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"
            
18
    ],
19
    ],
            
19
    "es": [
20
    "es": [
            
20
      "Leonardo Campillos-Llanos",
21
      "Leonardo Campillos-Llanos",
            
21
      "Roc\u00edo Bartolom\u00e9 Rodr\u00edguez",
22
      "Roc\u00edo Bartolom\u00e9 Rodr\u00edguez",
            
n
22
      "Ana Rosa Terroba Reinares"
n
23
      "Ana Rosa Terroba-Reinares"
            
23
    ]
24
    ]
            
24
  },
25
  },
            
25
  "conforms_to": [],
26
  "conforms_to": [],
            
26
  "coverage_new": {
27
  "coverage_new": {
            
27
    "1": {
28
    "1": {
            
n
28
      "from": "2009-01-04T00:00:00",
n

            
29
      "to": "2023-12-04T00:00:00"
29
      "from": "2024-02-09T00:00:00"
            
30
    }
30
    }
            
31
  },
31
  },
            
32
  "creator_user_id": "196556b3-e0c4-4c51-a9e6-f51cc752bc37",
32
  "creator_user_id": "196556b3-e0c4-4c51-a9e6-f51cc752bc37",
            
33
  "description": {
33
  "description": {
            
34
    "en": "This dataset contains 1200 manually simplified sentences 
34
    "en": "This dataset contains 1200 manually simplified sentences 
            
35
(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 
            
36
announcements from the European Clinical Trials Register (EudraCT) 
36
announcements from the European Clinical Trials Register (EudraCT) 
            
37
were analyzed to select sentences with ambiguities or exceeding 25 
37
were analyzed to select sentences with ambiguities or exceeding 25 
            
38
words. Simplification criteria were devised in an annotation 
38
words. Simplification criteria were devised in an annotation 
            
39
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 
            
40
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 
            
41
simplifying medical texts in the Spanish language and reduce the 
41
simplifying medical texts in the Spanish language and reduce the 
            
42
language barrier to patient's informed decision making. In particular, 
42
language barrier to patient's informed decision making. In particular, 
            
43
the project aims at developing linguistic resources for automatic 
43
the project aims at developing linguistic resources for automatic 
            
44
medical term simplification in Spanish; and conducting experiments in 
44
medical term simplification in Spanish; and conducting experiments in 
            
45
automatic text simplification.",
45
automatic text simplification.",
            
46
    "es": "This dataset contains 1200 manually simplified sentences 
46
    "es": "This dataset contains 1200 manually simplified sentences 
            
47
(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 
            
48
announcements from the European Clinical Trials Register (EudraCT) 
48
announcements from the European Clinical Trials Register (EudraCT) 
            
49
were analyzed to select sentences with ambiguities or exceeding 25 
49
were analyzed to select sentences with ambiguities or exceeding 25 
            
50
words. Simplification criteria were devised in an annotation 
50
words. Simplification criteria were devised in an annotation 
            
51
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 
            
52
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 
            
53
simplifying medical texts in the Spanish language and reduce the 
53
simplifying medical texts in the Spanish language and reduce the 
            
54
language barrier to patient's informed decision making. In particular, 
54
language barrier to patient's informed decision making. In particular, 
            
55
the project aims at developing linguistic resources for automatic 
55
the project aims at developing linguistic resources for automatic 
            
56
medical term simplification in Spanish; and conducting experiments in 
56
medical term simplification in Spanish; and conducting experiments in 
            
57
automatic text simplification."
57
automatic text simplification."
            
58
  },
58
  },
            
59
  "groups": [
59
  "groups": [
            
60
    {
60
    {
            
61
      "description": "",
61
      "description": "",
            
n
n
62
      "display_name": "Ling\u00fc\u00edstica",
            
63
      "id": "372aa551-b8e2-47fd-bc5e-0f807f9b09d6",
            
64
      "image_display_url": 
            
65
s.cchs.csic.es/uploads/group/2024-09-24-155551.755581Linguistica.png",
            
66
      "name": "linguistica",
            
67
      "title": "Ling\u00fc\u00edstica"
            
68
    },
            
69
    {
            
70
      "description": "",
            
71
      "display_name": "Tecnolog\u00edas del lenguaje",
            
72
      "id": "f50a92b2-8774-4390-82dd-5c080b098961",
            
73
      "image_display_url": 
            
74
s/uploads/group/2024-09-27-062643.156350Tecnologias-del-lenguaje.png",
            
75
      "name": "tecnologias-del-lenguaje",
            
76
      "title": "Tecnolog\u00edas del lenguaje"
            
77
    },
            
78
    {
            
79
      "description": "",
            
62
      "display_name": "Terminolog\u00eda",
80
      "display_name": "Terminolog\u00eda",
            
63
      "id": "f21d51d4-df60-44f9-ad1f-60f1d5ca24d2",
81
      "id": "f21d51d4-df60-44f9-ad1f-60f1d5ca24d2",
            
64
      "image_display_url": 
82
      "image_display_url": 
            
65
.cchs.csic.es/uploads/group/2024-09-27-062713.009717Terminologia.png",
83
.cchs.csic.es/uploads/group/2024-09-27-062713.009717Terminologia.png",
            
66
      "name": "terminologia",
84
      "name": "terminologia",
            
67
      "title": "Terminolog\u00eda"
85
      "title": "Terminolog\u00eda"
            
68
    }
86
    }
            
69
  ],
87
  ],
            
70
  "id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77",
88
  "id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77",
            
71
  "identifier": "https://doi.org/10.20350/digitalCSIC/16110",
89
  "identifier": "https://doi.org/10.20350/digitalCSIC/16110",
            
72
  "international_spatial_translated": {
90
  "international_spatial_translated": {
            
n
73
    "en": "Europe (data from EudraCT)",
n
91
    "en": "Europe",
            
74
    "es": "Europa (datos de EudraCT)"
92
    "es": "Europa"
            
75
  },
93
  },
            
76
  "isopen": false,
94
  "isopen": false,
            
77
  "issued_date": "2024-02-09T00:00:00",
95
  "issued_date": "2024-02-09T00:00:00",
            
78
  "language": [
96
  "language": [
            
79
    "es",
97
    "es",
            
80
    "en"
98
    "en"
            
81
  ],
99
  ],
            
82
  "license_id": "https://creativecommons.org/licenses/by-nc-sa/4.0/",
100
  "license_id": "https://creativecommons.org/licenses/by-nc-sa/4.0/",
            
83
  "license_title": 
101
  "license_title": 
            
84
"https://creativecommons.org/licenses/by-nc-sa/4.0/",
102
"https://creativecommons.org/licenses/by-nc-sa/4.0/",
            
85
  "maintainer": null,
103
  "maintainer": null,
            
86
  "maintainer_email": null,
104
  "maintainer_email": null,
            
87
  "metadata_created": "2024-05-30T15:57:14.431217",
105
  "metadata_created": "2024-05-30T15:57:14.431217",
            
n
88
  "metadata_modified": "2025-03-04T15:18:34.384571",
n
106
  "metadata_modified": "2025-03-05T07:51:16.478174",
            
89
  "multilingual_tags": {
107
  "multilingual_tags": {
            
90
    "en": [
108
    "en": [
            
91
      "Biomedical natural language processing",
109
      "Biomedical natural language processing",
            
92
      "Parallel sentences",
110
      "Parallel sentences",
            
93
      "Medical text simplification"
111
      "Medical text simplification"
            
n
n
112
    ],
            
113
    "es": [
            
114
      "Prcesamiento del Lenguaje Natural en Biomedicina",
            
115
      "Frases paralelas",
            
116
      "Simplificaci\u00f3n textual en medicina"
            
94
    ]
117
    ]
            
95
  },
118
  },
            
96
  "name": "clara-med-simplified-sentences",
119
  "name": "clara-med-simplified-sentences",
            
97
  "notes": null,
120
  "notes": null,
            
98
  "num_resources": 3,
121
  "num_resources": 3,
            
99
  "num_tags": 0,
122
  "num_tags": 0,
            
100
  "organization": {
123
  "organization": {
            
101
    "approval_status": "approved",
124
    "approval_status": "approved",
            
102
    "created": "2023-09-25T12:13:42.172869",
125
    "created": "2023-09-25T12:13:42.172869",
            
103
    "description": "El Instituto de Lengua, Literatura y 
126
    "description": "El Instituto de Lengua, Literatura y 
            
104
Antropolog\u00eda, ILLA (CSIC) tiene como objetivo primordial la 
127
Antropolog\u00eda, ILLA (CSIC) tiene como objetivo primordial la 
            
105
investigaci\u00f3n del patrimonio cultural hisp\u00e1nico en su triple 
128
investigaci\u00f3n del patrimonio cultural hisp\u00e1nico en su triple 
            
106
dimensi\u00f3n antropol\u00f3gica, ling\u00fc\u00edstica y 
129
dimensi\u00f3n antropol\u00f3gica, ling\u00fc\u00edstica y 
            
107
literaria.",
130
literaria.",
            
108
    "id": "fc47e531-a165-4eac-8fc7-34342a3a38ff",
131
    "id": "fc47e531-a165-4eac-8fc7-34342a3a38ff",
            
109
    "image_url": "2023-09-25-101342.167134illa0.png",
132
    "image_url": "2023-09-25-101342.167134illa0.png",
            
110
    "is_organization": true,
133
    "is_organization": true,
            
111
    "name": "instituto-de-lengua-literatura-y-antropologia-illa-csic",
134
    "name": "instituto-de-lengua-literatura-y-antropologia-illa-csic",
            
112
    "state": "active",
135
    "state": "active",
            
113
    "title": "Instituto de Lengua, Literatura y Antropolog\u00eda 
136
    "title": "Instituto de Lengua, Literatura y Antropolog\u00eda 
            
114
(ILLA), CSIC",
137
(ILLA), CSIC",
            
115
    "type": "organization"
138
    "type": "organization"
            
116
  },
139
  },
            
117
  "owner_org": "fc47e531-a165-4eac-8fc7-34342a3a38ff",
140
  "owner_org": "fc47e531-a165-4eac-8fc7-34342a3a38ff",
            
118
  "private": false,
141
  "private": false,
            
119
  "proyecto": {
142
  "proyecto": {
            
120
    "es": [
143
    "es": [
            
121
      "PID2020-116001RA-C33"
144
      "PID2020-116001RA-C33"
            
122
    ]
145
    ]
            
123
  },
146
  },
            
124
  "publisher": "b627d71d-2315-4e75-afc9-897da84459f0",
147
  "publisher": "b627d71d-2315-4e75-afc9-897da84459f0",
            
125
  "reference": [
148
  "reference": [
            
126
    "https://github.com/lcampillos/CLARA-MeD/"
149
    "https://github.com/lcampillos/CLARA-MeD/"
            
127
  ],
150
  ],
            
128
  "relationships_as_object": [],
151
  "relationships_as_object": [],
            
129
  "relationships_as_subject": [],
152
  "relationships_as_subject": [],
            
130
  "resources": [
153
  "resources": [
            
131
    {
154
    {
            
132
      "byte_size": "7,32 kB",
155
      "byte_size": "7,32 kB",
            
133
      "cache_last_updated": null,
156
      "cache_last_updated": null,
            
134
      "cache_url": null,
157
      "cache_url": null,
            
135
      "created": "2024-05-30T15:58:24.249419",
158
      "created": "2024-05-30T15:58:24.249419",
            
136
      "datastore_active": false,
159
      "datastore_active": false,
            
137
      "description": null,
160
      "description": null,
            
138
      "format": "txt",
161
      "format": "txt",
            
139
      "hash": "",
162
      "hash": "",
            
140
      "id": "30dfbb45-e41a-4c6e-bcdc-a4af2f040715",
163
      "id": "30dfbb45-e41a-4c6e-bcdc-a4af2f040715",
            
141
      "last_modified": null,
164
      "last_modified": null,
            
142
      "metadata_modified": "2024-05-30T15:58:24.421759",
165
      "metadata_modified": "2024-05-30T15:58:24.421759",
            
143
      "mimetype": "text/plain",
166
      "mimetype": "text/plain",
            
144
      "mimetype_inner": null,
167
      "mimetype_inner": null,
            
145
      "name": "README_CLARAMED_sentences.txt\t",
168
      "name": "README_CLARAMED_sentences.txt\t",
            
146
      "name_translated": {
169
      "name_translated": {
            
147
        "en": "README_CLARAMED_sentences.txt\t",
170
        "en": "README_CLARAMED_sentences.txt\t",
            
148
        "es": "README_CLARAMED_sentences.txt\t"
171
        "es": "README_CLARAMED_sentences.txt\t"
            
149
      },
172
      },
            
150
      "package_id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77",
173
      "package_id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77",
            
151
      "position": 0,
174
      "position": 0,
            
152
      "resource_identifier": "",
175
      "resource_identifier": "",
            
153
      "resource_relation": [],
176
      "resource_relation": [],
            
154
      "resource_relation-1": "",
177
      "resource_relation-1": "",
            
155
      "resource_type": null,
178
      "resource_type": null,
            
156
      "size": null,
179
      "size": null,
            
157
      "state": "active",
180
      "state": "active",
            
158
      "url": 
181
      "url": 
            
159
gital.csic.es/bitstream/10261/346579/6/README_CLARAMED_sentences.txt",
182
gital.csic.es/bitstream/10261/346579/6/README_CLARAMED_sentences.txt",
            
160
      "url_type": null
183
      "url_type": null
            
161
    },
184
    },
            
162
    {
185
    {
            
163
      "byte_size": "981,11 kB",
186
      "byte_size": "981,11 kB",
            
164
      "cache_last_updated": null,
187
      "cache_last_updated": null,
            
165
      "cache_url": null,
188
      "cache_url": null,
            
166
      "created": "2024-05-30T15:57:45.357301",
189
      "created": "2024-05-30T15:57:45.357301",
            
167
      "datastore_active": false,
190
      "datastore_active": false,
            
168
      "description": null,
191
      "description": null,
            
169
      "format": "tsv",
192
      "format": "tsv",
            
170
      "hash": "",
193
      "hash": "",
            
171
      "id": "a05fd101-9c06-4312-bb30-13f6ea008d46",
194
      "id": "a05fd101-9c06-4312-bb30-13f6ea008d46",
            
172
      "last_modified": null,
195
      "last_modified": null,
            
173
      "metadata_modified": "2024-05-30T15:58:24.247167",
196
      "metadata_modified": "2024-05-30T15:58:24.247167",
            
174
      "mimetype": "text/tab-separated-values",
197
      "mimetype": "text/tab-separated-values",
            
175
      "mimetype_inner": null,
198
      "mimetype_inner": null,
            
176
      "name": "Dataset 
199
      "name": "Dataset 
            
177
ital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv",
200
ital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv",
            
178
      "name_translated": {
201
      "name_translated": {
            
179
        "en": "Dataset 
202
        "en": "Dataset 
            
180
ital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv",
203
ital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv",
            
181
        "es": "Dataset 
204
        "es": "Dataset 
            
182
gital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv"
205
gital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv"
            
183
      },
206
      },
            
184
      "package_id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77",
207
      "package_id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77",
            
185
      "position": 1,
208
      "position": 1,
            
186
      "resource_identifier": "",
209
      "resource_identifier": "",
            
187
      "resource_relation": [],
210
      "resource_relation": [],
            
188
      "resource_relation-1": "",
211
      "resource_relation-1": "",
            
189
      "resource_type": null,
212
      "resource_type": null,
            
190
      "size": null,
213
      "size": null,
            
191
      "state": "active",
214
      "state": "active",
            
192
      "url": 
215
      "url": 
            
193
ital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv",
216
ital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv",
            
194
      "url_type": null
217
      "url_type": null
            
195
    },
218
    },
            
196
    {
219
    {
            
197
      "byte_size": "757,92 kB",
220
      "byte_size": "757,92 kB",
            
198
      "cache_last_updated": null,
221
      "cache_last_updated": null,
            
199
      "cache_url": null,
222
      "cache_url": null,
            
200
      "created": "2024-05-30T15:59:20.596413",
223
      "created": "2024-05-30T15:59:20.596413",
            
201
      "datastore_active": false,
224
      "datastore_active": false,
            
202
      "description": null,
225
      "description": null,
            
203
      "format": "pdf",
226
      "format": "pdf",
            
204
      "hash": "",
227
      "hash": "",
            
205
      "id": "a1f5a665-35a0-4513-8123-8e3feed8c66b",
228
      "id": "a1f5a665-35a0-4513-8123-8e3feed8c66b",
            
206
      "last_modified": null,
229
      "last_modified": null,
            
207
      "metadata_modified": "2024-05-30T15:59:40.961858",
230
      "metadata_modified": "2024-05-30T15:59:40.961858",
            
208
      "mimetype": "application/pdf",
231
      "mimetype": "application/pdf",
            
209
      "mimetype_inner": null,
232
      "mimetype_inner": null,
            
210
      "name": "Guideline CLARA-MeD_simplif_guideline.pdf",
233
      "name": "Guideline CLARA-MeD_simplif_guideline.pdf",
            
211
      "name_translated": {
234
      "name_translated": {
            
212
        "en": "Guideline CLARA-MeD_simplif_guideline.pdf",
235
        "en": "Guideline CLARA-MeD_simplif_guideline.pdf",
            
213
        "es": "Guideline CLARA-MeD_simplif_guideline.pdf"
236
        "es": "Guideline CLARA-MeD_simplif_guideline.pdf"
            
214
      },
237
      },
            
215
      "package_id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77",
238
      "package_id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77",
            
216
      "position": 2,
239
      "position": 2,
            
217
      "resource_identifier": "",
240
      "resource_identifier": "",
            
218
      "resource_relation": [],
241
      "resource_relation": [],
            
219
      "resource_relation-1": "",
242
      "resource_relation-1": "",
            
220
      "resource_type": null,
243
      "resource_type": null,
            
221
      "size": null,
244
      "size": null,
            
222
      "state": "active",
245
      "state": "active",
            
223
      "url": 
246
      "url": 
            
224
tal.csic.es/bitstream/10261/346579/2/CLARA-MeD_simplif_guideline.pdf",
247
tal.csic.es/bitstream/10261/346579/2/CLARA-MeD_simplif_guideline.pdf",
            
225
      "url_type": null
248
      "url_type": null
            
226
    }
249
    }
            
227
  ],
250
  ],
            
n
228
  "spatial": [],
n
251
  "spatial": [
            
252
    
            
253
ttp://datos.gob.es/recurso/sector-publico/territorio/Pais/Espa\u00f1a"
            
254
  ],
            
229
  "state": "active",
255
  "state": "active",
            
230
  "tags": [],
256
  "tags": [],
            
231
  "theme": [
257
  "theme": [
            
232
    
258
    
            
233
"http://datos.gob.es/kos/sector-publico/sector/ciencia-tecnologia",
259
"http://datos.gob.es/kos/sector-publico/sector/ciencia-tecnologia",
            
t
234
    "http://datos.gob.es/kos/sector-publico/sector/salud",
t
260
    "http://datos.gob.es/kos/sector-publico/sector/salud"
            
235
    "http://datos.gob.es/kos/sector-publico/sector/sector-publico"

            
236
  ],
261
  ],
            
237
  "title": "CLARA-MeD simplified sentences",
262
  "title": "CLARA-MeD simplified sentences",
            
238
  "title_translated": {
263
  "title_translated": {
            
239
    "en": "CLARA-MeD simplified sentences",
264
    "en": "CLARA-MeD simplified sentences",
            
240
    "es": "CLARA-MeD simplified sentences"
265
    "es": "CLARA-MeD simplified sentences"
            
241
  },
266
  },
            
242
  "type": "dataset",
267
  "type": "dataset",
            
243
  "url": null,
268
  "url": null,
            
244
  "version": null
269
  "version": null
            
245
}
270
}