Package edu.stanford.nlp.trees.international.french

Examples of edu.stanford.nlp.trees.international.french.FrenchTreeReaderFactory

42
43
44
45
46
47
48
49
50
51
52
53
    TwoDimensionalCounter<String,String> mweLabelToString = new TwoDimensionalCounter<String,String>();
    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);
View Full Code Here
146
147
148
149
150
151
152
153
154
155
156
157
      TwoDimensionalCounter<String, String> pretermLabel,
      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++) {
View Full Code Here
225
226
227
228
229
230
231
232
233
234
235
236
    TwoDimensionalCounter<String,String> unigramTagger =
      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);
      }
View Full Code Here
154
155
156
157
158
159
160
161
162
163
164
165
      //  (ROOT (SENT (. .)))
      TregexPattern pBadTree = TregexPattern.compile("@SENT <: @PUNC");
      TregexPattern pBadTree2 = TregexPattern.compile("@SENT <1 @PUNC <2 @PUNC !<3 __");
     
      BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(f), "UTF-8"));
      TreeReaderFactory trf = new FrenchTreeReaderFactory();
      TreeReader tr = trf.newTreeReader(br);
  
      int nTrees = 0;
      for(Tree t; (t = tr.readTree()) != null;nTrees++) {
        TregexMatcher m = pBadTree.matcher(t);
        TregexMatcher m2 = pBadTree2.matcher(t);
View Full Code Here
34
35
36
37
38
39
40
41
42
43
44
45
46
      System.exit(-1);
    }

    String treeFile = args[0];
   
    TreeReaderFactory trf = new FrenchTreeReaderFactory();
    try {
      TreeReader tr = trf.newTreeReader(new BufferedReader(new InputStreamReader(new FileInputStream(treeFile), "UTF-8")));
 
      for (Tree tree1; (tree1 = tr.readTree()) != null;) {
        List<Label> pretermYield = tree1.preTerminalYield();
        List<Label> yield = tree1.yield();
        int yieldLen = yield.size();
View Full Code Here
114
115
116
117
118
119
120
121
122
123
124
125
126
      System.exit(-1);
    }

    String treeFile = args[0];
    String morfetteFile = args[1];
    TreeReaderFactory trf = new FrenchTreeReaderFactory();
    try {
      TreeReader tr = trf.newTreeReader(new BufferedReader(new InputStreamReader(new FileInputStream(treeFile), "UTF-8")));
      Iterator<List<CoreLabel>> morfetteItr = new MorfetteFileIterator(morfetteFile);
      for (Tree tree; (tree = tr.readTree()) != null && morfetteItr.hasNext();) {
        List<CoreLabel> analysis = morfetteItr.next();
        List<Label> yield = tree.yield();
        assert analysis.size() == yield.size();
View Full Code Here
155
156
157
158
159
160
161
162
163
164
165
    } else if(trfName.equalsIgnoreCase("NoEmptiesCTBTreeReaderFactory")) {
      return new NoEmptiesCTBTreeReaderFactory();
    } else if(trfName.equalsIgnoreCase("Basic categories only (LabeledScoredTreeReaderFactory)")) {
      return new LabeledScoredTreeReaderFactory();
    } else if(trfName.equalsIgnoreCase("FrenchTreeReaderFactory")) {
      return new FrenchTreeReaderFactory();//PTB format
    } else if(trfName.equalsIgnoreCase("PennTreeReaderFactory")) {
      return new PennTreeReaderFactory();
    } else if(trfName.equalsIgnoreCase("StringLabeledScoredTreeReaderFactory")) {
      return new StringLabeledScoredTreeReaderFactory();
    } else if(trfName.equalsIgnoreCase("TregexTreeReaderFactory")) {
View Full Code Here
563
564
565
566
567
568
569
  public MemoryTreebank memoryTreebank() {
    return new MemoryTreebank(treeReaderFactory(), inputEncoding);
  }

  public TreeReaderFactory treeReaderFactory() {
    return (readPennFormat) ? new FrenchTreeReaderFactory() : new FrenchXMLTreeReaderFactory(false);
  }
View Full Code Here
TOP

Related Classes of edu.stanford.nlp.trees.international.french.FrenchTreeReaderFactory

  • 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.parser.lexparser.FrenchTreebankParserParams
  • edu.stanford.nlp.trees.tregex.gui.Preferences
    • 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.