Package org.apache.uima.examples.tagger.trainAndTest

Examples of org.apache.uima.examples.tagger.trainAndTest.Token

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
    //    for (int i=0; i<sentences.size(); i++){ // iterate over sentences
         
             List<Token> tokens2 = new ArrayList<Token>(tokens.size());
            
             for (int x=0; x<tokens.size(); x++){ // iterate over tokens of the sentence with their corresponding POS
               Token current_token = (Token)tokens.get(x);
             
               if(current_token.pos.startsWith("N")){
                 current_token.pos="Noun";
               }
               if(current_token.pos.startsWith("V")){
                 current_token.pos="Verb";
               }
               if(current_token.pos.startsWith("ADJ")){
                 current_token.pos="Adjective";
               }
               if(current_token.pos.startsWith("P")){
                 current_token.pos="Pronoun";
               }
               if(current_token.pos.startsWith("KO")){
                 current_token.pos="Conjunction";
               }
               if(current_token.pos.startsWith("AP")){
                 current_token.pos="Preposition";
               }
               if(current_token.pos.startsWith("PTK")){
                 current_token.pos="PTK";
               }
               if(current_token.pos.startsWith("ADV")){
                 current_token.pos="Adverb";
               }
              
               if(current_token.pos.startsWith("ART")){
                 current_token.pos="Article";
               }
              
               if(current_token.pos.startsWith("ITJ")){
                 current_token.pos="Interjection";
               }
              
               Token zwischen = new Token(current_token.word, current_token.pos);
      
               tokens2.add(zwischen);
             }
            return tokens2;
           
View Full Code Here
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
    List<Token> tokens2 = new ArrayList<Token>(tokens.size());

    for (int x = 0; x < tokens.size(); x++) { // iterate over tokens of the sentence with their
      // corresponding POS
      Token current_token = (Token)tokens.get(x);
      String[] z = new String[2];
      if (current_token.pos.contains("+")) {
        z = current_token.pos.split("[+]");
        current_token.pos = z[0];
      }
      // for cases like : BEZ*
      if (current_token.pos.contains("*") && !(current_token.pos.startsWith("*"))) {
        z[0] = current_token.pos.replace("*", "");
        current_token.pos = z[0];
      }

      // for: *-h1
      if (current_token.pos.startsWith("*")) {
        z[0] = "*";
        current_token.pos = z[0];
      }
      if (current_token.pos.contains("-") && !(current_token.pos.startsWith("--"))) {
        z = current_token.pos.split("[-]");
        current_token.pos = z[0];
      }
      if (current_token.pos.startsWith("--")) {
        z[0] = "--";
        current_token.pos = z[0];
      }

      Token zwischen = new Token(current_token.word, current_token.pos);

      tokens2.add(zwischen);
    }
    return tokens2;

View Full Code Here
127
128
129
130
131
132
133
134
135
136
137
        Integer i = 0;
        while ( itPOS.hasNext() ) {
          Annotation token = itPOS.next();
          // Create a new token to be learned and add it to the list,
          // if the POS value is relevant (not null)
          Token tokenTmp = new Token();
          tokenTmp.word  = token.getCoveredText();
          tokenTmp.pos   = token.getStringValue(featPOS);
          if (tokenTmp.pos != null) {
            c++;
            theLearnedTokens.add(tokenTmp);
View Full Code Here
TOP

Related Classes of org.apache.uima.examples.tagger.trainAndTest.Token

  • org.apache.uima.examples.tagger.HMMModelTrainer
  • org.apache.uima.examples.tagger.trainAndTest.GrobMappingTueba
  • org.apache.uima.examples.tagger.trainAndTest.TagMappingBrown
    • 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.