Package dkpro.similarity.ml

Examples of dkpro.similarity.ml.FeatureConfig

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
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
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
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
214
215
  {
    // Define the features
    List<FeatureConfig> configs = new ArrayList<FeatureConfig>();
   
    // String features
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              SimpleTextSimilarityResource.class,
              SimpleTextSimilarityResource.PARAM_MODE, "text",
              SimpleTextSimilarityResource.PARAM_TEXT_SIMILARITY_MEASURE, JaroSecondStringComparator.class.getName()),
        Document.class.getName(),
        false,
        "content/string",
        "Jaro"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              SimpleTextSimilarityResource.class,
              SimpleTextSimilarityResource.PARAM_MODE, "text",
              SimpleTextSimilarityResource.PARAM_TEXT_SIMILARITY_MEASURE, JaroWinklerSecondStringComparator.class.getName()),
        Document.class.getName(),
        false,
        "content/string",
        "JaroWinkler"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              SimpleTextSimilarityResource.class,
              SimpleTextSimilarityResource.PARAM_MODE, "text",
              SimpleTextSimilarityResource.PARAM_TEXT_SIMILARITY_MEASURE, MongeElkanSecondStringComparator.class.getName()),
        Document.class.getName(),
        false,
        "content/string",
        "MongeElkan"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              SimpleTextSimilarityResource.class,
              SimpleTextSimilarityResource.PARAM_MODE, "text",
              SimpleTextSimilarityResource.PARAM_TEXT_SIMILARITY_MEASURE, LevenshteinComparator.class.getName()),
        Document.class.getName(),
        false,
        "content/string",
        "Levenshtein"
        ));
   
//    configs.add(new FeatureConfig(
//        createExternalResourceDescription(
//              GreedyStringTilingMeasureResource.class,
//              GreedyStringTilingMeasureResource.PARAM_MIN_MATCH_LENGTH, "3"),
//        Document.class.getName(),
//        false,
//        "content/string",
//        "GreedyStringTiling_3"
//        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              SimpleTextSimilarityResource.class,
              SimpleTextSimilarityResource.PARAM_MODE, "text",
              SimpleTextSimilarityResource.PARAM_TEXT_SIMILARITY_MEASURE, LongestCommonSubsequenceComparator.class.getName()),
        Document.class.getName(),
        false,
        "content/string",
        "LongestCommonSubsequenceComparator"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              SimpleTextSimilarityResource.class,
              SimpleTextSimilarityResource.PARAM_MODE, "text",
              SimpleTextSimilarityResource.PARAM_TEXT_SIMILARITY_MEASURE, LongestCommonSubsequenceNormComparator.class.getName()),
        Document.class.getName(),
        false,
        "content/string",
        "LongestCommonSubsequenceNormComparator"
        ));

    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              SimpleTextSimilarityResource.class,
              SimpleTextSimilarityResource.PARAM_MODE, "text",
              SimpleTextSimilarityResource.PARAM_TEXT_SIMILARITY_MEASURE, LongestCommonSubstringComparator.class.getName()),
        Document.class.getName(),     
        false,
        "content/string",
        "LongestCommonSubstringComparator"
        ));

    // N-Grams
    for (int i = 1; i <= 5; i++)
    {
      configs.add(new FeatureConfig(
          createExternalResourceDescription(
                WordNGramContainmentResource.class,
                WordNGramContainmentResource.PARAM_N, new Integer(i).toString()),
          Token.class.getName(),
          false,
          "content/n-grams",
          "WordNGramContainmentMeasure_" + i
          ));
     
      configs.add(new FeatureConfig(
          createExternalResourceDescription(
                WordNGramJaccardResource.class,
                WordNGramJaccardResource.PARAM_N, new Integer(i).toString()),
          Token.class.getName(),
          false,
          "content/n-grams",
          "WordNGramJaccardMeasure_" + i
          ));
    }
   
    // ESA
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              VectorIndexSourceRelatednessResource.class,
              VectorIndexSourceRelatednessResource.PARAM_MODEL_LOCATION, "/home/danielb/Projekte/DKPro/Resources/ESA/VectorIndexes/wp_eng_lem_nc_c"),
        Lemma.class.getName() + "/value",
        false,
        "content/esa",
        "ESA_WP"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              VectorIndexSourceRelatednessResource.class,
              VectorIndexSourceRelatednessResource.PARAM_MODEL_LOCATION, "/home/danielb/Projekte/DKPro/Resources/ESA/VectorIndexes/wiktionary_en"),
        Lemma.class.getName() + "/value",
        false,
        "content/esa",
        "ESA_WK"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              VectorIndexSourceRelatednessResource.class,
              VectorIndexSourceRelatednessResource.PARAM_MODEL_LOCATION, "/home/danielb/Projekte/DKPro/Resources/ESA/VectorIndexes/wordnet_eng_lem_nc_c"),
        Lemma.class.getName() + "/value",
        false,
        "content/esa",
        "ESA_WN"
        ));
   
    // Structure
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              StopwordNGramContainmentMeasureResource.class,
              StopwordNGramContainmentMeasureResource.PARAM_N, "3",
              StopwordNGramContainmentMeasureResource.PARAM_STOPWORD_LIST_LOCATION, "/home/danielb/Projekte/Similarity/workspace/de.tudarmstadt.ukp.similarity-asl/de.tudarmstadt.ukp.similarity.dkpro.data-asl/src/main/resources/stopwords/stopwords-bnc-stamatatos.txt"),
        Lemma.class.getName() + "/value",
        false,
        "structure",
        "StopwordNGramContainmentMeasure_3_stamatatos"
        ));
   
    // Style
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              FunctionWordFrequenciesMeasureResource.class,
              FunctionWordFrequenciesMeasureResource.PARAM_FUNCTION_WORD_LIST_LOCATION, "/home/danielb/Projekte/Similarity/workspace/de.tudarmstadt.ukp.similarity-asl/de.tudarmstadt.ukp.similarity.dkpro.data-asl/src/main/resources/stopwords/function-words-mosteller-wallace.txt"),
        Lemma.class.getName() + "/value",
        false,
View Full Code Here
82
83
84
85
86
87
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
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
//        "custom",
//        "MyTextSimilarityMeasure_3"
//        ));
   
    // String features
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              GreedyStringTilingMeasureResource.class,
              GreedyStringTilingMeasureResource.PARAM_MIN_MATCH_LENGTH, "3"),
        Document.class.getName(),
        false,
        "string",
        "GreedyStringTiling_3"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              SimpleTextSimilarityResource.class,
              SimpleTextSimilarityResource.PARAM_MODE, "text",
              SimpleTextSimilarityResource.PARAM_TEXT_SIMILARITY_MEASURE, LongestCommonSubsequenceComparator.class.getName()),
        Document.class.getName(),
        false,
        "string",
        "LongestCommonSubsequenceComparator"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              SimpleTextSimilarityResource.class,
              SimpleTextSimilarityResource.PARAM_MODE, "text",
              SimpleTextSimilarityResource.PARAM_TEXT_SIMILARITY_MEASURE, LongestCommonSubsequenceNormComparator.class.getName()),
        Document.class.getName(),
        false,
        "string",
        "LongestCommonSubsequenceNormComparator"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              SimpleTextSimilarityResource.class,
              SimpleTextSimilarityResource.PARAM_MODE, "text",
              SimpleTextSimilarityResource.PARAM_TEXT_SIMILARITY_MEASURE, LongestCommonSubstringComparator.class.getName()),
        Document.class.getName(),     
        false,
        "string",
        "LongestCommonSubstringComparator"
        ));
   
    ngrams_n = new int[] { 2, 3, 4 };
    for (int n : ngrams_n)
    {
      configs.add(new FeatureConfig(
          createExternalResourceDescription(
              CharacterNGramResource.class,
              CharacterNGramResource.PARAM_N, new Integer(n).toString(),
              CharacterNGramResource.PARAM_IDF_VALUES_FILE, UTILS_DIR + "/character-ngrams-idf/" + mode.toString().toLowerCase() + "/" + n + "/" + dataset.toString() + ".txt"),
          Document.class.getName(),
          false,
          "n-grams",
          "CharacterNGramMeasure_" + n
          ));
    }
   
    ngrams_n = new int[] { 1, 2 };
    for (int n : ngrams_n)
    {
      configs.add(new FeatureConfig(
          createExternalResourceDescription(
                WordNGramContainmentResource.class,
                WordNGramContainmentResource.PARAM_N, new Integer(n).toString()),
          Token.class.getName(),
          true,
          "n-grams",
          "WordNGramContainmentMeasure_" + n + "_stopword-filtered"
          ));
    }
   
    ngrams_n = new int[] { 1, 3, 4 };
    for (int n : ngrams_n)
    {
      configs.add(new FeatureConfig(
          createExternalResourceDescription(
                WordNGramJaccardResource.class,
                WordNGramJaccardResource.PARAM_N, new Integer(n).toString()),
          Token.class.getName(),
          false,
          "n-grams",
          "WordNGramJaccardMeasure_" + n
          ));     
    }
   
    ngrams_n = new int[] { 2, 4 };
    for (int n : ngrams_n)
    {
      configs.add(new FeatureConfig(
          createExternalResourceDescription(
                WordNGramJaccardResource.class,
                WordNGramJaccardResource.PARAM_N, new Integer(n).toString()),
          Token.class.getName(),
          true,
View Full Code Here
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
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
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
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
214
215
  {
    // Define the features
    List<FeatureConfig> configs = new ArrayList<FeatureConfig>();
   
    // String features
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              SimpleTextSimilarityResource.class,
              SimpleTextSimilarityResource.PARAM_MODE, "text",
              SimpleTextSimilarityResource.PARAM_TEXT_SIMILARITY_MEASURE, JaroSecondStringComparator.class.getName()),
        Document.class.getName(),
        false,
        "content/string",
        "Jaro"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              SimpleTextSimilarityResource.class,
              SimpleTextSimilarityResource.PARAM_MODE, "text",
              SimpleTextSimilarityResource.PARAM_TEXT_SIMILARITY_MEASURE, JaroWinklerSecondStringComparator.class.getName()),
        Document.class.getName(),
        false,
        "content/string",
        "JaroWinkler"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              SimpleTextSimilarityResource.class,
              SimpleTextSimilarityResource.PARAM_MODE, "text",
              SimpleTextSimilarityResource.PARAM_TEXT_SIMILARITY_MEASURE, MongeElkanSecondStringComparator.class.getName()),
        Document.class.getName(),
        false,
        "content/string",
        "MongeElkan"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              SimpleTextSimilarityResource.class,
              SimpleTextSimilarityResource.PARAM_MODE, "text",
              SimpleTextSimilarityResource.PARAM_TEXT_SIMILARITY_MEASURE, LevenshteinComparator.class.getName()),
        Document.class.getName(),
        false,
        "content/string",
        "Levenshtein"
        ));
   
//    configs.add(new FeatureConfig(
//        createExternalResourceDescription(
//              GreedyStringTilingMeasureResource.class,
//              GreedyStringTilingMeasureResource.PARAM_MIN_MATCH_LENGTH, "3"),
//        Document.class.getName(),
//        false,
//        "content/string",
//        "GreedyStringTiling_3"
//        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              SimpleTextSimilarityResource.class,
              SimpleTextSimilarityResource.PARAM_MODE, "text",
              SimpleTextSimilarityResource.PARAM_TEXT_SIMILARITY_MEASURE, LongestCommonSubsequenceComparator.class.getName()),
        Document.class.getName(),
        false,
        "content/string",
        "LongestCommonSubsequenceComparator"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              SimpleTextSimilarityResource.class,
              SimpleTextSimilarityResource.PARAM_MODE, "text",
              SimpleTextSimilarityResource.PARAM_TEXT_SIMILARITY_MEASURE, LongestCommonSubsequenceNormComparator.class.getName()),
        Document.class.getName(),
        false,
        "content/string",
        "LongestCommonSubsequenceNormComparator"
        ));

    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              SimpleTextSimilarityResource.class,
              SimpleTextSimilarityResource.PARAM_MODE, "text",
              SimpleTextSimilarityResource.PARAM_TEXT_SIMILARITY_MEASURE, LongestCommonSubstringComparator.class.getName()),
        Document.class.getName(),     
        false,
        "content/string",
        "LongestCommonSubstringComparator"
        ));

    // N-Grams
    for (int i = 1; i <= 5; i++)
    {
      configs.add(new FeatureConfig(
          createExternalResourceDescription(
                WordNGramContainmentResource.class,
                WordNGramContainmentResource.PARAM_N, new Integer(i).toString()),
          Token.class.getName(),
          false,
          "content/n-grams",
          "WordNGramContainmentMeasure_" + i
          ));
     
      configs.add(new FeatureConfig(
          createExternalResourceDescription(
                WordNGramJaccardResource.class,
                WordNGramJaccardResource.PARAM_N, new Integer(i).toString()),
          Token.class.getName(),
          false,
          "content/n-grams",
          "WordNGramJaccardMeasure_" + i
          ));
    }
   
    // ESA
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              VectorIndexSourceRelatednessResource.class,
              VectorIndexSourceRelatednessResource.PARAM_MODEL_LOCATION, "/home/danielb/Projekte/DKPro/Resources/ESA/VectorIndexes/wp_eng_lem_nc_c"),
        Lemma.class.getName() + "/value",
        false,
        "content/esa",
        "ESA_WP"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              VectorIndexSourceRelatednessResource.class,
              VectorIndexSourceRelatednessResource.PARAM_MODEL_LOCATION, "/home/danielb/Projekte/DKPro/Resources/ESA/VectorIndexes/wiktionary_en"),
        Lemma.class.getName() + "/value",
        false,
        "content/esa",
        "ESA_WK"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              VectorIndexSourceRelatednessResource.class,
              VectorIndexSourceRelatednessResource.PARAM_MODEL_LOCATION, "/home/danielb/Projekte/DKPro/Resources/ESA/VectorIndexes/wordnet_eng_lem_nc_c"),
        Lemma.class.getName() + "/value",
        false,
        "content/esa",
        "ESA_WN"
        ));
   
    // Structure
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              StopwordNGramContainmentMeasureResource.class,
              StopwordNGramContainmentMeasureResource.PARAM_N, "3",
              StopwordNGramContainmentMeasureResource.PARAM_STOPWORD_LIST_LOCATION, "/home/danielb/Projekte/Similarity/workspace/de.tudarmstadt.ukp.similarity-asl/de.tudarmstadt.ukp.similarity.dkpro.data-asl/src/main/resources/stopwords/stopwords-bnc-stamatatos.txt"),
        Lemma.class.getName() + "/value",
        false,
        "structure",
        "StopwordNGramContainmentMeasure_3_stamatatos"
        ));
   
    // Style
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              FunctionWordFrequenciesMeasureResource.class,
              FunctionWordFrequenciesMeasureResource.PARAM_FUNCTION_WORD_LIST_LOCATION, "/home/danielb/Projekte/Similarity/workspace/de.tudarmstadt.ukp.similarity-asl/de.tudarmstadt.ukp.similarity.dkpro.data-asl/src/main/resources/stopwords/function-words-mosteller-wallace.txt"),
        Lemma.class.getName() + "/value",
        false,
View Full Code Here
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
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
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
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
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
        }
   
    WordIdfValuesGenerator.computeIdfScores(mode, dataset);
   
    // String features
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              GreedyStringTilingMeasureResource.class,
              GreedyStringTilingMeasureResource.PARAM_MIN_MATCH_LENGTH, "3"),
        Document.class.getName(),
        false,
        "string",
        "GreedyStringTiling_3"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              SimpleTextSimilarityResource.class,
              SimpleTextSimilarityResource.PARAM_MODE, "text",
              SimpleTextSimilarityResource.PARAM_TEXT_SIMILARITY_MEASURE, LongestCommonSubsequenceComparator.class.getName()),
        Document.class.getName(),
        false,
        "string",
        "LongestCommonSubsequenceComparator"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              SimpleTextSimilarityResource.class,
              SimpleTextSimilarityResource.PARAM_MODE, "text",
              SimpleTextSimilarityResource.PARAM_TEXT_SIMILARITY_MEASURE, LongestCommonSubsequenceNormComparator.class.getName()),
        Document.class.getName(),
        false,
        "string",
        "LongestCommonSubsequenceNormComparator"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              SimpleTextSimilarityResource.class,
              SimpleTextSimilarityResource.PARAM_MODE, "text",
              SimpleTextSimilarityResource.PARAM_TEXT_SIMILARITY_MEASURE, LongestCommonSubstringComparator.class.getName()),
        Document.class.getName(),     
        false,
        "string",
        "LongestCommonSubstringComparator"
        ));
   
    ngrams_n = new int[] { 2, 3, 4 };
    for (int n : ngrams_n)
    {
      configs.add(new FeatureConfig(
          createExternalResourceDescription(
              CharacterNGramResource.class,
              CharacterNGramResource.PARAM_N, new Integer(n).toString(),
              CharacterNGramResource.PARAM_IDF_VALUES_FILE, UTILS_DIR + "/character-ngrams-idf/" + mode.toString().toLowerCase() + "/" + n + "/" + dataset.toString() + ".txt"),
          Document.class.getName(),
          false,
          "n-grams",
          "CharacterNGramMeasure_" + n
          ));
    }
   
    ngrams_n = new int[] { 1, 2 };
    for (int n : ngrams_n)
    {
      configs.add(new FeatureConfig(
          createExternalResourceDescription(
                WordNGramContainmentResource.class,
                WordNGramContainmentResource.PARAM_N, new Integer(n).toString()),
          Token.class.getName(),
          true,
          "n-grams",
          "WordNGramContainmentMeasure_" + n + "_stopword-filtered"
          ));
    }
   
    ngrams_n = new int[] { 1, 3, 4 };
    for (int n : ngrams_n)
    {
      configs.add(new FeatureConfig(
          createExternalResourceDescription(
                WordNGramJaccardResource.class,
                WordNGramJaccardResource.PARAM_N, new Integer(n).toString()),
          Token.class.getName(),
          false,
          "n-grams",
          "WordNGramJaccardMeasure_" + n
          ));     
    }
   
    ngrams_n = new int[] { 2, 4 };
    for (int n : ngrams_n)
    {
      configs.add(new FeatureConfig(
          createExternalResourceDescription(
                WordNGramJaccardResource.class,
                WordNGramJaccardResource.PARAM_N, new Integer(n).toString()),
          Token.class.getName(),
          true,
          "n-grams",
          "WordNGramJaccardMeasure_" + n + "_stopword-filtered"
          ));     
    }
   
    /* TODO: If you plan to use the following measures, make sure that you have the
     * necessary resources installed.
     * Details on obtaining and installing them can be found here:
     * http://code.google.com/p/dkpro-similarity-asl/wiki/SettingUpTheResources
     */
   
    // Resnik word similarity measure, aggregated according to Mihalcea et al. (2006)
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              MCS06AggregateResource.class,
              MCS06AggregateResource.PARAM_TERM_SIMILARITY_RESOURCE, createExternalResourceDescription(
                  ResnikRelatednessResource.class,
                  ResnikRelatednessResource.PARAM_RESOURCE_NAME, "wordnet",
                  ResnikRelatednessResource.PARAM_RESOURCE_LANGUAGE, "en"
                  ),
              MCS06AggregateResource.PARAM_IDF_VALUES_FILE, UTILS_DIR + "/word-idf/" + mode.toString().toLowerCase() + "/" + dataset.toString() + ".txt"),
        Lemma.class.getName() + "/value",
        false,
        "word-sim",
        "MCS06_Resnik_WordNet"
        ));
   
    // Lexical Substitution System wrapper for
    // Resnik word similarity measure, aggregated according to Mihalcea et al. (2006)
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
            TWSISubstituteWrapperResource.class,
            TWSISubstituteWrapperResource.PARAM_TEXT_SIMILARITY_RESOURCE, createExternalResourceDescription(
                  MCS06AggregateResource.class,
                  MCS06AggregateResource.PARAM_TERM_SIMILARITY_RESOURCE, createExternalResourceDescription(
                      ResnikRelatednessResource.class,
                      ResnikRelatednessResource.PARAM_RESOURCE_NAME, "wordnet",
                      ResnikRelatednessResource.PARAM_RESOURCE_LANGUAGE, "en"
                      ),
                  MCS06AggregateResource.PARAM_IDF_VALUES_FILE, UTILS_DIR + "/word-idf/" + mode.toString().toLowerCase() + "/" + dataset.toString() + ".txt")),
        "word-sim",
        "TWSI_MCS06_Resnik_WordNet"
        ));
   
    // Bing SMT wrapper for
    // Resnik word similarity measure, aggregated according to Mihalcea et al. (2006)
    // In our original system, we used MOSES for machine translation.
//    configs.add(new FeatureConfig(
//        createExternalResourceDescription(
//            BingSMTWrapperResource.class,
//            BingSMTWrapperResource.PARAM_TEXT_SIMILARITY_RESOURCE, createExternalResourceDescription(
//                  MCS06AggregateResource.class,
//                  MCS06AggregateResource.PARAM_TERM_SIMILARITY_RESOURCE, createExternalResourceDescription(
//                      ResnikRelatednessResource.class,
//                      ResnikRelatednessResource.PARAM_RESOURCE_NAME, "wordnet",
//                      ResnikRelatednessResource.PARAM_RESOURCE_LANGUAGE, "en"
//                      ),
//                  MCS06AggregateResource.PARAM_IDF_VALUES_FILE, UTILS_DIR + "/word-idf/" + mode.toString().toLowerCase() + "/" + dataset.toString() + ".txt"
//                  ),
//            BingSMTWrapperResource.PARAM_ORIGINAL_LANGUAGE, Language.EN.toString(),
//            BingSMTWrapperResource.PARAM_BRIDGE_LANGUAGE, Language.ES.toString()),
//        "word-sim",
//        "BingSMT_MCS06_Resnik_WordNet"
//        ));
       
    // Explicit Semantic Analysis
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              VectorIndexSourceRelatednessResource.class,
              VectorIndexSourceRelatednessResource.PARAM_MODEL_LOCATION, DkproContext.getContext().getWorkspace().getAbsolutePath() + "/ESA/VectorIndexes/wordnet_eng_lem_nc_c"),
        Lemma.class.getName() + "/value",
        false,
        "esa",
        "ESA_WordNet"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              VectorIndexSourceRelatednessResource.class,
              VectorIndexSourceRelatednessResource.PARAM_MODEL_LOCATION, DkproContext.getContext().getWorkspace().getAbsolutePath() + "/ESA/VectorIndexes/wiktionary_en"),
        Lemma.class.getName() + "/value",
        false,
View Full Code Here
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
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
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
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
    WordIdfValuesGenerator.computeIdfScores(dataset);
   
    // ** FEATURES **
   
    // String features
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              GreedyStringTilingMeasureResource.class,
              GreedyStringTilingMeasureResource.PARAM_MIN_MATCH_LENGTH, "3"),
        Document.class.getName(),
        false,
        "string",
        "GreedyStringTiling_3"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              SimpleTextSimilarityResource.class,
              SimpleTextSimilarityResource.PARAM_MODE, "text",
              SimpleTextSimilarityResource.PARAM_TEXT_SIMILARITY_MEASURE, LongestCommonSubsequenceComparator.class.getName()),
        Document.class.getName(),
        false,
        "string",
        "LongestCommonSubsequenceComparator"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              SimpleTextSimilarityResource.class,
              SimpleTextSimilarityResource.PARAM_MODE, "text",
              SimpleTextSimilarityResource.PARAM_TEXT_SIMILARITY_MEASURE, LongestCommonSubsequenceNormComparator.class.getName()),
        Document.class.getName(),
        false,
        "string",
        "LongestCommonSubsequenceNormComparator"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              SimpleTextSimilarityResource.class,
              SimpleTextSimilarityResource.PARAM_MODE, "text",
              SimpleTextSimilarityResource.PARAM_TEXT_SIMILARITY_MEASURE, LongestCommonSubstringComparator.class.getName()),
        Document.class.getName(),     
        false,
        "string",
        "LongestCommonSubstringComparator"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              CosineSimilarityResource.class),
        Lemma.class.getName() + "/value",
        false,
        "string",
        "CosineSimilarity"
        ));
   
    // n-gram models
    ngrams_n = new int[] { 2, 3, 4, 5, 6, 7, 8, 9, 10 };
    for (int n : ngrams_n)
    {
      configs.add(new FeatureConfig(
          createExternalResourceDescription(
              CharacterNGramResource.class,
              CharacterNGramResource.PARAM_N, new Integer(n).toString(),
              CharacterNGramResource.PARAM_IDF_VALUES_FILE, UTILS_DIR + "/character-ngrams-idf/" + n + "/" + dataset.toString() + ".txt"),
          Document.class.getName(),
          false,
          "n-grams",
          "CharacterNGramMeasure_" + n
          ));
    }
   
    ngrams_n = new int[] { 1, 2, 3, 4, 5 };
    for (int n : ngrams_n)
    {
      configs.add(new FeatureConfig(
          createExternalResourceDescription(
                WordNGramContainmentResource.class,
                WordNGramContainmentResource.PARAM_N, new Integer(n).toString()),
          Token.class.getName(),
          false,
          "n-grams",
          "WordNGramContainmentMeasure_" + n
          ));
    }
   
    ngrams_n = new int[] { 1, 2, 3, 4, 5 };
    for (int n : ngrams_n)
    {
      configs.add(new FeatureConfig(
          createExternalResourceDescription(
                WordNGramContainmentResource.class,
                WordNGramContainmentResource.PARAM_N, new Integer(n).toString()),
          Token.class.getName(),
          true,
          "n-grams",
          "WordNGramContainmentMeasure_" + n + "_stopword-filtered"
          ));
    }
   
    ngrams_n = new int[] { 1, 2, 3, 4, 5 };
    for (int n : ngrams_n)
    {
      configs.add(new FeatureConfig(
          createExternalResourceDescription(
                WordNGramJaccardResource.class,
                WordNGramJaccardResource.PARAM_N, new Integer(n).toString()),
          Token.class.getName(),
          false,
          "n-grams",
          "WordNGramJaccardMeasure_" + n
          ));     
    }
   
    ngrams_n = new int[] { 1, 2, 3, 4, 5 };
    for (int n : ngrams_n)
    {
      configs.add(new FeatureConfig(
          createExternalResourceDescription(
                WordNGramJaccardResource.class,
                WordNGramJaccardResource.PARAM_N, new Integer(n).toString()),
          Token.class.getName(),
          true,
          "n-grams",
          "WordNGramJaccardMeasure_" + n + "_stopword-filtered"
          ));     
    }
   
    /* TODO: If you plan to use the following measures, make sure that you have the
     * necessary resources installed.
     * Details on obtaining and installing them can be found here:
     * http://code.google.com/p/dkpro-similarity-asl/wiki/SettingUpTheResources
     */
   
    // Resnik word similarity measure, aggregated according to Mihalcea et al. (2006)
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              MCS06AggregateResource.class,
              MCS06AggregateResource.PARAM_TERM_SIMILARITY_RESOURCE, createExternalResourceDescription(
                  ResnikRelatednessResource.class,
                  ResnikRelatednessResource.PARAM_RESOURCE_NAME, "wordnet",
                  ResnikRelatednessResource.PARAM_RESOURCE_LANGUAGE, "en"
                  ),
              MCS06AggregateResource.PARAM_IDF_VALUES_FILE, UTILS_DIR + "/word-idf/" + dataset.toString() + ".txt"),
        Lemma.class.getName() + "/value",
        false,
        "word-sim",
        "MCS06_Resnik_WordNet"
        ));
   
    // Lexical Substitution System wrapper for
    // Resnik word similarity measure, aggregated according to Mihalcea et al. (2006)
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
            TWSISubstituteWrapperResource.class,
            TWSISubstituteWrapperResource.PARAM_TEXT_SIMILARITY_RESOURCE, createExternalResourceDescription(
                  MCS06AggregateResource.class,
                  MCS06AggregateResource.PARAM_TERM_SIMILARITY_RESOURCE, createExternalResourceDescription(
                      ResnikRelatednessResource.class,
                      ResnikRelatednessResource.PARAM_RESOURCE_NAME, "wordnet",
                      ResnikRelatednessResource.PARAM_RESOURCE_LANGUAGE, "en"
                      ),
                  MCS06AggregateResource.PARAM_IDF_VALUES_FILE, UTILS_DIR + "/word-idf/" + dataset.toString() + ".txt")),
        "word-sim",
        "TWSI_MCS06_Resnik_WordNet"
        ));
       
    // Explicit Semantic Analysis
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              VectorIndexSourceRelatednessResource.class,
              VectorIndexSourceRelatednessResource.PARAM_MODEL_LOCATION, DkproContext.getContext().getWorkspace().getAbsolutePath() + "/ESA/VectorIndexes/wordnet_eng_lem_nc_c"),
        Lemma.class.getName() + "/value",
        false,
        "esa",
        "ESA_WordNet"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              VectorIndexSourceRelatednessResource.class,
              VectorIndexSourceRelatednessResource.PARAM_MODEL_LOCATION, DkproContext.getContext().getWorkspace().getAbsolutePath() + "/ESA/VectorIndexes/wiktionary_en"),
        Lemma.class.getName() + "/value",
        false,
        "esa",
        "ESA_Wiktionary"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              VectorIndexSourceRelatednessResource.class,
              VectorIndexSourceRelatednessResource.PARAM_MODEL_LOCATION, DkproContext.getContext().getWorkspace().getAbsolutePath() + "/ESA/VectorIndexes/wp_eng_lem_nc_c"),
        Lemma.class.getName() + "/value",
        false,
        "esa",
        "ESA_Wikipedia"
        ));
   
    // LSA
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
              LatentSemanticAnalysisResource.class,
              LatentSemanticAnalysisResource.PARAM_INPUT_DIR, UTILS_DIR + "/plaintexts/" + dataset.toString()),
        Token.class.getName(),
        false,
        "lsa",
        "LSA"
        ));
   
    // ** Structure **
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
            TokenPairDistanceResource.class),
        Token.class.getName(),
        false,
        "structure",
        "TokenPairDistanceMeasure"
        ));
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
            TokenPairOrderingResource.class),
        Token.class.getName(),
        false,
        "structure",
        "TokenPairOrderingMeasure"
        ));
   
    for (int n = 2; n <= 7; n++) {
            configs.add(new FeatureConfig(
          createExternalResourceDescription(
              StopwordNGramContainmentMeasureResource.class,
              StopwordNGramContainmentMeasureResource.PARAM_N, new Integer(n).toString(),
              StopwordNGramContainmentMeasureResource.PARAM_STOPWORD_LIST_LOCATION, "classpath:/stopwords/stopwords_english_punctuation.txt"),
          Token.class.getName(),
          false,
          "structure",
          "StopwordNGramContainmentMeasure_" + n + "_english-punctuation"
          ));
        }
   
    for (int n = 2; n <= 7; n++) {
            configs.add(new FeatureConfig(
          createExternalResourceDescription(
              StopwordNGramContainmentMeasureResource.class,
              StopwordNGramContainmentMeasureResource.PARAM_N, new Integer(n).toString(),
              StopwordNGramContainmentMeasureResource.PARAM_STOPWORD_LIST_LOCATION, "classpath:/stopwords/function-words-mosteller-wallace.txt"),
          Token.class.getName(),
          false,
          "structure",
          "StopwordNGramContainmentMeasure_" + n + "_mosteller-wallace"
          ));
        }
   
    for (int n = 2; n <= 7; n++) {
            configs.add(new FeatureConfig(
          createExternalResourceDescription(
              StopwordNGramContainmentMeasureResource.class,
              StopwordNGramContainmentMeasureResource.PARAM_N, new Integer(n).toString(),
              StopwordNGramContainmentMeasureResource.PARAM_STOPWORD_LIST_LOCATION, "classpath:/stopwords/stopwords-bnc-stamatatos.txt"),
          Token.class.getName(),
          false,
          "structure",
          "StopwordNGramContainmentMeasure_" + n + "_stamatatos"
          ));
        }
   
    for (int n = 1; n <= 7; n++)
    {
      configs.add(new FeatureConfig(
          createExternalResourceDescription(
              PosNGramJaccardResource.class,
              PosNGramJaccardResource.PARAM_N, new Integer(n).toString()),
          POS.class.getName(),
          false,
          "structure",
          "PosNGramJaccardMeasure_" + n
          ));
    }
     
    for (int n = 1; n <= 7; n++)
    {
      configs.add(new FeatureConfig(
          createExternalResourceDescription(
              PosNGramContainmentResource.class,
              PosNGramContainmentResource.PARAM_N, new Integer(n).toString()),
          POS.class.getName(),
          false,
          "structure",
          "PosNGramContainmentMeasure_" + n
          ));
    }
   
    // ** Style **

    configs.add(new FeatureConfig(
        createExternalResourceDescription(
            MTLDResource.class),
        null,
        false,
        "style",
        "MTLDComparator"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
            TypeTokenRatioResource.class),
        null,
        false,
        "style",
        "TypeTokenRatioComparator"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
            AvgCharactersPerTokenResource.class),
        null,
        false,
        "style",
        "AvgCharactersPerTokenComparator"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
            AvgTokensPerSentenceResource.class),
        null,
        false,
        "style",
        "AvgTokensPerSentenceComparator"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
            SentenceRatioResource.class),
        null,
        false,
        "style",
        "SentenceRatioComparator"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
            TokenRatioResource.class),
        null,
        false,
        "style",
        "TokenRatioComparator"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
            FunctionWordFrequenciesMeasureResource.class,
            FunctionWordFrequenciesMeasureResource.PARAM_FUNCTION_WORD_LIST_LOCATION, "classpath:/stopwords/stopwords_english_punctuation.txt"),
        Token.class.getName(),
        false,
        "style",
        "FunctionWordFrequenciesMeasure_english-punctuation"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
            FunctionWordFrequenciesMeasureResource.class,
            FunctionWordFrequenciesMeasureResource.PARAM_FUNCTION_WORD_LIST_LOCATION, "classpath:/stopwords/function-words-mosteller-wallace.txt"),
        Token.class.getName(),
        false,
        "style",
        "FunctionWordFrequenciesMeasure_mosteller-wallace"
        ));
   
    configs.add(new FeatureConfig(
        createExternalResourceDescription(
            FunctionWordFrequenciesMeasureResource.class,
            FunctionWordFrequenciesMeasureResource.PARAM_FUNCTION_WORD_LIST_LOCATION, "classpath:/stopwords/stopwords-bnc-stamatatos.txt"),
        Token.class.getName(),
        false,
View Full Code Here
TOP

Related Classes of dkpro.similarity.ml.FeatureConfig

  • dkpro.similarity.example.ml.mm09.FeatureGenerationTest
  • dkpro.similarity.example.ml.mm09.FeatureGenerationTrain
  • dkpro.similarity.experiments.rte.FeatureGeneration
  • dkpro.similarity.experiments.sts2013.FeatureGeneration
  • dkpro.similarity.experiments.sts2013baseline.FeatureGeneration
    • 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.