Cambios
En el instante 4 de marzo de 2025, 16:38:15 UTC,

-
Añadido recurso README.txt a CLARA-MeD corpus
f | 1 | { | f | 1 | { |
2 | "Observaciones": { | 2 | "Observaciones": { | ||
3 | "en": "Recommended citation for this dataset: Campillos-Llanos, | 3 | "en": "Recommended citation for this dataset: Campillos-Llanos, | ||
4 | Leonardo; Terroba Reinares, Ana Rosa; Zakhir Puig, Sof\u00eda; | 4 | Leonardo; Terroba Reinares, Ana Rosa; Zakhir Puig, Sof\u00eda; | ||
5 | Valverde Mateos, Ana; Capllonch Carri\u00f3n, Adri\u00e1n; 2022; | 5 | Valverde Mateos, Ana; Capllonch Carri\u00f3n, Adri\u00e1n; 2022; | ||
6 | CLARA-MeD corpus [Dataset]; DIGITAL.CSIC; | 6 | CLARA-MeD corpus [Dataset]; DIGITAL.CSIC; | ||
7 | https://doi.org/10.20350/digitalCSIC/14644", | 7 | https://doi.org/10.20350/digitalCSIC/14644", | ||
8 | "es": "Cita recomendada: Campillos-Llanos, Leonardo; Terroba | 8 | "es": "Cita recomendada: Campillos-Llanos, Leonardo; Terroba | ||
9 | Reinares, Ana Rosa; Zakhir Puig, Sof\u00eda; Valverde Mateos, Ana; | 9 | Reinares, Ana Rosa; Zakhir Puig, Sof\u00eda; Valverde Mateos, Ana; | ||
10 | Capllonch Carri\u00f3n, Adri\u00e1n; 2022; CLARA-MeD corpus [Dataset]; | 10 | Capllonch Carri\u00f3n, Adri\u00e1n; 2022; CLARA-MeD corpus [Dataset]; | ||
11 | DIGITAL.CSIC; https://doi.org/10.20350/digitalCSIC/14644" | 11 | DIGITAL.CSIC; https://doi.org/10.20350/digitalCSIC/14644" | ||
12 | }, | 12 | }, | ||
13 | "author": null, | 13 | "author": null, | ||
14 | "author_email": null, | 14 | "author_email": null, | ||
15 | "autor": { | 15 | "autor": { | ||
16 | "en": [ | 16 | "en": [ | ||
17 | "Leonardo Campillos-Llanos", | 17 | "Leonardo Campillos-Llanos", | ||
18 | "Ana Rosa Terroba Reinares", | 18 | "Ana Rosa Terroba Reinares", | ||
19 | "Sof\u00eda Zakhir Puig", | 19 | "Sof\u00eda Zakhir Puig", | ||
20 | "Ana Valverde Mateos", | 20 | "Ana Valverde Mateos", | ||
21 | "Adri\u00e1n Capllonch Carri\u00f3n" | 21 | "Adri\u00e1n Capllonch Carri\u00f3n" | ||
22 | ], | 22 | ], | ||
23 | "es": [ | 23 | "es": [ | ||
24 | "Leonardo Campillos-Llanos", | 24 | "Leonardo Campillos-Llanos", | ||
25 | "Ana Rosa Terroba Reinares", | 25 | "Ana Rosa Terroba Reinares", | ||
26 | "Sof\u00eda Zakhir Puig", | 26 | "Sof\u00eda Zakhir Puig", | ||
27 | "Ana Valverde Mateos", | 27 | "Ana Valverde Mateos", | ||
28 | "Adri\u00e1n Capllonch Carri\u00f3n" | 28 | "Adri\u00e1n Capllonch Carri\u00f3n" | ||
29 | ] | 29 | ] | ||
30 | }, | 30 | }, | ||
31 | "conforms_to": [], | 31 | "conforms_to": [], | ||
32 | "coverage_new": {}, | 32 | "coverage_new": {}, | ||
33 | "creator_user_id": "196556b3-e0c4-4c51-a9e6-f51cc752bc37", | 33 | "creator_user_id": "196556b3-e0c4-4c51-a9e6-f51cc752bc37", | ||
34 | "description": { | 34 | "description": { | ||
35 | "en": "A collection of 24.298 pairs of professional and simplified | 35 | "en": "A collection of 24.298 pairs of professional and simplified | ||
36 | texts (>96 million tokens): 1) Drug leaflets and summaries of product | 36 | texts (>96 million tokens): 1) Drug leaflets and summaries of product | ||
37 | characteristics (10 211 pairs of texts, >82M words); 2) Cancer-related | 37 | characteristics (10 211 pairs of texts, >82M words); 2) Cancer-related | ||
38 | information summaries (201 pairs of texts, >3M tokens); and 2) | 38 | information summaries (201 pairs of texts, >3M tokens); and 2) | ||
39 | Clinical trials announcements (5748 pairs of texts, 451 690 tokens). | 39 | Clinical trials announcements (5748 pairs of texts, 451 690 tokens). | ||
40 | The dataset also contains a parallel corpus with a subset of 3800 | 40 | The dataset also contains a parallel corpus with a subset of 3800 | ||
41 | sentence pairs of professional and laymen variants (149 862 tokens). | 41 | sentence pairs of professional and laymen variants (149 862 tokens). | ||
42 | This is a benchmark for medical text simplification. The latest | 42 | This is a benchmark for medical text simplification. The latest | ||
43 | download of files was in February 2022.", | 43 | download of files was in February 2022.", | ||
44 | "es": "A collection of 24.298 pairs of professional and simplified | 44 | "es": "A collection of 24.298 pairs of professional and simplified | ||
45 | texts (>96 million tokens): 1) Drug leaflets and summaries of product | 45 | texts (>96 million tokens): 1) Drug leaflets and summaries of product | ||
46 | characteristics (10 211 pairs of texts, >82M words); 2) Cancer-related | 46 | characteristics (10 211 pairs of texts, >82M words); 2) Cancer-related | ||
47 | information summaries (201 pairs of texts, >3M tokens); and 2) | 47 | information summaries (201 pairs of texts, >3M tokens); and 2) | ||
48 | Clinical trials announcements (5748 pairs of texts, 451 690 tokens). | 48 | Clinical trials announcements (5748 pairs of texts, 451 690 tokens). | ||
49 | The dataset also contains a parallel corpus with a subset of 3800 | 49 | The dataset also contains a parallel corpus with a subset of 3800 | ||
50 | sentence pairs of professional and laymen variants (149 862 tokens). | 50 | sentence pairs of professional and laymen variants (149 862 tokens). | ||
51 | This is a benchmark for medical text simplification. The latest | 51 | This is a benchmark for medical text simplification. The latest | ||
52 | download of files was in February 2022." | 52 | download of files was in February 2022." | ||
53 | }, | 53 | }, | ||
54 | "groups": [], | 54 | "groups": [], | ||
55 | "id": "0a3879bf-01f2-40ec-902c-5f059ce1a141", | 55 | "id": "0a3879bf-01f2-40ec-902c-5f059ce1a141", | ||
56 | "identifier": "http://hdl.handle.net/10261/269887", | 56 | "identifier": "http://hdl.handle.net/10261/269887", | ||
57 | "international_spatial_translated": { | 57 | "international_spatial_translated": { | ||
58 | "en": "Europe (data from EudraCT) and United States of America | 58 | "en": "Europe (data from EudraCT) and United States of America | ||
59 | (data from NCI)", | 59 | (data from NCI)", | ||
60 | "es": "Europa y Estados Unidos" | 60 | "es": "Europa y Estados Unidos" | ||
61 | }, | 61 | }, | ||
62 | "isopen": false, | 62 | "isopen": false, | ||
63 | "issued_date": "2022-05-19T00:00:00", | 63 | "issued_date": "2022-05-19T00:00:00", | ||
64 | "language": [ | 64 | "language": [ | ||
65 | "es", | 65 | "es", | ||
66 | "en" | 66 | "en" | ||
67 | ], | 67 | ], | ||
68 | "license_id": | 68 | "license_id": | ||
69 | "\thttps://creativecommons.org/licenses/by-nc-sa/4.0/", | 69 | "\thttps://creativecommons.org/licenses/by-nc-sa/4.0/", | ||
70 | "license_title": | 70 | "license_title": | ||
71 | "\thttps://creativecommons.org/licenses/by-nc-sa/4.0/", | 71 | "\thttps://creativecommons.org/licenses/by-nc-sa/4.0/", | ||
72 | "maintainer": null, | 72 | "maintainer": null, | ||
73 | "maintainer_email": null, | 73 | "maintainer_email": null, | ||
74 | "metadata_created": "2025-03-04T16:37:34.111951", | 74 | "metadata_created": "2025-03-04T16:37:34.111951", | ||
n | 75 | "metadata_modified": "2025-03-04T16:37:34.111955", | n | 75 | "metadata_modified": "2025-03-04T16:38:15.609457", |
76 | "modified_date": "2022-05-19T00:00:00", | 76 | "modified_date": "2022-05-19T00:00:00", | ||
77 | "multilingual_tags": { | 77 | "multilingual_tags": { | ||
78 | "en": [ | 78 | "en": [ | ||
79 | "Comparable corpus", | 79 | "Comparable corpus", | ||
80 | "Parallel sentences", | 80 | "Parallel sentences", | ||
81 | "Medical text simplification", | 81 | "Medical text simplification", | ||
82 | "Biomedical natural language processing" | 82 | "Biomedical natural language processing" | ||
83 | ], | 83 | ], | ||
84 | "es": [ | 84 | "es": [ | ||
85 | "Comparable corpus", | 85 | "Comparable corpus", | ||
86 | "Parallel sentences", | 86 | "Parallel sentences", | ||
87 | "Medical text simplification" | 87 | "Medical text simplification" | ||
88 | ] | 88 | ] | ||
89 | }, | 89 | }, | ||
90 | "name": "clara-med-corpus", | 90 | "name": "clara-med-corpus", | ||
91 | "notes": null, | 91 | "notes": null, | ||
n | 92 | "num_resources": 0, | n | 92 | "num_resources": 1, |
93 | "num_tags": 0, | 93 | "num_tags": 0, | ||
94 | "organization": { | 94 | "organization": { | ||
95 | "approval_status": "approved", | 95 | "approval_status": "approved", | ||
96 | "created": "2023-09-25T12:13:42.172869", | 96 | "created": "2023-09-25T12:13:42.172869", | ||
97 | "description": "El Instituto de Lengua, Literatura y | 97 | "description": "El Instituto de Lengua, Literatura y | ||
98 | Antropolog\u00eda, ILLA (CSIC) tiene como objetivo primordial la | 98 | Antropolog\u00eda, ILLA (CSIC) tiene como objetivo primordial la | ||
99 | investigaci\u00f3n del patrimonio cultural hisp\u00e1nico en su triple | 99 | investigaci\u00f3n del patrimonio cultural hisp\u00e1nico en su triple | ||
100 | dimensi\u00f3n antropol\u00f3gica, ling\u00fc\u00edstica y | 100 | dimensi\u00f3n antropol\u00f3gica, ling\u00fc\u00edstica y | ||
101 | literaria.", | 101 | literaria.", | ||
102 | "id": "fc47e531-a165-4eac-8fc7-34342a3a38ff", | 102 | "id": "fc47e531-a165-4eac-8fc7-34342a3a38ff", | ||
103 | "image_url": "2023-09-25-101342.167134illa0.png", | 103 | "image_url": "2023-09-25-101342.167134illa0.png", | ||
104 | "is_organization": true, | 104 | "is_organization": true, | ||
105 | "name": "instituto-de-lengua-literatura-y-antropologia-illa-csic", | 105 | "name": "instituto-de-lengua-literatura-y-antropologia-illa-csic", | ||
106 | "state": "active", | 106 | "state": "active", | ||
107 | "title": "Instituto de Lengua, Literatura y Antropolog\u00eda | 107 | "title": "Instituto de Lengua, Literatura y Antropolog\u00eda | ||
108 | (ILLA), CSIC", | 108 | (ILLA), CSIC", | ||
109 | "type": "organization" | 109 | "type": "organization" | ||
110 | }, | 110 | }, | ||
111 | "owner_org": "fc47e531-a165-4eac-8fc7-34342a3a38ff", | 111 | "owner_org": "fc47e531-a165-4eac-8fc7-34342a3a38ff", | ||
112 | "private": false, | 112 | "private": false, | ||
113 | "proyecto": {}, | 113 | "proyecto": {}, | ||
114 | "publisher": "b627d71d-2315-4e75-afc9-897da84459f0", | 114 | "publisher": "b627d71d-2315-4e75-afc9-897da84459f0", | ||
115 | "reference": [], | 115 | "reference": [], | ||
116 | "relationships_as_object": [], | 116 | "relationships_as_object": [], | ||
117 | "relationships_as_subject": [], | 117 | "relationships_as_subject": [], | ||
t | 118 | "resources": [], | t | 118 | "resources": [ |
119 | { | ||||
120 | "byte_size": "8,1 kB", | ||||
121 | "cache_last_updated": null, | ||||
122 | "cache_url": null, | ||||
123 | "created": "2025-03-04T16:38:15.618921", | ||||
124 | "datastore_active": false, | ||||
125 | "description": null, | ||||
126 | "format": "txt", | ||||
127 | "hash": "", | ||||
128 | "id": "084fe5a6-500d-4d1c-a87e-1e764b61c3a2", | ||||
129 | "last_modified": null, | ||||
130 | "metadata_modified": "2025-03-04T16:38:15.613454", | ||||
131 | "mimetype": "text/plain", | ||||
132 | "mimetype_inner": null, | ||||
133 | "name": "README.txt", | ||||
134 | "name_translated": { | ||||
135 | "en": "README.txt", | ||||
136 | "es": "README.txt" | ||||
137 | }, | ||||
138 | "package_id": "0a3879bf-01f2-40ec-902c-5f059ce1a141", | ||||
139 | "position": 0, | ||||
140 | "resource_identifier": | ||||
141 | "https://digital.csic.es/bitstream/10261/269887/4/README.txt", | ||||
142 | "resource_relation": [], | ||||
143 | "resource_relation-1": "", | ||||
144 | "resource_type": null, | ||||
145 | "size": null, | ||||
146 | "state": "active", | ||||
147 | "url": | ||||
148 | "https://digital.csic.es/bitstream/10261/269887/4/README.txt", | ||||
149 | "url_type": null | ||||
150 | } | ||||
151 | ], | ||||
119 | "spatial": [ | 152 | "spatial": [ | ||
120 | 153 | ||||
121 | ttp://datos.gob.es/recurso/sector-publico/territorio/Pais/Espa\u00f1a" | 154 | ttp://datos.gob.es/recurso/sector-publico/territorio/Pais/Espa\u00f1a" | ||
122 | ], | 155 | ], | ||
123 | "state": "draft", | 156 | "state": "draft", | ||
124 | "tags": [], | 157 | "tags": [], | ||
125 | "theme": [ | 158 | "theme": [ | ||
126 | 159 | ||||
127 | "http://datos.gob.es/kos/sector-publico/sector/ciencia-tecnologia", | 160 | "http://datos.gob.es/kos/sector-publico/sector/ciencia-tecnologia", | ||
128 | "http://datos.gob.es/kos/sector-publico/sector/salud" | 161 | "http://datos.gob.es/kos/sector-publico/sector/salud" | ||
129 | ], | 162 | ], | ||
130 | "title": "CLARA-MeD corpus", | 163 | "title": "CLARA-MeD corpus", | ||
131 | "title_translated": { | 164 | "title_translated": { | ||
132 | "en": "CLARA-MeD corpus", | 165 | "en": "CLARA-MeD corpus", | ||
133 | "es": "CLARA-MeD corpus" | 166 | "es": "CLARA-MeD corpus" | ||
134 | }, | 167 | }, | ||
135 | "type": "dataset", | 168 | "type": "dataset", | ||
136 | "url": null, | 169 | "url": null, | ||
137 | "version": null | 170 | "version": null | ||
138 | } | 171 | } |