Package edu.stanford.nlp.process

Examples of edu.stanford.nlp.process.CoreLabelTokenFactory

105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
  }

  // TODO replace with GrammaticalStructure#readCoNLLGrammaticalStructureCollection
  public static void loadConllFile(String inFile, List<CoreMap> sents, List<DependencyTree> trees, boolean labeled)
  {
    CoreLabelTokenFactory tf = new CoreLabelTokenFactory(false);

    BufferedReader reader = null;
    try {
      reader = IOUtils.readerFromString(inFile);

      CoreMap sentence = new CoreLabel();
      List<CoreLabel> sentenceTokens = new ArrayList<>();

      DependencyTree tree = new DependencyTree();

      for (String line : IOUtils.getLineIterable(reader, false)) {
        String[] splits = line.split("\t");
        if (splits.length < 10) {
          trees.add(tree);
          sentence.set(CoreAnnotations.TokensAnnotation.class, sentenceTokens);
          sents.add(sentence);

          tree = new DependencyTree();
          sentence = new CoreLabel();
          sentenceTokens = new ArrayList<>();
        } else {
          String word = splits[1],
                  pos = splits[4],
                  depType = splits[7];
          int head = Integer.parseInt(splits[6]);

          CoreLabel token = tf.makeToken(word, 0, 0);
          token.setTag(pos);
          token.set(CoreAnnotations.CoNLLDepParentIndexAnnotation.class, head);
          token.set(CoreAnnotations.CoNLLDepTypeAnnotation.class, depType);
          sentenceTokens.add(token);
View Full Code Here
93
94
95
96
97
98
99
100
101
102
103
    System.out.println();

    // This option shows loading and using an explicit tokenizer
    String sent2 = "This is another sentence.";
    TokenizerFactory<CoreLabel> tokenizerFactory =
        PTBTokenizer.factory(new CoreLabelTokenFactory(), "");
    Tokenizer<CoreLabel> tok =
        tokenizerFactory.getTokenizer(new StringReader(sent2));
    List<CoreLabel> rawWords2 = tok.tokenize();
    parse = lp.apply(rawWords2);
View Full Code Here
72
73
74
75
76
77
78
79
80
81
        this.tokenFactory = (CoreTokenFactory<IN>) Class.forName(flags.tokenFactory).newInstance();
      } catch (Exception e) {
        throw new RuntimeException(e);
      }
    } else {
      this.tokenFactory = (CoreTokenFactory<IN>) new CoreLabelTokenFactory();
    }

    init(flags, this.tokenFactory, this.tokensAnnotationClassName);
  }
View Full Code Here
100
101
102
103
104
105
106
107
108
        this.tokenFactory = (CoreTokenFactory<IN>) Class.forName(tokenFactoryClassName).newInstance();
      } catch (Exception e) {
        throw new RuntimeException(e);
      }
    } else {
      this.tokenFactory = (CoreTokenFactory<IN>) new CoreLabelTokenFactory();
    }
    init(mapString, this.tokenFactory, this.tokensAnnotationClassName);
  }
View Full Code Here
106
107
108
109
110
111
112
113
    }
    init(mapString, this.tokenFactory, this.tokensAnnotationClassName);
  }

  public void init(String map) {
    init(map, (CoreTokenFactory<IN>) new CoreLabelTokenFactory(),
        "edu.stanford.nlp.ling.CoreAnnotations$TokensAnnotation");
  }
View Full Code Here
230
231
232
233
234
235
236
    protected boolean splitCompoundOption = false;
    protected boolean splitVerbOption = false;
    protected boolean splitContractionOption = false;

    public static TokenizerFactory<CoreLabel> newCoreLabelTokenizerFactory() {
      return new SpanishTokenizerFactory<CoreLabel>(new CoreLabelTokenFactory(), ANCORA_OPTS);
    }
View Full Code Here
137
138
139
140
141
142
143
144
145
146
147
            createInstance(flags.featureFactoriesArgs.get(i));
        this.featureFactories.add(indFeatureFactory);
      }
    }
    if (flags.tokenFactory == null) {
      tokenFactory = (CoreTokenFactory<IN>) new CoreLabelTokenFactory();
    } else {
      this.tokenFactory = new MetaClass(flags.tokenFactory).createInstance(flags.tokenFactoryArgs);
    //   this.tokenFactory = (CoreTokenFactory<IN>) Class.forName(flags.tokenFactory).newInstance();
    }
    // } catch (Exception e) {
View Full Code Here
31
32
33
34
35
36
37
38
39
40
41
    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);
View Full Code Here
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
      }
    }
   
    switch(type) {
    case Spanish:
      factory = SpanishTokenizer.factory(new CoreLabelTokenFactory(), options);
      break;
     
    case French:
      factory = FrenchTokenizer.factory(new CoreLabelTokenFactory(), options);
      break;
     
    case Whitespace:
      boolean eolIsSignificant = Boolean.valueOf(props.getProperty(EOL_PROPERTY, "false"));
      eolIsSignificant = eolIsSignificant || Boolean.valueOf(props.getProperty(StanfordCoreNLP.NEWLINE_SPLITTER_PROPERTY, "false"));
      factory = new WhitespaceTokenizer.WhitespaceTokenizerFactory<CoreLabel> (new CoreLabelTokenFactory(), eolIsSignificant);
      break;
     
    case English:
    case German:
      factory = PTBTokenizer.factory(new CoreLabelTokenFactory(), options);
      break;
     
    case Unspecified:
      System.err.println("TokenizerAnnotator: No tokenizer type provided. Defaulting to PTBTokenizer.");
      factory = PTBTokenizer.factory(new CoreLabelTokenFactory(), options);
      break;
     
    default:
      throw new IllegalArgumentException("No valid tokenizer type provided.\n" +
                                         "Use -tokenize.language, -tokenize.class, or -tokenize.whitespace \n" +
View Full Code Here
65
66
67
68
69
70
71
72
   *
   * @return A tokenizer
   */
  @Override
  public TokenizerFactory<? extends HasWord> getTokenizerFactory() {
    return SpanishTokenizer.factory(new CoreLabelTokenFactory(),
        "invertible,ptb3Escaping=true,splitAll=true");
  }
View Full Code Here
TOP

Related Classes of edu.stanford.nlp.process.CoreLabelTokenFactory

  • edu.stanford.nlp.dcoref.MUCMentionExtractor
  • edu.stanford.nlp.ie.AbstractSequenceClassifier
  • edu.stanford.nlp.international.arabic.process.ArabicTokenizer
  • edu.stanford.nlp.international.arabic.process.ArabicTokenizer$ArabicTokenizerFactory
  • edu.stanford.nlp.international.french.process.FrenchTokenizer$FrenchTokenizerFactory
  • edu.stanford.nlp.international.spanish.process.SpanishTokenizer$SpanishTokenizerFactory
  • edu.stanford.nlp.ling.CoreLabel
  • edu.stanford.nlp.parser.lexparser.demo.ParserDemo
  • edu.stanford.nlp.parser.nndep.Util
  • edu.stanford.nlp.pipeline.TokenizerAnnotator
    • 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.