Examples of VocabularyWritable

Examples of edu.umd.hooka.VocabularyWritable

147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
    testOOV("zh", vocab, false, false, zhExpectedOOVRates);   
  }

  @Test
  public void testTurkishOOVs() {
    VocabularyWritable vocab = new VocabularyWritable();
    List<String> sentences = readInput(dir + "data/tokenizer/test/tr-test.tok.stemmed.stop");
    for (String token : sentences.get(3).split(" ")) {
      vocab.addOrGet(token);
    }
    vocab.addOrGet("ispanyol");
    vocab.addOrGet("isim");
    vocab.addOrGet("10");

    float[] trStopStemExpectedOOVRates = {0.85714287f, 1f, 0.6f, 0f};
    float[] trStopExpectedOOVRates = {1f, 1f, 0.8f, 0.5f};
    float[] trStemExpectedOOVRates = {0.85714287f, 1f, 0.71428573f, 0.33333334f};
    float[] trExpectedOOVRates = {1f, 1f, 0.85714287f, 0.6666667f};
View Full Code Here

Examples of edu.umd.hooka.VocabularyWritable

169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
    testOOV("tr", vocab, false, false, trExpectedOOVRates);   
  }

  @Test
  public void testArabicOOVs() {
    VocabularyWritable vocab = new VocabularyWritable();
    List<String> sentences = readInput(dir + "data/tokenizer/test/ar-test.tok.stemmed.stop");
    for (String token : sentences.get(0).split(" ")) {
      vocab.addOrGet(token);
    }
    vocab.addOrGet("2011");
    float[] arStopStemExpectedOOVRates = {0f, 1f, 0.8181818f, 1f};
    float[] arStopExpectedOOVRates = {0.6666667f, 1f, 0.8181818f, 1f};
    float[] arStemExpectedOOVRates = {0f, 1f, 0.85714287f, 1f};
    float[] arExpectedOOVRates = {0.6666667f, 1f, 0.85714287f, 1f};
View Full Code Here

Examples of edu.umd.hooka.VocabularyWritable

188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
    testOOV("ar", vocab, false, false, arExpectedOOVRates);
  }

  @Test
  public void testEnglishOOVs() {
    VocabularyWritable vocab = new VocabularyWritable();
    vocab.addOrGet("r.d.");
    vocab.addOrGet("craig");
    vocab.addOrGet("dictionari");
    vocab.addOrGet("polynesian");
    vocab.addOrGet("mytholog");
    vocab.addOrGet("greenwood");
    vocab.addOrGet("press");
    vocab.addOrGet("new");
    vocab.addOrGet("york");
    vocab.addOrGet("1989");
    vocab.addOrGet("24");
    vocab.addOrGet("26");
    vocab.addOrGet("english");
    vocab.addOrGet("tree");
    vocab.addOrGet("einbaum");

    float[] enStopStemExpectedOOVRates = {1f, 18/19f, 4/7.0f, 0f};
    float[] enStopExpectedOOVRates = {1f, 18/19f, 4/7.0f, 2/12f};
    float[] enStemExpectedOOVRates = {1f, 36/37f, 15/18.0f, 7/19f};
    float[] enExpectedOOVRates = {1f, 36/37f, 15/18.0f, 9/19f};
View Full Code Here

Examples of edu.umd.hooka.VocabularyWritable

42
43
44
45
46
47
48
49
50
51
52
    String stemmedStopwordsFile = conf.get(Constants.StemmedStopwordList);
    stemmedStopwords = readInput(fs, stemmedStopwordsFile);
    isStopwordRemoval = !stopwords.isEmpty();
    isStemming = conf.getBoolean(Constants.Stemming, true);

    VocabularyWritable vocab;
    try {
      vocab = (VocabularyWritable) HadoopAlign.loadVocab(new Path(conf.get(Constants.CollectionVocab)), fs);
      setVocab(vocab);
    } catch (Exception e) {
      LOG.warn("No vocabulary provided to tokenizer.");
View Full Code Here

Examples of edu.umd.hooka.VocabularyWritable

148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
    }
  }

  @Test
  public void testChineseOOVs() {
    VocabularyWritable vocab = new VocabularyWritable();
    List<String> sentences = readInput(dir + "data/tokenizer/test/zh-test.tok.stemmed.stop");
    for (String token : sentences.get(3).split(" ")) {
      vocab.addOrGet(token);
    }
    vocab.addOrGet("1457");
    vocab.addOrGet("19");

    float[] zhExpectedOOVRates = {0.6666667f, 0.8666667f, 0.72727275f, 0f};     // all same since no stemming or stopword removal
    testOOV("zh", vocab, true, true, zhExpectedOOVRates);
    testOOV("zh", vocab, false, true, zhExpectedOOVRates);
View Full Code Here

Examples of edu.umd.hooka.VocabularyWritable

166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
    testOOV("zh", vocab, false, false, zhExpectedOOVRates);   
  }

  @Test
  public void testTurkishOOVs() {
    VocabularyWritable vocab = new VocabularyWritable();
    List<String> sentences = readInput(dir + "data/tokenizer/test/tr-test.tok.stemmed.stop");
    for (String token : sentences.get(3).split(" ")) {
      vocab.addOrGet(token);
    }
    vocab.addOrGet("ispanyol");
    vocab.addOrGet("isim");
    vocab.addOrGet("10");

    float[] trStopStemExpectedOOVRates = {0.85714287f, 1f, 0.6f, 0f};
    float[] trStopExpectedOOVRates = {1f, 1f, 0.8f, 0.5f};
    float[] trStemExpectedOOVRates = {0.85714287f, 1f, 0.71428573f, 0.33333334f};
    float[] trExpectedOOVRates = {1f, 1f, 0.85714287f, 0.6666667f};
View Full Code Here

Examples of edu.umd.hooka.VocabularyWritable

188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
    testOOV("tr", vocab, false, false, trExpectedOOVRates);   
  }

  @Test
  public void testArabicOOVs() {
    VocabularyWritable vocab = new VocabularyWritable();
    List<String> sentences = readInput(dir + "data/tokenizer/test/ar-test.tok.stemmed.stop");
    for (String token : sentences.get(0).split(" ")) {
      vocab.addOrGet(token);
    }
    vocab.addOrGet("2011");
    float[] arStopStemExpectedOOVRates = {0f, 1f, 0.8181818f, 1f};
    float[] arStopExpectedOOVRates = {0.6666667f, 1f, 0.8181818f, 1f};
    float[] arStemExpectedOOVRates = {0f, 1f, 0.85714287f, 1f};
    float[] arExpectedOOVRates = {0.6666667f, 1f, 0.85714287f, 1f};
View Full Code Here

Examples of edu.umd.hooka.VocabularyWritable

207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
    testOOV("ar", vocab, false, false, arExpectedOOVRates);
  }

  @Test
  public void testEnglishOOVs() {
    VocabularyWritable vocab = new VocabularyWritable();
    vocab.addOrGet("r.d.");
    vocab.addOrGet("craig");
    vocab.addOrGet("dictionari");
    vocab.addOrGet("polynesian");
    vocab.addOrGet("mytholog");
    vocab.addOrGet("greenwood");
    vocab.addOrGet("press");
    vocab.addOrGet("new");
    vocab.addOrGet("york");
    vocab.addOrGet("1989");
    vocab.addOrGet("24");
    vocab.addOrGet("26");
    vocab.addOrGet("english");
    vocab.addOrGet("tree");
    vocab.addOrGet("einbaum");

    float[] enStopStemExpectedOOVRates = {1f, 18/19f, 4/7.0f, 0f};
    float[] enStopExpectedOOVRates = {1f, 18/19f, 4/7.0f, 2/12f};
    float[] enStemExpectedOOVRates = {1f, 36/37f, 15/18.0f, 7/19f};
    float[] enExpectedOOVRates = {1f, 36/37f, 15/18.0f, 9/19f};
View Full Code Here

Examples of edu.umd.hooka.VocabularyWritable

49
50
51
52
53
54
55
56
57
58
59
    stopwords = readInput(fs, stopwordsFile);     
    String stemmedStopwordsFile = conf.get(Constants.StemmedStopwordList);
    stemmedStopwords = readInput(fs, stemmedStopwordsFile);
    isStopwordRemoval = !stopwords.isEmpty();
   
    VocabularyWritable vocab;
    try {
      vocab = (VocabularyWritable) HadoopAlign.loadVocab(new Path(conf.get(Constants.CollectionVocab)), fs);
      setVocab(vocab);
    } catch (Exception e) {
      LOG.warn("No vocabulary provided to tokenizer.");
View Full Code Here

Examples of edu.umd.hooka.VocabularyWritable

59
60
61
62
63
64
65
66
67
68
69
    String stopwordsFile = conf.get(Constants.StopwordList);
    stopwords = readInput(fs, stopwordsFile);     
    String stemmedStopwordsFile = conf.get(Constants.StemmedStopwordList);
    stemmedStopwords = readInput(fs, stemmedStopwordsFile);

    VocabularyWritable vocab;
    try {
      vocab = (VocabularyWritable) HadoopAlign.loadVocab(new Path(conf.get(Constants.CollectionVocab)), fs);
      setVocab(vocab);
    } catch (Exception e) {
      sLogger.warn("No vocabulary provided to tokenizer.");
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.