Changes

              
    

          
          
        
        

            
f
1
{
f
1
{
            
2
  "Observaciones": {
2
  "Observaciones": {
            
n
3
    "en": "",
n
3
    "en": "Recommended citation for this dataset: Bartolom\u00e9 
            
4
    "es": ""
4
Rodr\u00edguez, Roc\u00edo; Terroba Reinares, Ana Rosa; 
            
5
Campillos-Llanos, Leonardo; 2024; CLARA-MeD simplified sentences 
            
6
[Dataset]; DIGITAL.CSIC; https://doi.org/10.20350/digitalCSIC/16110",
            
7
    "es": "Cita recomendada para este dataset: Bartolom\u00e9 
            
8
Rodr\u00edguez, Roc\u00edo; Terroba Reinares, Ana Rosa; 
            
9
Campillos-Llanos, Leonardo; 2024; CLARA-MeD simplified sentences 
            
10
[Dataset]; DIGITAL.CSIC; https://doi.org/10.20350/digitalCSIC/16110"
            
5
  },
11
  },
            
6
  "author": null,
12
  "author": null,
            
7
  "author_email": null,
13
  "author_email": null,
            
8
  "autor": {
14
  "autor": {
            
9
    "en": [
15
    "en": [
            
n
10
      "Leonardo Campillos-Llanos"
n
16
      "Leonardo Campillos-Llanos",
            
17
      "Roc\u00edo Bartolom\u00e9 Rodr\u00edguez",
            
18
      "Ana Rosa Terroba Reinares"
            
11
    ],
19
    ],
            
12
    "es": [
20
    "es": [
            
n
13
      "Leonardo Campillos-Llanos"
n
21
      "Leonardo Campillos-Llanos",
            
22
      "Roc\u00edo Bartolom\u00e9 Rodr\u00edguez",
            
23
      "Ana Rosa Terroba Reinares"
            
14
    ]
24
    ]
            
15
  },
25
  },
            
16
  "conforms_to": [],
26
  "conforms_to": [],
            
n
17
  "coverage_new": {},
n
27
  "coverage_new": {
            
28
    "1": {
            
29
      "from": "2009-01-04T00:00:00",
            
30
      "to": "2023-12-04T00:00:00"
            
31
    }
            
32
  },
            
18
  "creator_user_id": "196556b3-e0c4-4c51-a9e6-f51cc752bc37",
33
  "creator_user_id": "196556b3-e0c4-4c51-a9e6-f51cc752bc37",
            
19
  "description": {
34
  "description": {
            
20
    "en": "This dataset contains 1200 manually simplified sentences 
35
    "en": "This dataset contains 1200 manually simplified sentences 
            
21
(144 019 tokens) from clinical trials in Spanish. A total of 1040 
36
(144 019 tokens) from clinical trials in Spanish. A total of 1040 
            
22
announcements from the European Clinical Trials Register (EudraCT) 
37
announcements from the European Clinical Trials Register (EudraCT) 
            
23
were analyzed to select sentences with ambiguities or exceeding 25 
38
were analyzed to select sentences with ambiguities or exceeding 25 
            
24
words. Simplification criteria were devised in an annotation 
39
words. Simplification criteria were devised in an annotation 
            
25
guideline, which is released publicly along the dataset.\r\n\r\nThis 
40
guideline, which is released publicly along the dataset.\r\n\r\nThis 
            
26
resource was collected in the CLARA-MeD project, with the goal of 
41
resource was collected in the CLARA-MeD project, with the goal of 
            
27
simplifying medical texts in the Spanish language and reduce the 
42
simplifying medical texts in the Spanish language and reduce the 
            
28
language barrier to patient's informed decision making. In particular, 
43
language barrier to patient's informed decision making. In particular, 
            
29
the project aims at developing linguistic resources for automatic 
44
the project aims at developing linguistic resources for automatic 
            
30
medical term simplification in Spanish; and conducting experiments in 
45
medical term simplification in Spanish; and conducting experiments in 
            
31
automatic text simplification.",
46
automatic text simplification.",
            
32
    "es": "This dataset contains 1200 manually simplified sentences 
47
    "es": "This dataset contains 1200 manually simplified sentences 
            
33
(144 019 tokens) from clinical trials in Spanish. A total of 1040 
48
(144 019 tokens) from clinical trials in Spanish. A total of 1040 
            
34
announcements from the European Clinical Trials Register (EudraCT) 
49
announcements from the European Clinical Trials Register (EudraCT) 
            
35
were analyzed to select sentences with ambiguities or exceeding 25 
50
were analyzed to select sentences with ambiguities or exceeding 25 
            
36
words. Simplification criteria were devised in an annotation 
51
words. Simplification criteria were devised in an annotation 
            
37
guideline, which is released publicly along the dataset.\r\n\r\nThis 
52
guideline, which is released publicly along the dataset.\r\n\r\nThis 
            
38
resource was collected in the CLARA-MeD project, with the goal of 
53
resource was collected in the CLARA-MeD project, with the goal of 
            
39
simplifying medical texts in the Spanish language and reduce the 
54
simplifying medical texts in the Spanish language and reduce the 
            
40
language barrier to patient's informed decision making. In particular, 
55
language barrier to patient's informed decision making. In particular, 
            
41
the project aims at developing linguistic resources for automatic 
56
the project aims at developing linguistic resources for automatic 
            
42
medical term simplification in Spanish; and conducting experiments in 
57
medical term simplification in Spanish; and conducting experiments in 
            
43
automatic text simplification."
58
automatic text simplification."
            
44
  },
59
  },
            
45
  "groups": [
60
  "groups": [
            
46
    {
61
    {
            
47
      "description": "",
62
      "description": "",
            
48
      "display_name": "Terminolog\u00eda",
63
      "display_name": "Terminolog\u00eda",
            
49
      "id": "f21d51d4-df60-44f9-ad1f-60f1d5ca24d2",
64
      "id": "f21d51d4-df60-44f9-ad1f-60f1d5ca24d2",
            
50
      "image_display_url": 
65
      "image_display_url": 
            
51
.cchs.csic.es/uploads/group/2024-09-27-062713.009717Terminologia.png",
66
.cchs.csic.es/uploads/group/2024-09-27-062713.009717Terminologia.png",
            
52
      "name": "terminologia",
67
      "name": "terminologia",
            
53
      "title": "Terminolog\u00eda"
68
      "title": "Terminolog\u00eda"
            
54
    }
69
    }
            
55
  ],
70
  ],
            
56
  "id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77",
71
  "id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77",
            
57
  "identifier": "https://doi.org/10.20350/digitalCSIC/16110",
72
  "identifier": "https://doi.org/10.20350/digitalCSIC/16110",
            
58
  "international_spatial_translated": {
73
  "international_spatial_translated": {
            
n
59
    "en": "",
n
74
    "en": "Europe (data from EudraCT)",
            
60
    "es": ""
75
    "es": "Europa (datos de EudraCT)"
            
61
  },
76
  },
            
62
  "isopen": false,
77
  "isopen": false,
            
63
  "issued_date": "2024-02-09T00:00:00",
78
  "issued_date": "2024-02-09T00:00:00",
            
64
  "language": [
79
  "language": [
            
65
    "es",
80
    "es",
            
66
    "en"
81
    "en"
            
67
  ],
82
  ],
            
68
  "license_id": "https://creativecommons.org/licenses/by-nc-sa/4.0/",
83
  "license_id": "https://creativecommons.org/licenses/by-nc-sa/4.0/",
            
69
  "license_title": 
84
  "license_title": 
            
70
"https://creativecommons.org/licenses/by-nc-sa/4.0/",
85
"https://creativecommons.org/licenses/by-nc-sa/4.0/",
            
71
  "maintainer": null,
86
  "maintainer": null,
            
72
  "maintainer_email": null,
87
  "maintainer_email": null,
            
73
  "metadata_created": "2024-05-30T15:57:14.431217",
88
  "metadata_created": "2024-05-30T15:57:14.431217",
            
n
74
  "metadata_modified": "2025-03-04T12:51:05.028495",
n
89
  "metadata_modified": "2025-03-04T15:15:49.810266",
            
75
  "multilingual_tags": {
90
  "multilingual_tags": {
            
76
    "en": [
91
    "en": [
            
77
      "Biomedical natural language processing",
92
      "Biomedical natural language processing",
            
78
      "Parallel sentences",
93
      "Parallel sentences",
            
79
      "Medical text simplification"
94
      "Medical text simplification"
            
80
    ]
95
    ]
            
81
  },
96
  },
            
82
  "name": "clara-med-simplified-sentences",
97
  "name": "clara-med-simplified-sentences",
            
83
  "notes": null,
98
  "notes": null,
            
84
  "num_resources": 3,
99
  "num_resources": 3,
            
85
  "num_tags": 0,
100
  "num_tags": 0,
            
86
  "organization": {
101
  "organization": {
            
87
    "approval_status": "approved",
102
    "approval_status": "approved",
            
88
    "created": "2023-09-25T12:13:42.172869",
103
    "created": "2023-09-25T12:13:42.172869",
            
89
    "description": "El Instituto de Lengua, Literatura y 
104
    "description": "El Instituto de Lengua, Literatura y 
            
90
Antropolog\u00eda, ILLA (CSIC) tiene como objetivo primordial la 
105
Antropolog\u00eda, ILLA (CSIC) tiene como objetivo primordial la 
            
91
investigaci\u00f3n del patrimonio cultural hisp\u00e1nico en su triple 
106
investigaci\u00f3n del patrimonio cultural hisp\u00e1nico en su triple 
            
92
dimensi\u00f3n antropol\u00f3gica, ling\u00fc\u00edstica y 
107
dimensi\u00f3n antropol\u00f3gica, ling\u00fc\u00edstica y 
            
93
literaria.",
108
literaria.",
            
94
    "id": "fc47e531-a165-4eac-8fc7-34342a3a38ff",
109
    "id": "fc47e531-a165-4eac-8fc7-34342a3a38ff",
            
95
    "image_url": "2023-09-25-101342.167134illa0.png",
110
    "image_url": "2023-09-25-101342.167134illa0.png",
            
96
    "is_organization": true,
111
    "is_organization": true,
            
97
    "name": "instituto-de-lengua-literatura-y-antropologia-illa-csic",
112
    "name": "instituto-de-lengua-literatura-y-antropologia-illa-csic",
            
98
    "state": "active",
113
    "state": "active",
            
99
    "title": "Instituto de Lengua, Literatura y Antropolog\u00eda 
114
    "title": "Instituto de Lengua, Literatura y Antropolog\u00eda 
            
100
(ILLA), CSIC",
115
(ILLA), CSIC",
            
101
    "type": "organization"
116
    "type": "organization"
            
102
  },
117
  },
            
103
  "owner_org": "fc47e531-a165-4eac-8fc7-34342a3a38ff",
118
  "owner_org": "fc47e531-a165-4eac-8fc7-34342a3a38ff",
            
104
  "private": false,
119
  "private": false,
            
105
  "proyecto": {
120
  "proyecto": {
            
106
    "es": [
121
    "es": [
            
107
      "PID2020-116001RA-C33"
122
      "PID2020-116001RA-C33"
            
108
    ]
123
    ]
            
109
  },
124
  },
            
110
  "publisher": "b627d71d-2315-4e75-afc9-897da84459f0",
125
  "publisher": "b627d71d-2315-4e75-afc9-897da84459f0",
            
t
111
  "reference": [],
t
126
  "reference": [
            
127
    "https://github.com/lcampillos/CLARA-MeD/"
            
128
  ],
            
112
  "relationships_as_object": [],
129
  "relationships_as_object": [],
            
113
  "relationships_as_subject": [],
130
  "relationships_as_subject": [],
            
114
  "resources": [
131
  "resources": [
            
115
    {
132
    {
            
116
      "byte_size": "7,32 kB",
133
      "byte_size": "7,32 kB",
            
117
      "cache_last_updated": null,
134
      "cache_last_updated": null,
            
118
      "cache_url": null,
135
      "cache_url": null,
            
119
      "created": "2024-05-30T15:58:24.249419",
136
      "created": "2024-05-30T15:58:24.249419",
            
120
      "datastore_active": false,
137
      "datastore_active": false,
            
121
      "description": null,
138
      "description": null,
            
122
      "format": "txt",
139
      "format": "txt",
            
123
      "hash": "",
140
      "hash": "",
            
124
      "id": "30dfbb45-e41a-4c6e-bcdc-a4af2f040715",
141
      "id": "30dfbb45-e41a-4c6e-bcdc-a4af2f040715",
            
125
      "last_modified": null,
142
      "last_modified": null,
            
126
      "metadata_modified": "2024-05-30T15:58:24.421759",
143
      "metadata_modified": "2024-05-30T15:58:24.421759",
            
127
      "mimetype": "text/plain",
144
      "mimetype": "text/plain",
            
128
      "mimetype_inner": null,
145
      "mimetype_inner": null,
            
129
      "name": "README_CLARAMED_sentences.txt\t",
146
      "name": "README_CLARAMED_sentences.txt\t",
            
130
      "name_translated": {
147
      "name_translated": {
            
131
        "en": "README_CLARAMED_sentences.txt\t",
148
        "en": "README_CLARAMED_sentences.txt\t",
            
132
        "es": "README_CLARAMED_sentences.txt\t"
149
        "es": "README_CLARAMED_sentences.txt\t"
            
133
      },
150
      },
            
134
      "package_id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77",
151
      "package_id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77",
            
135
      "position": 0,
152
      "position": 0,
            
136
      "resource_identifier": "",
153
      "resource_identifier": "",
            
137
      "resource_relation": [],
154
      "resource_relation": [],
            
138
      "resource_relation-1": "",
155
      "resource_relation-1": "",
            
139
      "resource_type": null,
156
      "resource_type": null,
            
140
      "size": null,
157
      "size": null,
            
141
      "state": "active",
158
      "state": "active",
            
142
      "url": 
159
      "url": 
            
143
gital.csic.es/bitstream/10261/346579/6/README_CLARAMED_sentences.txt",
160
gital.csic.es/bitstream/10261/346579/6/README_CLARAMED_sentences.txt",
            
144
      "url_type": null
161
      "url_type": null
            
145
    },
162
    },
            
146
    {
163
    {
            
147
      "byte_size": "981,11 kB",
164
      "byte_size": "981,11 kB",
            
148
      "cache_last_updated": null,
165
      "cache_last_updated": null,
            
149
      "cache_url": null,
166
      "cache_url": null,
            
150
      "created": "2024-05-30T15:57:45.357301",
167
      "created": "2024-05-30T15:57:45.357301",
            
151
      "datastore_active": false,
168
      "datastore_active": false,
            
152
      "description": null,
169
      "description": null,
            
153
      "format": "tsv",
170
      "format": "tsv",
            
154
      "hash": "",
171
      "hash": "",
            
155
      "id": "a05fd101-9c06-4312-bb30-13f6ea008d46",
172
      "id": "a05fd101-9c06-4312-bb30-13f6ea008d46",
            
156
      "last_modified": null,
173
      "last_modified": null,
            
157
      "metadata_modified": "2024-05-30T15:58:24.247167",
174
      "metadata_modified": "2024-05-30T15:58:24.247167",
            
158
      "mimetype": "text/tab-separated-values",
175
      "mimetype": "text/tab-separated-values",
            
159
      "mimetype_inner": null,
176
      "mimetype_inner": null,
            
160
      "name": "Dataset 
177
      "name": "Dataset 
            
161
ital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv",
178
ital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv",
            
162
      "name_translated": {
179
      "name_translated": {
            
163
        "en": "Dataset 
180
        "en": "Dataset 
            
164
ital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv",
181
ital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv",
            
165
        "es": "Dataset 
182
        "es": "Dataset 
            
166
gital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv"
183
gital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv"
            
167
      },
184
      },
            
168
      "package_id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77",
185
      "package_id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77",
            
169
      "position": 1,
186
      "position": 1,
            
170
      "resource_identifier": "",
187
      "resource_identifier": "",
            
171
      "resource_relation": [],
188
      "resource_relation": [],
            
172
      "resource_relation-1": "",
189
      "resource_relation-1": "",
            
173
      "resource_type": null,
190
      "resource_type": null,
            
174
      "size": null,
191
      "size": null,
            
175
      "state": "active",
192
      "state": "active",
            
176
      "url": 
193
      "url": 
            
177
ital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv",
194
ital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv",
            
178
      "url_type": null
195
      "url_type": null
            
179
    },
196
    },
            
180
    {
197
    {
            
181
      "byte_size": "757,92 kB",
198
      "byte_size": "757,92 kB",
            
182
      "cache_last_updated": null,
199
      "cache_last_updated": null,
            
183
      "cache_url": null,
200
      "cache_url": null,
            
184
      "created": "2024-05-30T15:59:20.596413",
201
      "created": "2024-05-30T15:59:20.596413",
            
185
      "datastore_active": false,
202
      "datastore_active": false,
            
186
      "description": null,
203
      "description": null,
            
187
      "format": "pdf",
204
      "format": "pdf",
            
188
      "hash": "",
205
      "hash": "",
            
189
      "id": "a1f5a665-35a0-4513-8123-8e3feed8c66b",
206
      "id": "a1f5a665-35a0-4513-8123-8e3feed8c66b",
            
190
      "last_modified": null,
207
      "last_modified": null,
            
191
      "metadata_modified": "2024-05-30T15:59:40.961858",
208
      "metadata_modified": "2024-05-30T15:59:40.961858",
            
192
      "mimetype": "application/pdf",
209
      "mimetype": "application/pdf",
            
193
      "mimetype_inner": null,
210
      "mimetype_inner": null,
            
194
      "name": "Guideline CLARA-MeD_simplif_guideline.pdf",
211
      "name": "Guideline CLARA-MeD_simplif_guideline.pdf",
            
195
      "name_translated": {
212
      "name_translated": {
            
196
        "en": "Guideline CLARA-MeD_simplif_guideline.pdf",
213
        "en": "Guideline CLARA-MeD_simplif_guideline.pdf",
            
197
        "es": "Guideline CLARA-MeD_simplif_guideline.pdf"
214
        "es": "Guideline CLARA-MeD_simplif_guideline.pdf"
            
198
      },
215
      },
            
199
      "package_id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77",
216
      "package_id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77",
            
200
      "position": 2,
217
      "position": 2,
            
201
      "resource_identifier": "",
218
      "resource_identifier": "",
            
202
      "resource_relation": [],
219
      "resource_relation": [],
            
203
      "resource_relation-1": "",
220
      "resource_relation-1": "",
            
204
      "resource_type": null,
221
      "resource_type": null,
            
205
      "size": null,
222
      "size": null,
            
206
      "state": "active",
223
      "state": "active",
            
207
      "url": 
224
      "url": 
            
208
tal.csic.es/bitstream/10261/346579/2/CLARA-MeD_simplif_guideline.pdf",
225
tal.csic.es/bitstream/10261/346579/2/CLARA-MeD_simplif_guideline.pdf",
            
209
      "url_type": null
226
      "url_type": null
            
210
    }
227
    }
            
211
  ],
228
  ],
            
212
  "spatial": [],
229
  "spatial": [],
            
213
  "state": "active",
230
  "state": "active",
            
214
  "tags": [],
231
  "tags": [],
            
215
  "theme": [
232
  "theme": [
            
216
    
233
    
            
217
"http://datos.gob.es/kos/sector-publico/sector/ciencia-tecnologia",
234
"http://datos.gob.es/kos/sector-publico/sector/ciencia-tecnologia",
            
218
    "http://datos.gob.es/kos/sector-publico/sector/salud",
235
    "http://datos.gob.es/kos/sector-publico/sector/salud",
            
219
    "http://datos.gob.es/kos/sector-publico/sector/sector-publico"
236
    "http://datos.gob.es/kos/sector-publico/sector/sector-publico"
            
220
  ],
237
  ],
            
221
  "title": "CLARA-MeD simplified sentences",
238
  "title": "CLARA-MeD simplified sentences",
            
222
  "title_translated": {
239
  "title_translated": {
            
223
    "en": "CLARA-MeD simplified sentences",
240
    "en": "CLARA-MeD simplified sentences",
            
224
    "es": "CLARA-MeD simplified sentences"
241
    "es": "CLARA-MeD simplified sentences"
            
225
  },
242
  },
            
226
  "type": "dataset",
243
  "type": "dataset",
            
227
  "url": null,
244
  "url": null,
            
228
  "version": null
245
  "version": null
            
229
}
246
}