Changes

              
    

          
          
        
        

            
f
1
{
f
1
{
            
2
  "Observaciones": {
2
  "Observaciones": {
            
3
    "en": "Recommended citation for this dataset: Bartolom\u00e9 
3
    "en": "Recommended citation for this dataset: Bartolom\u00e9 
            
4
Rodr\u00edguez, Roc\u00edo; Terroba Reinares, Ana Rosa; 
4
Rodr\u00edguez, Roc\u00edo; Terroba Reinares, Ana Rosa; 
            
5
Campillos-Llanos, Leonardo; 2024; CLARA-MeD simplified sentences 
5
Campillos-Llanos, Leonardo; 2024; CLARA-MeD simplified sentences 
            
6
[Dataset]; DIGITAL.CSIC; https://doi.org/10.20350/digitalCSIC/16110",
6
[Dataset]; DIGITAL.CSIC; https://doi.org/10.20350/digitalCSIC/16110",
            
7
    "es": "Cita recomendada para este dataset: Bartolom\u00e9 
7
    "es": "Cita recomendada para este dataset: Bartolom\u00e9 
            
8
Rodr\u00edguez, Roc\u00edo; Terroba Reinares, Ana Rosa; 
8
Rodr\u00edguez, Roc\u00edo; Terroba Reinares, Ana Rosa; 
            
9
Campillos-Llanos, Leonardo; 2024; CLARA-MeD simplified sentences 
9
Campillos-Llanos, Leonardo; 2024; CLARA-MeD simplified sentences 
            
10
[Dataset]; DIGITAL.CSIC; https://doi.org/10.20350/digitalCSIC/16110"
10
[Dataset]; DIGITAL.CSIC; https://doi.org/10.20350/digitalCSIC/16110"
            
11
  },
11
  },
            
12
  "author": null,
12
  "author": null,
            
13
  "author_email": null,
13
  "author_email": null,
            
14
  "autor": {
14
  "autor": {
            
15
    "en": [
15
    "en": [
            
16
      "Leonardo Campillos-Llanos",
16
      "Leonardo Campillos-Llanos",
            
n
17
      "Roc\u00edo Bartolom\u00e9 Rodr\u00edguez",
n
17
      "Roc\u00edo Bartolom\u00e9 Rodr\u00edguez"
            
18
      "Ana Rosa Terroba Reinares"

            
19
    ],
18
    ],
            
20
    "es": [
19
    "es": [
            
21
      "Leonardo Campillos-Llanos",
20
      "Leonardo Campillos-Llanos",
            
22
      "Roc\u00edo Bartolom\u00e9 Rodr\u00edguez",
21
      "Roc\u00edo Bartolom\u00e9 Rodr\u00edguez",
            
23
      "Ana Rosa Terroba Reinares"
22
      "Ana Rosa Terroba Reinares"
            
24
    ]
23
    ]
            
25
  },
24
  },
            
26
  "conforms_to": [],
25
  "conforms_to": [],
            
27
  "coverage_new": {
26
  "coverage_new": {
            
28
    "1": {
27
    "1": {
            
29
      "from": "2009-01-04T00:00:00",
28
      "from": "2009-01-04T00:00:00",
            
30
      "to": "2023-12-04T00:00:00"
29
      "to": "2023-12-04T00:00:00"
            
31
    }
30
    }
            
32
  },
31
  },
            
33
  "creator_user_id": "196556b3-e0c4-4c51-a9e6-f51cc752bc37",
32
  "creator_user_id": "196556b3-e0c4-4c51-a9e6-f51cc752bc37",
            
34
  "description": {
33
  "description": {
            
35
    "en": "This dataset contains 1200 manually simplified sentences 
34
    "en": "This dataset contains 1200 manually simplified sentences 
            
36
(144 019 tokens) from clinical trials in Spanish. A total of 1040 
35
(144 019 tokens) from clinical trials in Spanish. A total of 1040 
            
37
announcements from the European Clinical Trials Register (EudraCT) 
36
announcements from the European Clinical Trials Register (EudraCT) 
            
38
were analyzed to select sentences with ambiguities or exceeding 25 
37
were analyzed to select sentences with ambiguities or exceeding 25 
            
39
words. Simplification criteria were devised in an annotation 
38
words. Simplification criteria were devised in an annotation 
            
40
guideline, which is released publicly along the dataset.\r\n\r\nThis 
39
guideline, which is released publicly along the dataset.\r\n\r\nThis 
            
41
resource was collected in the CLARA-MeD project, with the goal of 
40
resource was collected in the CLARA-MeD project, with the goal of 
            
42
simplifying medical texts in the Spanish language and reduce the 
41
simplifying medical texts in the Spanish language and reduce the 
            
43
language barrier to patient's informed decision making. In particular, 
42
language barrier to patient's informed decision making. In particular, 
            
44
the project aims at developing linguistic resources for automatic 
43
the project aims at developing linguistic resources for automatic 
            
45
medical term simplification in Spanish; and conducting experiments in 
44
medical term simplification in Spanish; and conducting experiments in 
            
46
automatic text simplification.",
45
automatic text simplification.",
            
47
    "es": "This dataset contains 1200 manually simplified sentences 
46
    "es": "This dataset contains 1200 manually simplified sentences 
            
48
(144 019 tokens) from clinical trials in Spanish. A total of 1040 
47
(144 019 tokens) from clinical trials in Spanish. A total of 1040 
            
49
announcements from the European Clinical Trials Register (EudraCT) 
48
announcements from the European Clinical Trials Register (EudraCT) 
            
50
were analyzed to select sentences with ambiguities or exceeding 25 
49
were analyzed to select sentences with ambiguities or exceeding 25 
            
51
words. Simplification criteria were devised in an annotation 
50
words. Simplification criteria were devised in an annotation 
            
52
guideline, which is released publicly along the dataset.\r\n\r\nThis 
51
guideline, which is released publicly along the dataset.\r\n\r\nThis 
            
53
resource was collected in the CLARA-MeD project, with the goal of 
52
resource was collected in the CLARA-MeD project, with the goal of 
            
54
simplifying medical texts in the Spanish language and reduce the 
53
simplifying medical texts in the Spanish language and reduce the 
            
55
language barrier to patient's informed decision making. In particular, 
54
language barrier to patient's informed decision making. In particular, 
            
56
the project aims at developing linguistic resources for automatic 
55
the project aims at developing linguistic resources for automatic 
            
57
medical term simplification in Spanish; and conducting experiments in 
56
medical term simplification in Spanish; and conducting experiments in 
            
58
automatic text simplification."
57
automatic text simplification."
            
59
  },
58
  },
            
60
  "groups": [
59
  "groups": [
            
61
    {
60
    {
            
62
      "description": "",
61
      "description": "",
            
63
      "display_name": "Terminolog\u00eda",
62
      "display_name": "Terminolog\u00eda",
            
64
      "id": "f21d51d4-df60-44f9-ad1f-60f1d5ca24d2",
63
      "id": "f21d51d4-df60-44f9-ad1f-60f1d5ca24d2",
            
65
      "image_display_url": 
64
      "image_display_url": 
            
66
.cchs.csic.es/uploads/group/2024-09-27-062713.009717Terminologia.png",
65
.cchs.csic.es/uploads/group/2024-09-27-062713.009717Terminologia.png",
            
67
      "name": "terminologia",
66
      "name": "terminologia",
            
68
      "title": "Terminolog\u00eda"
67
      "title": "Terminolog\u00eda"
            
69
    }
68
    }
            
70
  ],
69
  ],
            
71
  "id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77",
70
  "id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77",
            
72
  "identifier": "https://doi.org/10.20350/digitalCSIC/16110",
71
  "identifier": "https://doi.org/10.20350/digitalCSIC/16110",
            
73
  "international_spatial_translated": {
72
  "international_spatial_translated": {
            
74
    "en": "Europe (data from EudraCT)",
73
    "en": "Europe (data from EudraCT)",
            
75
    "es": "Europa (datos de EudraCT)"
74
    "es": "Europa (datos de EudraCT)"
            
76
  },
75
  },
            
77
  "isopen": false,
76
  "isopen": false,
            
78
  "issued_date": "2024-02-09T00:00:00",
77
  "issued_date": "2024-02-09T00:00:00",
            
79
  "language": [
78
  "language": [
            
80
    "es",
79
    "es",
            
81
    "en"
80
    "en"
            
82
  ],
81
  ],
            
83
  "license_id": "https://creativecommons.org/licenses/by-nc-sa/4.0/",
82
  "license_id": "https://creativecommons.org/licenses/by-nc-sa/4.0/",
            
84
  "license_title": 
83
  "license_title": 
            
85
"https://creativecommons.org/licenses/by-nc-sa/4.0/",
84
"https://creativecommons.org/licenses/by-nc-sa/4.0/",
            
86
  "maintainer": null,
85
  "maintainer": null,
            
87
  "maintainer_email": null,
86
  "maintainer_email": null,
            
88
  "metadata_created": "2024-05-30T15:57:14.431217",
87
  "metadata_created": "2024-05-30T15:57:14.431217",
            
t
89
  "metadata_modified": "2025-03-04T15:17:51.364123",
t
88
  "metadata_modified": "2025-03-04T15:18:34.384571",
            
90
  "multilingual_tags": {
89
  "multilingual_tags": {
            
91
    "en": [
90
    "en": [
            
92
      "Biomedical natural language processing",
91
      "Biomedical natural language processing",
            
93
      "Parallel sentences",
92
      "Parallel sentences",
            
94
      "Medical text simplification"
93
      "Medical text simplification"
            
95
    ]
94
    ]
            
96
  },
95
  },
            
97
  "name": "clara-med-simplified-sentences",
96
  "name": "clara-med-simplified-sentences",
            
98
  "notes": null,
97
  "notes": null,
            
99
  "num_resources": 3,
98
  "num_resources": 3,
            
100
  "num_tags": 0,
99
  "num_tags": 0,
            
101
  "organization": {
100
  "organization": {
            
102
    "approval_status": "approved",
101
    "approval_status": "approved",
            
103
    "created": "2023-09-25T12:13:42.172869",
102
    "created": "2023-09-25T12:13:42.172869",
            
104
    "description": "El Instituto de Lengua, Literatura y 
103
    "description": "El Instituto de Lengua, Literatura y 
            
105
Antropolog\u00eda, ILLA (CSIC) tiene como objetivo primordial la 
104
Antropolog\u00eda, ILLA (CSIC) tiene como objetivo primordial la 
            
106
investigaci\u00f3n del patrimonio cultural hisp\u00e1nico en su triple 
105
investigaci\u00f3n del patrimonio cultural hisp\u00e1nico en su triple 
            
107
dimensi\u00f3n antropol\u00f3gica, ling\u00fc\u00edstica y 
106
dimensi\u00f3n antropol\u00f3gica, ling\u00fc\u00edstica y 
            
108
literaria.",
107
literaria.",
            
109
    "id": "fc47e531-a165-4eac-8fc7-34342a3a38ff",
108
    "id": "fc47e531-a165-4eac-8fc7-34342a3a38ff",
            
110
    "image_url": "2023-09-25-101342.167134illa0.png",
109
    "image_url": "2023-09-25-101342.167134illa0.png",
            
111
    "is_organization": true,
110
    "is_organization": true,
            
112
    "name": "instituto-de-lengua-literatura-y-antropologia-illa-csic",
111
    "name": "instituto-de-lengua-literatura-y-antropologia-illa-csic",
            
113
    "state": "active",
112
    "state": "active",
            
114
    "title": "Instituto de Lengua, Literatura y Antropolog\u00eda 
113
    "title": "Instituto de Lengua, Literatura y Antropolog\u00eda 
            
115
(ILLA), CSIC",
114
(ILLA), CSIC",
            
116
    "type": "organization"
115
    "type": "organization"
            
117
  },
116
  },
            
118
  "owner_org": "fc47e531-a165-4eac-8fc7-34342a3a38ff",
117
  "owner_org": "fc47e531-a165-4eac-8fc7-34342a3a38ff",
            
119
  "private": false,
118
  "private": false,
            
120
  "proyecto": {
119
  "proyecto": {
            
121
    "es": [
120
    "es": [
            
122
      "PID2020-116001RA-C33"
121
      "PID2020-116001RA-C33"
            
123
    ]
122
    ]
            
124
  },
123
  },
            
125
  "publisher": "b627d71d-2315-4e75-afc9-897da84459f0",
124
  "publisher": "b627d71d-2315-4e75-afc9-897da84459f0",
            
126
  "reference": [
125
  "reference": [
            
127
    "https://github.com/lcampillos/CLARA-MeD/"
126
    "https://github.com/lcampillos/CLARA-MeD/"
            
128
  ],
127
  ],
            
129
  "relationships_as_object": [],
128
  "relationships_as_object": [],
            
130
  "relationships_as_subject": [],
129
  "relationships_as_subject": [],
            
131
  "resources": [
130
  "resources": [
            
132
    {
131
    {
            
133
      "byte_size": "7,32 kB",
132
      "byte_size": "7,32 kB",
            
134
      "cache_last_updated": null,
133
      "cache_last_updated": null,
            
135
      "cache_url": null,
134
      "cache_url": null,
            
136
      "created": "2024-05-30T15:58:24.249419",
135
      "created": "2024-05-30T15:58:24.249419",
            
137
      "datastore_active": false,
136
      "datastore_active": false,
            
138
      "description": null,
137
      "description": null,
            
139
      "format": "txt",
138
      "format": "txt",
            
140
      "hash": "",
139
      "hash": "",
            
141
      "id": "30dfbb45-e41a-4c6e-bcdc-a4af2f040715",
140
      "id": "30dfbb45-e41a-4c6e-bcdc-a4af2f040715",
            
142
      "last_modified": null,
141
      "last_modified": null,
            
143
      "metadata_modified": "2024-05-30T15:58:24.421759",
142
      "metadata_modified": "2024-05-30T15:58:24.421759",
            
144
      "mimetype": "text/plain",
143
      "mimetype": "text/plain",
            
145
      "mimetype_inner": null,
144
      "mimetype_inner": null,
            
146
      "name": "README_CLARAMED_sentences.txt\t",
145
      "name": "README_CLARAMED_sentences.txt\t",
            
147
      "name_translated": {
146
      "name_translated": {
            
148
        "en": "README_CLARAMED_sentences.txt\t",
147
        "en": "README_CLARAMED_sentences.txt\t",
            
149
        "es": "README_CLARAMED_sentences.txt\t"
148
        "es": "README_CLARAMED_sentences.txt\t"
            
150
      },
149
      },
            
151
      "package_id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77",
150
      "package_id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77",
            
152
      "position": 0,
151
      "position": 0,
            
153
      "resource_identifier": "",
152
      "resource_identifier": "",
            
154
      "resource_relation": [],
153
      "resource_relation": [],
            
155
      "resource_relation-1": "",
154
      "resource_relation-1": "",
            
156
      "resource_type": null,
155
      "resource_type": null,
            
157
      "size": null,
156
      "size": null,
            
158
      "state": "active",
157
      "state": "active",
            
159
      "url": 
158
      "url": 
            
160
gital.csic.es/bitstream/10261/346579/6/README_CLARAMED_sentences.txt",
159
gital.csic.es/bitstream/10261/346579/6/README_CLARAMED_sentences.txt",
            
161
      "url_type": null
160
      "url_type": null
            
162
    },
161
    },
            
163
    {
162
    {
            
164
      "byte_size": "981,11 kB",
163
      "byte_size": "981,11 kB",
            
165
      "cache_last_updated": null,
164
      "cache_last_updated": null,
            
166
      "cache_url": null,
165
      "cache_url": null,
            
167
      "created": "2024-05-30T15:57:45.357301",
166
      "created": "2024-05-30T15:57:45.357301",
            
168
      "datastore_active": false,
167
      "datastore_active": false,
            
169
      "description": null,
168
      "description": null,
            
170
      "format": "tsv",
169
      "format": "tsv",
            
171
      "hash": "",
170
      "hash": "",
            
172
      "id": "a05fd101-9c06-4312-bb30-13f6ea008d46",
171
      "id": "a05fd101-9c06-4312-bb30-13f6ea008d46",
            
173
      "last_modified": null,
172
      "last_modified": null,
            
174
      "metadata_modified": "2024-05-30T15:58:24.247167",
173
      "metadata_modified": "2024-05-30T15:58:24.247167",
            
175
      "mimetype": "text/tab-separated-values",
174
      "mimetype": "text/tab-separated-values",
            
176
      "mimetype_inner": null,
175
      "mimetype_inner": null,
            
177
      "name": "Dataset 
176
      "name": "Dataset 
            
178
ital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv",
177
ital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv",
            
179
      "name_translated": {
178
      "name_translated": {
            
180
        "en": "Dataset 
179
        "en": "Dataset 
            
181
ital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv",
180
ital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv",
            
182
        "es": "Dataset 
181
        "es": "Dataset 
            
183
gital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv"
182
gital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv"
            
184
      },
183
      },
            
185
      "package_id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77",
184
      "package_id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77",
            
186
      "position": 1,
185
      "position": 1,
            
187
      "resource_identifier": "",
186
      "resource_identifier": "",
            
188
      "resource_relation": [],
187
      "resource_relation": [],
            
189
      "resource_relation-1": "",
188
      "resource_relation-1": "",
            
190
      "resource_type": null,
189
      "resource_type": null,
            
191
      "size": null,
190
      "size": null,
            
192
      "state": "active",
191
      "state": "active",
            
193
      "url": 
192
      "url": 
            
194
ital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv",
193
ital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv",
            
195
      "url_type": null
194
      "url_type": null
            
196
    },
195
    },
            
197
    {
196
    {
            
198
      "byte_size": "757,92 kB",
197
      "byte_size": "757,92 kB",
            
199
      "cache_last_updated": null,
198
      "cache_last_updated": null,
            
200
      "cache_url": null,
199
      "cache_url": null,
            
201
      "created": "2024-05-30T15:59:20.596413",
200
      "created": "2024-05-30T15:59:20.596413",
            
202
      "datastore_active": false,
201
      "datastore_active": false,
            
203
      "description": null,
202
      "description": null,
            
204
      "format": "pdf",
203
      "format": "pdf",
            
205
      "hash": "",
204
      "hash": "",
            
206
      "id": "a1f5a665-35a0-4513-8123-8e3feed8c66b",
205
      "id": "a1f5a665-35a0-4513-8123-8e3feed8c66b",
            
207
      "last_modified": null,
206
      "last_modified": null,
            
208
      "metadata_modified": "2024-05-30T15:59:40.961858",
207
      "metadata_modified": "2024-05-30T15:59:40.961858",
            
209
      "mimetype": "application/pdf",
208
      "mimetype": "application/pdf",
            
210
      "mimetype_inner": null,
209
      "mimetype_inner": null,
            
211
      "name": "Guideline CLARA-MeD_simplif_guideline.pdf",
210
      "name": "Guideline CLARA-MeD_simplif_guideline.pdf",
            
212
      "name_translated": {
211
      "name_translated": {
            
213
        "en": "Guideline CLARA-MeD_simplif_guideline.pdf",
212
        "en": "Guideline CLARA-MeD_simplif_guideline.pdf",
            
214
        "es": "Guideline CLARA-MeD_simplif_guideline.pdf"
213
        "es": "Guideline CLARA-MeD_simplif_guideline.pdf"
            
215
      },
214
      },
            
216
      "package_id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77",
215
      "package_id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77",
            
217
      "position": 2,
216
      "position": 2,
            
218
      "resource_identifier": "",
217
      "resource_identifier": "",
            
219
      "resource_relation": [],
218
      "resource_relation": [],
            
220
      "resource_relation-1": "",
219
      "resource_relation-1": "",
            
221
      "resource_type": null,
220
      "resource_type": null,
            
222
      "size": null,
221
      "size": null,
            
223
      "state": "active",
222
      "state": "active",
            
224
      "url": 
223
      "url": 
            
225
tal.csic.es/bitstream/10261/346579/2/CLARA-MeD_simplif_guideline.pdf",
224
tal.csic.es/bitstream/10261/346579/2/CLARA-MeD_simplif_guideline.pdf",
            
226
      "url_type": null
225
      "url_type": null
            
227
    }
226
    }
            
228
  ],
227
  ],
            
229
  "spatial": [],
228
  "spatial": [],
            
230
  "state": "active",
229
  "state": "active",
            
231
  "tags": [],
230
  "tags": [],
            
232
  "theme": [
231
  "theme": [
            
233
    
232
    
            
234
"http://datos.gob.es/kos/sector-publico/sector/ciencia-tecnologia",
233
"http://datos.gob.es/kos/sector-publico/sector/ciencia-tecnologia",
            
235
    "http://datos.gob.es/kos/sector-publico/sector/salud",
234
    "http://datos.gob.es/kos/sector-publico/sector/salud",
            
236
    "http://datos.gob.es/kos/sector-publico/sector/sector-publico"
235
    "http://datos.gob.es/kos/sector-publico/sector/sector-publico"
            
237
  ],
236
  ],
            
238
  "title": "CLARA-MeD simplified sentences",
237
  "title": "CLARA-MeD simplified sentences",
            
239
  "title_translated": {
238
  "title_translated": {
            
240
    "en": "CLARA-MeD simplified sentences",
239
    "en": "CLARA-MeD simplified sentences",
            
241
    "es": "CLARA-MeD simplified sentences"
240
    "es": "CLARA-MeD simplified sentences"
            
242
  },
241
  },
            
243
  "type": "dataset",
242
  "type": "dataset",
            
244
  "url": null,
243
  "url": null,
            
245
  "version": null
244
  "version": null
            
246
}
245
}