Package edu.stanford.nlp.tagger.maxent

Examples of edu.stanford.nlp.tagger.maxent.MaxentTagger

46
47
48
49
50
51
52
53
54
55
56
  void setTagger() throws Exception
  {
    if(Dictionary.tagger==null)
    {
      if(this.language.equals("en"))
        Dictionary.tagger=new MaxentTagger("./data/taggermodels/"+this.language+"/english-left3words-distsim.tagger");
      if(this.language.equals("es"))
      {
        //TODO
      }
       
View Full Code Here
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
    preprocessor.setSentenceDelimiter(config.sentenceDelimiter);
    preprocessor.setTokenizerFactory(config.tlp.getTokenizerFactory());

    Timing timer = new Timing();

    MaxentTagger tagger = new MaxentTagger(config.tagger);
    List<List<TaggedWord>> tagged = new ArrayList<>();
    for (List<HasWord> sentence : preprocessor) {
      tagged.add(tagger.tagSentence(sentence));
    }

    System.err.printf("Tagging completed in %.2f sec.%n",
        timer.stop() / 1000.0);
View Full Code Here
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
      }
    }

    String text = "I can almost always tell when movies use fake dinosaurs.";

    MaxentTagger tagger = new MaxentTagger(taggerPath);
    DependencyParser parser = DependencyParser.loadFromModelFile(modelPath);

    DocumentPreprocessor tokenizer = new DocumentPreprocessor(new StringReader(text));
    for (List<HasWord> sentence : tokenizer) {
      List<TaggedWord> tagged = tagger.tagSentence(sentence);
      GrammaticalStructure gs = parser.predict(tagged);

      // Print typed dependencies
      System.err.println(gs);
    }
View Full Code Here
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
      }
    }

    String text = "My dog likes to shake his stuffed chickadee toy.";

    MaxentTagger tagger = new MaxentTagger(taggerPath);
    ShiftReduceParser model = ShiftReduceParser.loadModel(modelPath);

    DocumentPreprocessor tokenizer = new DocumentPreprocessor(new StringReader(text));
    for (List<HasWord> sentence : tokenizer) {
      List<TaggedWord> tagged = tagger.tagSentence(sentence);
      Tree tree = model.apply(tagged);
      System.err.println(tree);
    }
  }
View Full Code Here
33
34
35
36
37
38
39
40
41
        throw new IllegalArgumentException("Unknown argument: " + args[argIndex]);
      }
    }

    LexicalizedParser parser = LexicalizedParser.loadModel(inputFile);
    MaxentTagger tagger = new MaxentTagger(taggerFile);
    parser.reranker = new TaggerReranker(tagger, parser.getOp());
    parser.saveParserToSerialized(outputFile);
  }
View Full Code Here
92
93
94
95
96
97
98
99
100
101
102
    Timing timer = null;
    if (verbose) {
      timer = new Timing();
      timer.doing("Loading POS Model [" + loc + ']');
    }
    MaxentTagger tagger = new MaxentTagger(loc);
    if (verbose) {
      timer.done();
    }
    return tagger;
  }
View Full Code Here
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
      System.exit(-1);
    }
    try {
      // Load MaxentTagger, which is threadsafe
      String modelFile = args[0];
      final MaxentTagger tagger = new MaxentTagger(modelFile);

      // Configure to run with 4 worker threads
      int nThreads = 4;
      MulticoreWrapper<String,String> wrapper =
          new MulticoreWrapper<String,String>(nThreads,
              new ThreadsafeProcessor<String,String>() {
                @Override
                public String process(String input) {
                  return tagger.tagString(input);
                }
                @Override
                public ThreadsafeProcessor<String, String> newInstance() {
                  // MaxentTagger is threadsafe
                  return this;
View Full Code Here
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
  public static void main(String[] args) throws Exception {
    if (args.length != 2) {
      System.err.println("usage: java TaggerDemo2 modelFile fileToTag");
      return;
    }
    MaxentTagger tagger = new MaxentTagger(args[0]);
    TokenizerFactory<CoreLabel> ptbTokenizerFactory = PTBTokenizer.factory(new CoreLabelTokenFactory(),
                     "untokenizable=noneKeep");
    BufferedReader r = new BufferedReader(new InputStreamReader(new FileInputStream(args[1]), "utf-8"));
    PrintWriter pw = new PrintWriter(new OutputStreamWriter(System.out, "utf-8"));
    DocumentPreprocessor documentPreprocessor = new DocumentPreprocessor(r);
    documentPreprocessor.setTokenizerFactory(ptbTokenizerFactory);
    for (List<HasWord> sentence : documentPreprocessor) {
      List<TaggedWord> tSentence = tagger.tagSentence(sentence);
      pw.println(Sentence.listToString(tSentence, false));
    }

    // print the adjectives in one more sentence. This shows how to get at words and tags in a tagged sentence.
    List<HasWord> sent = Sentence.toWordList("The", "slimy", "slug", "crawled", "over", "the", "long", ",", "green", "grass", ".");
    List<TaggedWord> taggedSent = tagger.tagSentence(sent);
    for (TaggedWord tw : taggedSent) {
      if (tw.tag().startsWith("JJ")) {
        pw.println(tw.word());
      }
    }
View Full Code Here
16
17
18
19
20
21
22
23
24
25
26
27
  public static void main(String[] args) throws Exception {
    if (args.length != 2) {
      System.err.println("usage: java TaggerDemo modelFile fileToTag");
      return;
    }
    MaxentTagger tagger = new MaxentTagger(args[0]);
    List<List<HasWord>> sentences = MaxentTagger.tokenizeText(new BufferedReader(new FileReader(args[1])));
    for (List<HasWord> sentence : sentences) {
      List<TaggedWord> tSentence = tagger.tagSentence(sentence);
      System.out.println(Sentence.listToString(tSentence, false));
    }
  }
View Full Code Here
30
31
32
33
34
35
36
37
38
39
40
41
  public void testEnglishTagSet() {
    LexicalizedParser lp = LexicalizedParser.loadModel(englishParsers[0]);
    Set<String> tagSet = lp.getLexicon().tagSet(lp.treebankLanguagePack().getBasicCategoryFunction());
    for (String name : englishTaggers) {
      MaxentTagger tagger = new MaxentTagger(name);
      assertEquals("English PCFG parser/" + name + " tag set mismatch", tagSet, tagger.tagSet());
    }
    for (String name : englishParsers) {
      LexicalizedParser lp2 = LexicalizedParser.loadModel(name);
      assertEquals("English PCFG parser/" + name + " tag set mismatch",
                   tagSet, lp2.getLexicon().tagSet(lp.treebankLanguagePack().getBasicCategoryFunction()));
View Full Code Here
TOP

Related Classes of edu.stanford.nlp.tagger.maxent.MaxentTagger

  • com.jgaap.eventDrivers.StanfordPartOfSpeechEventDriver
  • com.samir_ahmed.Iris.PoSTagger
  • edu.stanford.nlp.io.PrintFile
  • edu.stanford.nlp.maxent.CGRunner
  • edu.stanford.nlp.maxent.Problem
  • edu.stanford.nlp.objectbank.ReaderIteratorFactory
  • edu.stanford.nlp.parser.lexparser.AddTaggerToParser
  • edu.stanford.nlp.parser.nndep.demo.DependencyParserDemo
  • edu.stanford.nlp.parser.nndep.DependencyParser
  • edu.stanford.nlp.parser.shiftreduce.demo.ShiftReduceDemo
    • 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.