Package opennlp.tools.tokenize

Examples of opennlp.tools.tokenize.TokenizerME

94
95
96
97
98
99
100
      model = modelResource.getModel();
    } catch (ResourceAccessException e) {
      throw new ResourceInitializationException(e);
    }

    tokenizer = new TokenizerME(model);
  }
View Full Code Here
77
78
79
80
81
82
83
84
85
86
87
  public void setTokenizer(FileSystem fs, Path p){
    try {
      FSDataInputStream in = fs.open(p);
      TokenizerModel model;
      model = new TokenizerModel(in);
      tokenizer = new TokenizerME(model);
    }
    catch (IOException e) {
      e.printStackTrace();
    }
  }
View Full Code Here
77
78
79
80
81
82
83
84
85
86
87
  public void setTokenizer(FileSystem fs, Path p){
    try {
      FSDataInputStream in = fs.open(p);
      TokenizerModel model;
      model = new TokenizerModel(in);
      tokenizer = new TokenizerME(model);
    } catch (IOException e) {
      e.printStackTrace();
      throw new RuntimeException("OpenNLPTokenizer model not available at " + p);
    }
  }
View Full Code Here
81
82
83
84
85
86
87
88
89
90
91
  public void setTokenizer(FileSystem fs, Path p){
    try {
      FSDataInputStream in = fs.open(p);
      TokenizerModel model;
      model = new TokenizerModel(in);
      tokenizer = new TokenizerME(model);
    }
    catch (IOException e) {
      e.printStackTrace();
    }
  }
View Full Code Here
134
135
136
137
138
139
140
141
142
143
144
        Tokenizer tokenizer = null;
        if(language != null){
            try {
                TokenizerModel model = getTokenizerModel(language);
                if(model != null){
                    tokenizer = new TokenizerME(getTokenizerModel(language));
                }
            } catch (InvalidFormatException e) {
                log.warn("Unable to load Tokenizer Model for "+language+": " +
                    "Will use Simple Tokenizer instead",e);
            } catch (IOException e) {
View Full Code Here
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
    // the sentence detector and tokenizer constructors
    // take paths to their respective models
    SentenceDetectorME sdetector = new SentenceDetectorME(
        new SentenceModel(new FileInputStream(
            "models/en-sent.bin")));
    Tokenizer tokenizer = new TokenizerME(new TokenizerModel(
        new FileInputStream("models/en-token.bin")));

    // the parser takes the path to the parser models
    // directory and a few other options
    /*
     * boolean useTagDict = true; boolean useCaseInsensitiveTagDict = false;
     * int beamSize = opennlp.tools.parser.chunking.Parser.defaultBeamSize;
     * double advancePercentage =
     * opennlp.tools.parser.chunking.Parser.defaultAdvancePercentage;
     * opennlp.tools.parser.Parser parser = TreebankParser.getParser(
     * "models/parser", useTagDict, useCaseInsensitiveTagDict, beamSize,
     * advancePercentage);
     */Parser parser = ParserFactory.create(new ParserModel(
        new FileInputStream("models/en-parser-chunking.bin")),
        AbstractBottomUpParser.defaultBeamSize,
        AbstractBottomUpParser.defaultAdvancePercentage);

    // break a paragraph into sentences
    String[] sents = sdetector.sentDetect(paragraph.toString());

    // TODO handle paragraph (multiple sentences)
    String sent = sents[0];

    // tokenize brackets and parentheses by putting a space on either side.
    // this makes sure it doesn't get confused with output from the parser
    sent = untokenizedParenPattern1.matcher(sent).replaceAll("$1 $2");
    sent = untokenizedParenPattern2.matcher(sent).replaceAll("$1 $2");

    // get the tokenizer to break apart the sentence
    String[] tokens = tokenizer.tokenize(sent);

    // build a string to parse as well as a list of tokens
    StringBuffer sb = new StringBuffer();
    List<String> tokenList = new ArrayList<String>();
    for (int j = 0; j < tokens.length; j++) {
View Full Code Here
68
69
70
71
72
73
74
75
   *
   * @throws IOException
   */
  public ApacheExtractor() throws IOException {
    nameFinder = new NameFinderME(new TokenNameFinderModel(ApacheExtractor.class.getResourceAsStream(pathToNERModel)));
    tokenizer = new TokenizerME(new TokenizerModel(ApacheExtractor.class.getResourceAsStream(pathToTokenizerModel)));
        sentenceDetector = new SentenceDetectorME(new SentenceModel(ApacheExtractor.class.getResourceAsStream(pathToSentenceDetectorModel)));
  }
View Full Code Here
79
80
81
82
83
84
85
86
87
88
89
  public void setTokenizer(FileSystem fs, Path p){
    try {
      FSDataInputStream in = fs.open(p);
      TokenizerModel model;
      model = new TokenizerModel(in);
      tokenizer = new TokenizerME(model);
    } catch (IOException e) {
      e.printStackTrace();
      throw new RuntimeException("OpenNLPTokenizer model not available at " + p);
    }
  }
View Full Code Here
89
90
91
92
93
94
95
96
97
98
99
        if(languageConfig.isLanguage(language)){
            String modelName = languageConfig.getParameter(language, PARAM_MODEL);
            if(modelName != null){
                try {
                    TokenizerModel model = openNlp.getModel(TokenizerModel.class, modelName, null);
                    return new TokenizerME(model).tokenize(label);
                } catch (Exception e) {
                    log.warn("Unable to load configured TokenizerModel '"+modelName
                        + "' for language '"+language
                        + "! Fallback to default Tokenizers",e);
                }
View Full Code Here
TOP

Related Classes of opennlp.tools.tokenize.TokenizerME

  • com.bericotech.clavin.extractor.ApacheExtractor
  • edu.washington.cs.knowitall.util.DefaultObjects
  • functionality.SentencesToTree
  • gate.opennlp.OpenNlpTokenizer
  • io.lumify.opennlpDictionary.OpenNLPDictionaryExtractorGraphPropertyWorker
  • io.lumify.opennlpme.OpenNLPMaximumEntropyExtractorGraphPropertyWorker
  • ivory.core.tokenize.OpenNLPTokenizer
  • net.sf.nlpshell.Main
  • opennlp.maxent.EventCollectorAsStream
  • opennlp.maxent.EventStream
    • 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.