Changes
On February 25, 2025 at 10:54:05 AM UTC,
-
No fields were updated. See the metadata diff for more details.
| f | 1 | { | f | 1 | { |
| n | n | 2 | "Observaciones": {}, | ||
| 2 | "author": null, | 3 | "author": null, | ||
| 3 | "author_email": null, | 4 | "author_email": null, | ||
| n | n | 5 | "autor": {}, | ||
| 4 | "conforms_to": [], | 6 | "conforms_to": [], | ||
| 5 | "coverage_new": {}, | 7 | "coverage_new": {}, | ||
| 6 | "creator_user_id": "196556b3-e0c4-4c51-a9e6-f51cc752bc37", | 8 | "creator_user_id": "196556b3-e0c4-4c51-a9e6-f51cc752bc37", | ||
| 7 | "description": { | 9 | "description": { | ||
| 8 | "en": "This dataset contains 1200 manually simplified sentences | 10 | "en": "This dataset contains 1200 manually simplified sentences | ||
| 9 | (144 019 tokens) from clinical trials in Spanish. A total of 1040 | 11 | (144 019 tokens) from clinical trials in Spanish. A total of 1040 | ||
| 10 | announcements from the European Clinical Trials Register (EudraCT) | 12 | announcements from the European Clinical Trials Register (EudraCT) | ||
| 11 | were analyzed to select sentences with ambiguities or exceeding 25 | 13 | were analyzed to select sentences with ambiguities or exceeding 25 | ||
| 12 | words. Simplification criteria were devised in an annotation | 14 | words. Simplification criteria were devised in an annotation | ||
| 13 | guideline, which is released publicly along the dataset.\r\n\r\nThis | 15 | guideline, which is released publicly along the dataset.\r\n\r\nThis | ||
| 14 | resource was collected in the CLARA-MeD project, with the goal of | 16 | resource was collected in the CLARA-MeD project, with the goal of | ||
| 15 | simplifying medical texts in the Spanish language and reduce the | 17 | simplifying medical texts in the Spanish language and reduce the | ||
| 16 | language barrier to patient's informed decision making. In particular, | 18 | language barrier to patient's informed decision making. In particular, | ||
| 17 | the project aims at developing linguistic resources for automatic | 19 | the project aims at developing linguistic resources for automatic | ||
| 18 | medical term simplification in Spanish; and conducting experiments in | 20 | medical term simplification in Spanish; and conducting experiments in | ||
| 19 | automatic text simplification.", | 21 | automatic text simplification.", | ||
| 20 | "es": "This dataset contains 1200 manually simplified sentences | 22 | "es": "This dataset contains 1200 manually simplified sentences | ||
| 21 | (144 019 tokens) from clinical trials in Spanish. A total of 1040 | 23 | (144 019 tokens) from clinical trials in Spanish. A total of 1040 | ||
| 22 | announcements from the European Clinical Trials Register (EudraCT) | 24 | announcements from the European Clinical Trials Register (EudraCT) | ||
| 23 | were analyzed to select sentences with ambiguities or exceeding 25 | 25 | were analyzed to select sentences with ambiguities or exceeding 25 | ||
| 24 | words. Simplification criteria were devised in an annotation | 26 | words. Simplification criteria were devised in an annotation | ||
| 25 | guideline, which is released publicly along the dataset.\r\n\r\nThis | 27 | 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 | 28 | resource was collected in the CLARA-MeD project, with the goal of | ||
| 27 | simplifying medical texts in the Spanish language and reduce the | 29 | simplifying medical texts in the Spanish language and reduce the | ||
| 28 | language barrier to patient's informed decision making. In particular, | 30 | language barrier to patient's informed decision making. In particular, | ||
| 29 | the project aims at developing linguistic resources for automatic | 31 | the project aims at developing linguistic resources for automatic | ||
| 30 | medical term simplification in Spanish; and conducting experiments in | 32 | medical term simplification in Spanish; and conducting experiments in | ||
| 31 | automatic text simplification." | 33 | automatic text simplification." | ||
| 32 | }, | 34 | }, | ||
| n | 33 | "groups": [], | n | 35 | "groups": [ |
| 36 | { | ||||
| 37 | "description": "", | ||||
| 38 | "display_name": "Terminolog\u00eda", | ||||
| 39 | "id": "f21d51d4-df60-44f9-ad1f-60f1d5ca24d2", | ||||
| 40 | "image_display_url": | ||||
| 41 | .cchs.csic.es/uploads/group/2024-09-27-062713.009717Terminologia.png", | ||||
| 42 | "name": "terminologia", | ||||
| 43 | "title": "Terminolog\u00eda" | ||||
| 44 | } | ||||
| 45 | ], | ||||
| 34 | "id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77", | 46 | "id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77", | ||
| 35 | "identifier": "https://doi.org/10.20350/digitalCSIC/16110", | 47 | "identifier": "https://doi.org/10.20350/digitalCSIC/16110", | ||
| n | n | 48 | "international_spatial_translated": {}, | ||
| 36 | "isopen": false, | 49 | "isopen": false, | ||
| 37 | "issued_date": "2024-02-09T00:00:00", | 50 | "issued_date": "2024-02-09T00:00:00", | ||
| 38 | "language": [ | 51 | "language": [ | ||
| 39 | "es", | 52 | "es", | ||
| 40 | "en" | 53 | "en" | ||
| 41 | ], | 54 | ], | ||
| 42 | "license_id": | 55 | "license_id": | ||
| 43 | "https://digital.csic.es/handle/10261/346579?mode=full", | 56 | "https://digital.csic.es/handle/10261/346579?mode=full", | ||
| 44 | "license_title": | 57 | "license_title": | ||
| 45 | "https://digital.csic.es/handle/10261/346579?mode=full", | 58 | "https://digital.csic.es/handle/10261/346579?mode=full", | ||
| 46 | "maintainer": null, | 59 | "maintainer": null, | ||
| 47 | "maintainer_email": null, | 60 | "maintainer_email": null, | ||
| 48 | "metadata_created": "2024-05-30T15:57:14.431217", | 61 | "metadata_created": "2024-05-30T15:57:14.431217", | ||
| n | 49 | "metadata_modified": "2024-05-30T16:05:15.774184", | n | 62 | "metadata_modified": "2025-02-25T10:54:05.255559", |
| 50 | "multilingual_tags": { | 63 | "multilingual_tags": { | ||
| 51 | "en": [ | 64 | "en": [ | ||
| 52 | "Biomedical natural language processing", | 65 | "Biomedical natural language processing", | ||
| 53 | "Parallel sentences", | 66 | "Parallel sentences", | ||
| 54 | "Medical text simplification" | 67 | "Medical text simplification" | ||
| 55 | ] | 68 | ] | ||
| 56 | }, | 69 | }, | ||
| 57 | "name": "clara-med-simplified-sentences", | 70 | "name": "clara-med-simplified-sentences", | ||
| 58 | "notes": null, | 71 | "notes": null, | ||
| 59 | "num_resources": 3, | 72 | "num_resources": 3, | ||
| 60 | "num_tags": 0, | 73 | "num_tags": 0, | ||
| 61 | "organization": { | 74 | "organization": { | ||
| 62 | "approval_status": "approved", | 75 | "approval_status": "approved", | ||
| 63 | "created": "2023-09-25T12:13:42.172869", | 76 | "created": "2023-09-25T12:13:42.172869", | ||
| 64 | "description": "El Instituto de Lengua, Literatura y | 77 | "description": "El Instituto de Lengua, Literatura y | ||
| 65 | Antropolog\u00eda, ILLA (CSIC) tiene como objetivo primordial la | 78 | Antropolog\u00eda, ILLA (CSIC) tiene como objetivo primordial la | ||
| 66 | investigaci\u00f3n del patrimonio cultural hisp\u00e1nico en su triple | 79 | investigaci\u00f3n del patrimonio cultural hisp\u00e1nico en su triple | ||
| 67 | dimensi\u00f3n antropol\u00f3gica, ling\u00fc\u00edstica y | 80 | dimensi\u00f3n antropol\u00f3gica, ling\u00fc\u00edstica y | ||
| 68 | literaria.", | 81 | literaria.", | ||
| 69 | "id": "fc47e531-a165-4eac-8fc7-34342a3a38ff", | 82 | "id": "fc47e531-a165-4eac-8fc7-34342a3a38ff", | ||
| 70 | "image_url": "2023-09-25-101342.167134illa0.png", | 83 | "image_url": "2023-09-25-101342.167134illa0.png", | ||
| 71 | "is_organization": true, | 84 | "is_organization": true, | ||
| 72 | "name": "instituto-de-lengua-literatura-y-antropologia-illa-csic", | 85 | "name": "instituto-de-lengua-literatura-y-antropologia-illa-csic", | ||
| 73 | "state": "active", | 86 | "state": "active", | ||
| 74 | "title": "Instituto de Lengua, Literatura y Antropolog\u00eda | 87 | "title": "Instituto de Lengua, Literatura y Antropolog\u00eda | ||
| 75 | (ILLA), CSIC", | 88 | (ILLA), CSIC", | ||
| 76 | "type": "organization" | 89 | "type": "organization" | ||
| 77 | }, | 90 | }, | ||
| 78 | "owner_org": "fc47e531-a165-4eac-8fc7-34342a3a38ff", | 91 | "owner_org": "fc47e531-a165-4eac-8fc7-34342a3a38ff", | ||
| 79 | "private": false, | 92 | "private": false, | ||
| n | n | 93 | "proyecto": {}, | ||
| 80 | "publisher": "fc47e531-a165-4eac-8fc7-34342a3a38ff", | 94 | "publisher": "fc47e531-a165-4eac-8fc7-34342a3a38ff", | ||
| 81 | "reference": [], | 95 | "reference": [], | ||
| 82 | "relationships_as_object": [], | 96 | "relationships_as_object": [], | ||
| 83 | "relationships_as_subject": [], | 97 | "relationships_as_subject": [], | ||
| 84 | "resources": [ | 98 | "resources": [ | ||
| n | n | 99 | { | ||
| 100 | "byte_size": "7,32 kB", | ||||
| 101 | "cache_last_updated": null, | ||||
| 102 | "cache_url": null, | ||||
| 103 | "created": "2024-05-30T15:58:24.249419", | ||||
| 104 | "datastore_active": false, | ||||
| 105 | "description": null, | ||||
| 106 | "format": "txt", | ||||
| 107 | "hash": "", | ||||
| 108 | "id": "30dfbb45-e41a-4c6e-bcdc-a4af2f040715", | ||||
| 109 | "last_modified": null, | ||||
| 110 | "metadata_modified": "2024-05-30T15:58:24.421759", | ||||
| 111 | "mimetype": "text/plain", | ||||
| 112 | "mimetype_inner": null, | ||||
| 113 | "name": "README_CLARAMED_sentences.txt\t", | ||||
| 114 | "name_translated": { | ||||
| 115 | "en": "README_CLARAMED_sentences.txt\t", | ||||
| 116 | "es": "README_CLARAMED_sentences.txt\t" | ||||
| 117 | }, | ||||
| 118 | "package_id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77", | ||||
| 119 | "position": 0, | ||||
| 120 | "resource_identifier": "", | ||||
| 121 | "resource_relation": [], | ||||
| 122 | "resource_relation-1": "", | ||||
| 123 | "resource_type": null, | ||||
| 124 | "size": null, | ||||
| 125 | "state": "active", | ||||
| 126 | "url": | ||||
| 127 | gital.csic.es/bitstream/10261/346579/6/README_CLARAMED_sentences.txt", | ||||
| 128 | "url_type": null | ||||
| 129 | }, | ||||
| 85 | { | 130 | { | ||
| 86 | "byte_size": "981,11 kB", | 131 | "byte_size": "981,11 kB", | ||
| 87 | "cache_last_updated": null, | 132 | "cache_last_updated": null, | ||
| 88 | "cache_url": null, | 133 | "cache_url": null, | ||
| 89 | "created": "2024-05-30T15:57:45.357301", | 134 | "created": "2024-05-30T15:57:45.357301", | ||
| 90 | "datastore_active": false, | 135 | "datastore_active": false, | ||
| 91 | "description": null, | 136 | "description": null, | ||
| 92 | "format": "tsv", | 137 | "format": "tsv", | ||
| 93 | "hash": "", | 138 | "hash": "", | ||
| 94 | "id": "a05fd101-9c06-4312-bb30-13f6ea008d46", | 139 | "id": "a05fd101-9c06-4312-bb30-13f6ea008d46", | ||
| 95 | "last_modified": null, | 140 | "last_modified": null, | ||
| 96 | "metadata_modified": "2024-05-30T15:58:24.247167", | 141 | "metadata_modified": "2024-05-30T15:58:24.247167", | ||
| 97 | "mimetype": "text/tab-separated-values", | 142 | "mimetype": "text/tab-separated-values", | ||
| 98 | "mimetype_inner": null, | 143 | "mimetype_inner": null, | ||
| 99 | "name": "Dataset | 144 | "name": "Dataset | ||
| 100 | ital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv", | 145 | ital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv", | ||
| 101 | "name_translated": { | 146 | "name_translated": { | ||
| 102 | "en": "Dataset | 147 | "en": "Dataset | ||
| 103 | ital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv", | 148 | ital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv", | ||
| 104 | "es": "Dataset | 149 | "es": "Dataset | ||
| 105 | gital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv" | 150 | gital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv" | ||
| 106 | }, | 151 | }, | ||
| 107 | "package_id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77", | 152 | "package_id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77", | ||
| n | 108 | "position": 0, | n | 153 | "position": 1, |
| 109 | "resource_identifier": "", | 154 | "resource_identifier": "", | ||
| 110 | "resource_relation": [], | 155 | "resource_relation": [], | ||
| 111 | "resource_relation-1": "", | 156 | "resource_relation-1": "", | ||
| 112 | "resource_type": null, | 157 | "resource_type": null, | ||
| 113 | "size": null, | 158 | "size": null, | ||
| 114 | "state": "active", | 159 | "state": "active", | ||
| 115 | "url": | 160 | "url": | ||
| 116 | ital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv", | 161 | ital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv", | ||
| 117 | "url_type": null | 162 | "url_type": null | ||
| 118 | }, | 163 | }, | ||
| 119 | { | 164 | { | ||
| 120 | "byte_size": "757,92 kB", | 165 | "byte_size": "757,92 kB", | ||
| 121 | "cache_last_updated": null, | 166 | "cache_last_updated": null, | ||
| 122 | "cache_url": null, | 167 | "cache_url": null, | ||
| 123 | "created": "2024-05-30T15:59:20.596413", | 168 | "created": "2024-05-30T15:59:20.596413", | ||
| 124 | "datastore_active": false, | 169 | "datastore_active": false, | ||
| 125 | "description": null, | 170 | "description": null, | ||
| 126 | "format": "pdf", | 171 | "format": "pdf", | ||
| 127 | "hash": "", | 172 | "hash": "", | ||
| 128 | "id": "a1f5a665-35a0-4513-8123-8e3feed8c66b", | 173 | "id": "a1f5a665-35a0-4513-8123-8e3feed8c66b", | ||
| 129 | "last_modified": null, | 174 | "last_modified": null, | ||
| 130 | "metadata_modified": "2024-05-30T15:59:40.961858", | 175 | "metadata_modified": "2024-05-30T15:59:40.961858", | ||
| 131 | "mimetype": "application/pdf", | 176 | "mimetype": "application/pdf", | ||
| 132 | "mimetype_inner": null, | 177 | "mimetype_inner": null, | ||
| 133 | "name": "Guideline CLARA-MeD_simplif_guideline.pdf", | 178 | "name": "Guideline CLARA-MeD_simplif_guideline.pdf", | ||
| 134 | "name_translated": { | 179 | "name_translated": { | ||
| 135 | "en": "Guideline CLARA-MeD_simplif_guideline.pdf", | 180 | "en": "Guideline CLARA-MeD_simplif_guideline.pdf", | ||
| 136 | "es": "Guideline CLARA-MeD_simplif_guideline.pdf" | 181 | "es": "Guideline CLARA-MeD_simplif_guideline.pdf" | ||
| 137 | }, | 182 | }, | ||
| 138 | "package_id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77", | 183 | "package_id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77", | ||
| n | 139 | "position": 1, | n | 184 | "position": 2, |
| 140 | "resource_identifier": "", | 185 | "resource_identifier": "", | ||
| 141 | "resource_relation": [], | 186 | "resource_relation": [], | ||
| 142 | "resource_relation-1": "", | 187 | "resource_relation-1": "", | ||
| 143 | "resource_type": null, | 188 | "resource_type": null, | ||
| 144 | "size": null, | 189 | "size": null, | ||
| 145 | "state": "active", | 190 | "state": "active", | ||
| 146 | "url": | 191 | "url": | ||
| 147 | tal.csic.es/bitstream/10261/346579/2/CLARA-MeD_simplif_guideline.pdf", | 192 | tal.csic.es/bitstream/10261/346579/2/CLARA-MeD_simplif_guideline.pdf", | ||
| t | 148 | "url_type": null | t | ||
| 149 | }, | ||||
| 150 | { | ||||
| 151 | "byte_size": "7,32 kB", | ||||
| 152 | "cache_last_updated": null, | ||||
| 153 | "cache_url": null, | ||||
| 154 | "created": "2024-05-30T15:58:24.249419", | ||||
| 155 | "datastore_active": false, | ||||
| 156 | "description": null, | ||||
| 157 | "format": "txt", | ||||
| 158 | "hash": "", | ||||
| 159 | "id": "30dfbb45-e41a-4c6e-bcdc-a4af2f040715", | ||||
| 160 | "last_modified": null, | ||||
| 161 | "metadata_modified": "2024-05-30T15:58:24.421759", | ||||
| 162 | "mimetype": "text/plain", | ||||
| 163 | "mimetype_inner": null, | ||||
| 164 | "name": "README_CLARAMED_sentences.txt\t", | ||||
| 165 | "name_translated": { | ||||
| 166 | "en": "README_CLARAMED_sentences.txt\t", | ||||
| 167 | "es": "README_CLARAMED_sentences.txt\t" | ||||
| 168 | }, | ||||
| 169 | "package_id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77", | ||||
| 170 | "position": 2, | ||||
| 171 | "resource_identifier": "", | ||||
| 172 | "resource_relation": [], | ||||
| 173 | "resource_relation-1": "", | ||||
| 174 | "resource_type": null, | ||||
| 175 | "size": null, | ||||
| 176 | "state": "active", | ||||
| 177 | "url": | ||||
| 178 | gital.csic.es/bitstream/10261/346579/6/README_CLARAMED_sentences.txt", | ||||
| 179 | "url_type": null | 193 | "url_type": null | ||
| 180 | } | 194 | } | ||
| 181 | ], | 195 | ], | ||
| 182 | "spatial": [], | 196 | "spatial": [], | ||
| 183 | "state": "active", | 197 | "state": "active", | ||
| 184 | "tags": [], | 198 | "tags": [], | ||
| 185 | "theme": [ | 199 | "theme": [ | ||
| 186 | 200 | ||||
| 187 | "http://datos.gob.es/kos/sector-publico/sector/ciencia-tecnologia", | 201 | "http://datos.gob.es/kos/sector-publico/sector/ciencia-tecnologia", | ||
| 188 | "http://datos.gob.es/kos/sector-publico/sector/cultura-ocio", | 202 | "http://datos.gob.es/kos/sector-publico/sector/cultura-ocio", | ||
| 189 | "http://datos.gob.es/kos/sector-publico/sector/educacion", | 203 | "http://datos.gob.es/kos/sector-publico/sector/educacion", | ||
| 190 | "http://datos.gob.es/kos/sector-publico/sector/salud", | 204 | "http://datos.gob.es/kos/sector-publico/sector/salud", | ||
| 191 | "http://datos.gob.es/kos/sector-publico/sector/sector-publico" | 205 | "http://datos.gob.es/kos/sector-publico/sector/sector-publico" | ||
| 192 | ], | 206 | ], | ||
| 193 | "title": "CLARA-MeD simplified sentences", | 207 | "title": "CLARA-MeD simplified sentences", | ||
| 194 | "title_translated": { | 208 | "title_translated": { | ||
| 195 | "en": "CLARA-MeD simplified sentences", | 209 | "en": "CLARA-MeD simplified sentences", | ||
| 196 | "es": "CLARA-MeD simplified sentences" | 210 | "es": "CLARA-MeD simplified sentences" | ||
| 197 | }, | 211 | }, | ||
| 198 | "type": "dataset", | 212 | "type": "dataset", | ||
| 199 | "url": null, | 213 | "url": null, | ||
| 200 | "version": null | 214 | "version": null | ||
| 201 | } | 215 | } |
