  • edu.stanford.nlp.international.french.pipeline.MWEPreprocessor
  • edu.stanford.nlp.international.french.scripts.MungeTreesWithMorfetteAnalyses
  • edu.stanford.nlp.international.french.scripts.MWEFrequencyDist
  • edu.stanford.nlp.international.french.scripts.TreeToMorfette
  • edu.stanford.nlp.international.spanish.pipeline.AnCoraPOSStats
  • edu.stanford.nlp.international.spanish.pipeline.MultiWordPreprocessor
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.