Package edu.stanford.nlp.parser.lexparser

Examples of edu.stanford.nlp.parser.lexparser.TreebankLangParserParams

120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
   * Run the Evalb scoring metric on guess/gold input. The default language is English.
   *
   * @param args
   */
  public static void main(String[] args) {
    TreebankLangParserParams tlpp = new EnglishTreebankParserParams();
    int maxGoldYield = Integer.MAX_VALUE;
    boolean VERBOSE = false;
    String encoding = "UTF-8";

    String guessFile = null;
    String goldFile = null;

    Map<String, String[]> argsMap = StringUtils.argsToMap(args, optionArgDefs);

    for(Map.Entry<String, String[]> opt : argsMap.entrySet()) {
      if(opt.getKey() == null) continue;
      if(opt.getKey().equals("-l")) {
        Language lang = Language.valueOf(opt.getValue()[0].trim());
        tlpp = Languages.getLanguageParams(lang);

      } else if(opt.getKey().equals("-y")) {
        maxGoldYield = Integer.parseInt(opt.getValue()[0].trim());

      } else if(opt.getKey().equals("-v")) {
        VERBOSE = true;

      } else if(opt.getKey().equals("-e")) {
        encoding = opt.getValue()[0];

      } else {
        System.err.println(usage.toString());
        System.exit(-1);
      }

      //Non-option arguments located at key null
      String[] rest = argsMap.get(null);
      if(rest == null || rest.length < minArgs) {
        System.err.println(usage.toString());
        System.exit(-1);
      }
      goldFile = rest[0];
      guessFile = rest[1];
    }

    tlpp.setInputEncoding(encoding);
    final PrintWriter pwOut = tlpp.pw();

    final Treebank guessTreebank = tlpp.diskTreebank();
    guessTreebank.loadPath(guessFile);
    pwOut.println("GUESS TREEBANK:");
    pwOut.println(guessTreebank.textualSummary());

    final Treebank goldTreebank = tlpp.diskTreebank();
    goldTreebank.loadPath(goldFile);
    pwOut.println("GOLD TREEBANK:");
    pwOut.println(goldTreebank.textualSummary());

    final UnlabeledAttachmentEval metric = new UnlabeledAttachmentEval("UAS LP/LR", true, tlpp.headFinder());

    final TreeTransformer tc = tlpp.collinizer();

    //The evalb ref implementation assigns status for each tree pair as follows:
    //
    //   0 - Ok (yields match)
    //   1 - length mismatch
View Full Code Here
37
38
39
40
41
42
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
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
    if(args.length < minArgs) {
      System.out.println(usage.toString());
      System.exit(-1);
    }

    TreebankLangParserParams tlpp = new EnglishTreebankParserParams();
    DiskTreebank tb = null;
    String encoding = "UTF-8";

    for(int i = 0; i < args.length; i++) {
      if(args[i].startsWith("-")) {
        switch (args[i]) {
          case "-l":
            Language lang = Language.valueOf(args[++i].trim());
            tlpp = Languages.getLanguageParams(lang);

            break;
          case "-e":
            encoding = args[++i];

            break;
          default:
            System.out.println(usage.toString());
            System.exit(-1);
        }

      } else {
        if(tb == null) {
          if(tlpp == null) {
            System.out.println(usage.toString());
            System.exit(-1);
          } else {
            tlpp.setInputEncoding(encoding);
            tlpp.setOutputEncoding(encoding);
            tb = tlpp.diskTreebank();
          }
        }
        tb.loadPath(args[i]);
      }
    }

    Counter<String> vocab = new ClassicCounter<String>();
    for(Tree t : tb) {
      List<Label> yield = t.yield();
      for(Label word : yield)
        vocab.incrementCount(word.value());
    }

    List<String> biggestKeys = new ArrayList<String>(vocab.keySet());
    Collections.sort(biggestKeys, Counters.toComparatorDescending(vocab));

    PrintWriter pw = tlpp.pw();
    for(String wordType : biggestKeys)
      pw.printf("%s\t%d%n", wordType,(int) vocab.getCount(wordType));
    pw.close();
  }
View Full Code Here
37
38
39
40
41
42
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
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
    if(args.length < minArgs) {
      System.out.println(usage.toString());
      System.exit(-1);
    }

    TreebankLangParserParams tlpp = new EnglishTreebankParserParams();
    DiskTreebank tb = null;
    String encoding = "UTF-8";
    String puncTag = null;

    for(int i = 0; i < args.length; i++) {
      if(args[i].startsWith("-")) {
        switch (args[i]) {
          case "-l":
            Language lang = Language.valueOf(args[++i].trim());
            tlpp = Languages.getLanguageParams(lang);

            break;
          case "-e":
            encoding = args[++i];

            break;
          default:
            System.out.println(usage.toString());
            System.exit(-1);
        }

      } else {
        puncTag = args[i++];
       
        if(tb == null) {
          if(tlpp == null) {
            System.out.println(usage.toString());
            System.exit(-1);
          } else {
            tlpp.setInputEncoding(encoding);
            tlpp.setOutputEncoding(encoding);
            tb = tlpp.diskTreebank();
          }
        }
        tb.loadPath(args[i]);
      }
    }

    Counter<String> puncTypes = new ClassicCounter<String>();
    for(Tree t : tb) {
      List<CoreLabel> yield = t.taggedLabeledYield();
      for(CoreLabel word : yield)
        if(word.tag().equals(puncTag))
          puncTypes.incrementCount(word.word());
    }

    List<String> biggestKeys = new ArrayList<String>(puncTypes.keySet());
    Collections.sort(biggestKeys, Counters.toComparatorDescending(puncTypes));

    PrintWriter pw = tlpp.pw();
    for(String wordType : biggestKeys)
      pw.printf("%s\t%d%n", wordType,(int) puncTypes.getCount(wordType));
    pw.close();
  }
View Full Code Here
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
    boolean printTrees = PropertiesUtils.getBool(options, "p", false);
    boolean flattenTrees = PropertiesUtils.getBool(options, "f", false);
    boolean printPOS = PropertiesUtils.getBool(options, "a", false);
    boolean printTnT = PropertiesUtils.getBool(options, "t", false);
    Language language = PropertiesUtils.get(options, "l", Language.English, Language.class);
    TreebankLangParserParams tlpp = Languages.getLanguageParams(language);
    String encoding = options.getProperty("e", "UTF-8");
    tlpp.setInputEncoding(encoding);
    tlpp.setOutputEncoding(encoding);
   
    DiskTreebank tb = tlpp.diskTreebank();
    tb.loadPath(fileName);
   
    // Read the treebank
    PrintWriter pw = tlpp.pw();
    int numTrees = 0;
    for (Tree tree : tb) {
      if(tree.yield().size() > maxLen) continue;
      ++numTrees;
      if (printTrees) {
View Full Code Here
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
      System.exit(-1);
    }

    Properties options = StringUtils.argsToProperties(args, argDefs());
    Language language = PropertiesUtils.get(options, "l", Language.English, Language.class);
    TreebankLangParserParams tlpp = Languages.getLanguageParams(language);
    DiskTreebank tb = null;
    String encoding = options.getProperty("l", "UTF-8");
    boolean removeBracket = PropertiesUtils.getBool(options, "b", false);
   
    tlpp.setInputEncoding(encoding);
    tlpp.setOutputEncoding(encoding);
    tb = tlpp.diskTreebank();

    String[] files = options.getProperty("", "").split("\\s+");
    if (files.length != 0) {
      for (String filename : files) {
        tb.loadPath(filename);
      }
    } else {
      System.err.println(usage());
      System.exit(-1);
    }

    PrintWriter pwo = tlpp.pw();
    String startSymbol = tlpp.treebankLanguagePack().startSymbol();
    TreeFactory tf = new LabeledScoredTreeFactory();
    int nTrees = 0;
    for(Tree t : tb) {
      if(removeBracket) {
        if(t.value().equals(startSymbol)) {
View Full Code Here
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
    if(args.length < minArgs) {
      System.out.println(usage.toString());
      System.exit(-1);
    }

    TreebankLangParserParams tlpp = new EnglishTreebankParserParams();
    int maxGoldYield = Integer.MAX_VALUE;
    boolean VERBOSE = false;
    String encoding = "UTF-8";

    String guessFile = null;
    String goldFile = null;

    Map<String, String[]> argsMap = StringUtils.argsToMap(args, optionArgDefs);

    for(Map.Entry<String, String[]> opt : argsMap.entrySet()) {
      if(opt.getKey() == null) continue;
      if(opt.getKey().equals("-l")) {
        Language lang = Language.valueOf(opt.getValue()[0].trim());
        tlpp = Languages.getLanguageParams(lang);

      } else if(opt.getKey().equals("-y")) {
        maxGoldYield = Integer.parseInt(opt.getValue()[0].trim());

      } else if(opt.getKey().equals("-v")) {
        VERBOSE = true;

      } else if(opt.getKey().equals("-c")) {
        TaggingEval.doCatLevelEval = true;

      } else if(opt.getKey().equals("-e")) {
        encoding = opt.getValue()[0];

      } else {
        System.err.println(usage.toString());
        System.exit(-1);
      }

      //Non-option arguments located at key null
      String[] rest = argsMap.get(null);
      if(rest == null || rest.length < minArgs) {
        System.err.println(usage.toString());
        System.exit(-1);
      }
      goldFile = rest[0];
      guessFile = rest[1];
    }

    tlpp.setInputEncoding(encoding);
    final PrintWriter pwOut = tlpp.pw();

    final Treebank guessTreebank = tlpp.diskTreebank();
    guessTreebank.loadPath(guessFile);
    pwOut.println("GUESS TREEBANK:");
    pwOut.println(guessTreebank.textualSummary());

    final Treebank goldTreebank = tlpp.diskTreebank();
    goldTreebank.loadPath(goldFile);
    pwOut.println("GOLD TREEBANK:");
    pwOut.println(goldTreebank.textualSummary());

    final TaggingEval metric = new TaggingEval("Tagging LP/LR");

    final TreeTransformer tc = tlpp.collinizer();

    //The evalb ref implementation assigns status for each tree pair as follows:
    //
    //   0 - Ok (yields match)
    //   1 - length mismatch
View Full Code Here
38
39
40
41
42
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
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
    if(args.length < minArgs) {
      System.out.println(usage.toString());
      System.exit(-1);
    }

    TreebankLangParserParams tlpp = new EnglishTreebankParserParams();
    DiskTreebank tb = null;
    String encoding = "UTF-8";
    TregexPattern rootMatch = null;
   
    for(int i = 0; i < args.length; i++) {
      if(args[i].startsWith("-")) {
        switch (args[i]) {
          case "-l":
            Language lang = Language.valueOf(args[++i].trim());
            tlpp = Languages.getLanguageParams(lang);

            break;
          case "-e":
            encoding = args[++i];

            break;
          default:
            System.out.println(usage.toString());
            System.exit(-1);
        }

      } else {
        rootMatch = TregexPattern.compile("@" + args[i++]);

        if(tb == null) {
          if(tlpp == null) {
            System.out.println(usage.toString());
            System.exit(-1);
          } else {
            tlpp.setInputEncoding(encoding);
            tlpp.setOutputEncoding(encoding);
            tb = tlpp.diskTreebank();
          }
        }
        tb.loadPath(args[i++]);
      }
    }

    Counter<String> rhsCounter = new ClassicCounter<String>();
    for(Tree t : tb) {
      TregexMatcher m = rootMatch.matcher(t);
      while(m.findNextMatchingNode()) {
        Tree match = m.getMatch();
        StringBuilder sb = new StringBuilder();
        for(Tree kid : match.children())
          sb.append(kid.value()).append(" ");
        rhsCounter.incrementCount(sb.toString().trim());
      }
    }

    List<String> biggestKeys = new ArrayList<String>(rhsCounter.keySet());
    Collections.sort(biggestKeys, Counters.toComparatorDescending(rhsCounter));

    PrintWriter pw = tlpp.pw();
    for(String rhs : biggestKeys)
      pw.printf("%s\t%d%n", rhs,(int) rhsCounter.getCount(rhs));
    pw.close();
  }
View Full Code Here
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
      System.err.println(usage());
      System.exit(-1);
    }
    Properties options = StringUtils.argsToProperties(args, optionArgDefs());
    Language language = PropertiesUtils.get(options, "l", Language.English, Language.class);
    final TreebankLangParserParams tlpp = Languages.getLanguageParams(language);
    final int maxGoldYield = PropertiesUtils.getInt(options, "y", Integer.MAX_VALUE);
    final boolean VERBOSE = PropertiesUtils.getBool(options, "v", false);
    final boolean sortByF1 = PropertiesUtils.hasProperty(options, "s");
    int worstKTreesToEmit = PropertiesUtils.getInt(options, "s", 0);
    PriorityQueue<Triple<Double,Tree,Tree>> queue = sortByF1 ? new PriorityQueue<Triple<Double,Tree,Tree>>(2000, new F1Comparator()) : null;
    boolean doCatLevel = PropertiesUtils.getBool(options, "c", false);
    String labelRegex = options.getProperty("f", null);
    String encoding = options.getProperty("e", "UTF-8");

    String[] parsedArgs = options.getProperty("","").split("\\s+");
    if (parsedArgs.length != minArgs) {
      System.err.println(usage());
      System.exit(-1);
    }
    String goldFile = parsedArgs[0];
    String guessFile = parsedArgs[1];

    // Command-line has been parsed. Configure the metric for evaluation.
    tlpp.setInputEncoding(encoding);
    final PrintWriter pwOut = tlpp.pw();

    final Treebank guessTreebank = tlpp.diskTreebank();
    guessTreebank.loadPath(guessFile);
    pwOut.println("GUESS TREEBANK:");
    pwOut.println(guessTreebank.textualSummary());

    final Treebank goldTreebank = tlpp.diskTreebank();
    goldTreebank.loadPath(goldFile);
    pwOut.println("GOLD TREEBANK:");
    pwOut.println(goldTreebank.textualSummary());

    final Evalb metric = new Evalb("Evalb LP/LR", true);
    final EvalbByCat evalbCat = (doCatLevel) ? new EvalbByCat("EvalbByCat LP/LR", true, labelRegex) : null;
    final TreeTransformer tc = tlpp.collinizer();

    //The evalb ref implementation assigns status for each tree pair as follows:
    //
    //   0 - Ok (yields match)
    //   1 - length mismatch
View Full Code Here
448
449
450
451
452
453
454
455
456
457
458
    List<String> corpusPaths = new ArrayList<String>(parsedArgs.length-1);
    for (int i = 1; i < parsedArgs.length; ++i) {
      corpusPaths.add(parsedArgs[i]);
    }

    TreebankLangParserParams tlpp = Languages.getLanguageParams(language);
    TreebankStats cs = new TreebankStats(language,corpusPaths,tlpp);
    if(splitPrefix != null) {
      if(!cs.useSplit(splitPrefix)) System.err.println("Could not load split!");
    }
    cs.run(pathsAreFiles, SHOW_WORDS, SHOW_OOV);
View Full Code Here
TOP

Related Classes of edu.stanford.nlp.parser.lexparser.TreebankLangParserParams

  • edu.stanford.nlp.international.Languages
  • edu.stanford.nlp.parser.eval.TreebankFactoredLexiconStats
  • edu.stanford.nlp.parser.eval.TreebankStats
  • edu.stanford.nlp.parser.eval.UNKPrinter
  • edu.stanford.nlp.parser.metrics.CollinsDepEval
  • edu.stanford.nlp.parser.metrics.Evalb
  • edu.stanford.nlp.parser.metrics.LeafAncestorEval
  • edu.stanford.nlp.parser.metrics.TaggingEval
  • edu.stanford.nlp.parser.metrics.TsarfatyEval
  • edu.stanford.nlp.parser.metrics.UnlabeledAttachmentEval
    • 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.