Cambios
En el instante 30 de mayo de 2024, 15:57:45 UTC, Administrador CKAN:
-
Añadido recurso Dataset https://digital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv a CLARA-MeD simplified sentences
f | 1 | { | f | 1 | { |
2 | "author": null, | 2 | "author": null, | ||
3 | "author_email": null, | 3 | "author_email": null, | ||
4 | "conforms_to": [], | 4 | "conforms_to": [], | ||
5 | "coverage_new": {}, | 5 | "coverage_new": {}, | ||
6 | "creator_user_id": "196556b3-e0c4-4c51-a9e6-f51cc752bc37", | 6 | "creator_user_id": "196556b3-e0c4-4c51-a9e6-f51cc752bc37", | ||
7 | "description": { | 7 | "description": { | ||
8 | "en": "This dataset contains 1200 manually simplified sentences | 8 | "en": "This dataset contains 1200 manually simplified sentences | ||
9 | (144 019 tokens) from clinical trials in Spanish. A total of 1040 | 9 | (144 019 tokens) from clinical trials in Spanish. A total of 1040 | ||
10 | announcements from the European Clinical Trials Register (EudraCT) | 10 | announcements from the European Clinical Trials Register (EudraCT) | ||
11 | were analyzed to select sentences with ambiguities or exceeding 25 | 11 | were analyzed to select sentences with ambiguities or exceeding 25 | ||
12 | words. Simplification criteria were devised in an annotation | 12 | words. Simplification criteria were devised in an annotation | ||
13 | guideline, which is released publicly along the dataset.\r\n\r\nThis | 13 | 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 | 14 | resource was collected in the CLARA-MeD project, with the goal of | ||
15 | simplifying medical texts in the Spanish language and reduce the | 15 | simplifying medical texts in the Spanish language and reduce the | ||
16 | language barrier to patient's informed decision making. In particular, | 16 | language barrier to patient's informed decision making. In particular, | ||
17 | the project aims at developing linguistic resources for automatic | 17 | the project aims at developing linguistic resources for automatic | ||
18 | medical term simplification in Spanish; and conducting experiments in | 18 | medical term simplification in Spanish; and conducting experiments in | ||
19 | automatic text simplification.", | 19 | automatic text simplification.", | ||
20 | "es": "This dataset contains 1200 manually simplified sentences | 20 | "es": "This dataset contains 1200 manually simplified sentences | ||
21 | (144 019 tokens) from clinical trials in Spanish. A total of 1040 | 21 | (144 019 tokens) from clinical trials in Spanish. A total of 1040 | ||
22 | announcements from the European Clinical Trials Register (EudraCT) | 22 | announcements from the European Clinical Trials Register (EudraCT) | ||
23 | were analyzed to select sentences with ambiguities or exceeding 25 | 23 | were analyzed to select sentences with ambiguities or exceeding 25 | ||
24 | words. Simplification criteria were devised in an annotation | 24 | words. Simplification criteria were devised in an annotation | ||
25 | guideline, which is released publicly along the dataset.\r\n\r\nThis | 25 | 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 | 26 | resource was collected in the CLARA-MeD project, with the goal of | ||
27 | simplifying medical texts in the Spanish language and reduce the | 27 | simplifying medical texts in the Spanish language and reduce the | ||
28 | language barrier to patient's informed decision making. In particular, | 28 | language barrier to patient's informed decision making. In particular, | ||
29 | the project aims at developing linguistic resources for automatic | 29 | the project aims at developing linguistic resources for automatic | ||
30 | medical term simplification in Spanish; and conducting experiments in | 30 | medical term simplification in Spanish; and conducting experiments in | ||
31 | automatic text simplification." | 31 | automatic text simplification." | ||
32 | }, | 32 | }, | ||
33 | "groups": [], | 33 | "groups": [], | ||
34 | "id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77", | 34 | "id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77", | ||
35 | "identifier": "https://doi.org/10.20350/digitalCSIC/16110", | 35 | "identifier": "https://doi.org/10.20350/digitalCSIC/16110", | ||
36 | "isopen": false, | 36 | "isopen": false, | ||
37 | "issued_date": "2024-02-09T00:00:00", | 37 | "issued_date": "2024-02-09T00:00:00", | ||
38 | "language": [ | 38 | "language": [ | ||
39 | "es", | 39 | "es", | ||
40 | "en" | 40 | "en" | ||
41 | ], | 41 | ], | ||
42 | "license_id": | 42 | "license_id": | ||
43 | "https://digital.csic.es/handle/10261/346579?mode=full", | 43 | "https://digital.csic.es/handle/10261/346579?mode=full", | ||
44 | "license_title": | 44 | "license_title": | ||
45 | "https://digital.csic.es/handle/10261/346579?mode=full", | 45 | "https://digital.csic.es/handle/10261/346579?mode=full", | ||
46 | "maintainer": null, | 46 | "maintainer": null, | ||
47 | "maintainer_email": null, | 47 | "maintainer_email": null, | ||
48 | "metadata_created": "2024-05-30T15:57:14.431217", | 48 | "metadata_created": "2024-05-30T15:57:14.431217", | ||
n | 49 | "metadata_modified": "2024-05-30T15:57:14.431221", | n | 49 | "metadata_modified": "2024-05-30T15:57:45.352676", |
50 | "multilingual_tags": { | 50 | "multilingual_tags": { | ||
51 | "en": [ | 51 | "en": [ | ||
52 | "Biomedical natural language processing", | 52 | "Biomedical natural language processing", | ||
53 | "Parallel sentences", | 53 | "Parallel sentences", | ||
54 | "Medical text simplification" | 54 | "Medical text simplification" | ||
55 | ], | 55 | ], | ||
56 | "es": [ | 56 | "es": [ | ||
57 | "Biomedical natural language processing", | 57 | "Biomedical natural language processing", | ||
58 | "Parallel sentences", | 58 | "Parallel sentences", | ||
59 | "Medical text simplification" | 59 | "Medical text simplification" | ||
60 | ] | 60 | ] | ||
61 | }, | 61 | }, | ||
62 | "name": "clara-med-simplified-sentences", | 62 | "name": "clara-med-simplified-sentences", | ||
63 | "notes": null, | 63 | "notes": null, | ||
n | 64 | "num_resources": 0, | n | 64 | "num_resources": 1, |
65 | "num_tags": 0, | 65 | "num_tags": 0, | ||
66 | "organization": { | 66 | "organization": { | ||
67 | "approval_status": "approved", | 67 | "approval_status": "approved", | ||
68 | "created": "2023-09-25T12:13:42.172869", | 68 | "created": "2023-09-25T12:13:42.172869", | ||
69 | "description": "El Instituto de Lengua, Literatura y | 69 | "description": "El Instituto de Lengua, Literatura y | ||
70 | Antropolog\u00eda, ILLA (CSIC) tiene como objetivo primordial la | 70 | Antropolog\u00eda, ILLA (CSIC) tiene como objetivo primordial la | ||
71 | investigaci\u00f3n del patrimonio cultural hisp\u00e1nico en su triple | 71 | investigaci\u00f3n del patrimonio cultural hisp\u00e1nico en su triple | ||
72 | dimensi\u00f3n antropol\u00f3gica, ling\u00fc\u00edstica y | 72 | dimensi\u00f3n antropol\u00f3gica, ling\u00fc\u00edstica y | ||
73 | literaria.", | 73 | literaria.", | ||
74 | "id": "fc47e531-a165-4eac-8fc7-34342a3a38ff", | 74 | "id": "fc47e531-a165-4eac-8fc7-34342a3a38ff", | ||
75 | "image_url": "2023-09-25-101342.167134illa0.png", | 75 | "image_url": "2023-09-25-101342.167134illa0.png", | ||
76 | "is_organization": true, | 76 | "is_organization": true, | ||
77 | "name": "instituto-de-lengua-literatura-y-antropologia-illa-csic", | 77 | "name": "instituto-de-lengua-literatura-y-antropologia-illa-csic", | ||
78 | "state": "active", | 78 | "state": "active", | ||
79 | "title": "Instituto de Lengua, Literatura y Antropolog\u00eda | 79 | "title": "Instituto de Lengua, Literatura y Antropolog\u00eda | ||
80 | (ILLA), CSIC", | 80 | (ILLA), CSIC", | ||
81 | "type": "organization" | 81 | "type": "organization" | ||
82 | }, | 82 | }, | ||
83 | "owner_org": "fc47e531-a165-4eac-8fc7-34342a3a38ff", | 83 | "owner_org": "fc47e531-a165-4eac-8fc7-34342a3a38ff", | ||
84 | "private": false, | 84 | "private": false, | ||
85 | "publisher": "fc47e531-a165-4eac-8fc7-34342a3a38ff", | 85 | "publisher": "fc47e531-a165-4eac-8fc7-34342a3a38ff", | ||
86 | "reference": [], | 86 | "reference": [], | ||
87 | "relationships_as_object": [], | 87 | "relationships_as_object": [], | ||
88 | "relationships_as_subject": [], | 88 | "relationships_as_subject": [], | ||
t | 89 | "resources": [], | t | 89 | "resources": [ |
90 | { | ||||
91 | "byte_size": "981,11 kB", | ||||
92 | "cache_last_updated": null, | ||||
93 | "cache_url": null, | ||||
94 | "created": "2024-05-30T15:57:45.357301", | ||||
95 | "datastore_active": false, | ||||
96 | "description": null, | ||||
97 | "format": "tsv", | ||||
98 | "hash": "", | ||||
99 | "id": "a05fd101-9c06-4312-bb30-13f6ea008d46", | ||||
100 | "last_modified": null, | ||||
101 | "metadata_modified": "2024-05-30T15:57:45.355001", | ||||
102 | "mimetype": "text/tab-separated-values", | ||||
103 | "mimetype_inner": null, | ||||
104 | "name": "Dataset | ||||
105 | ital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv", | ||||
106 | "name_translated": { | ||||
107 | "en": "Dataset | ||||
108 | ital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv", | ||||
109 | "es": "Dataset | ||||
110 | gital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv" | ||||
111 | }, | ||||
112 | "package_id": "73cc4b2b-f43c-4efd-9d6d-113bc923cd77", | ||||
113 | "position": 0, | ||||
114 | "resource_identifier": "", | ||||
115 | "resource_relation": [], | ||||
116 | "resource_relation-1": "", | ||||
117 | "resource_type": null, | ||||
118 | "size": null, | ||||
119 | "state": "active", | ||||
120 | "url": | ||||
121 | ital.csic.es/bitstream/10261/346579/1/claramed_synt_simp_aligned.tsv", | ||||
122 | "url_type": null | ||||
123 | } | ||||
124 | ], | ||||
90 | "spatial": [], | 125 | "spatial": [], | ||
91 | "state": "draft", | 126 | "state": "draft", | ||
92 | "tags": [], | 127 | "tags": [], | ||
93 | "theme": [ | 128 | "theme": [ | ||
94 | 129 | ||||
95 | "http://datos.gob.es/kos/sector-publico/sector/ciencia-tecnologia", | 130 | "http://datos.gob.es/kos/sector-publico/sector/ciencia-tecnologia", | ||
96 | "http://datos.gob.es/kos/sector-publico/sector/cultura-ocio", | 131 | "http://datos.gob.es/kos/sector-publico/sector/cultura-ocio", | ||
97 | "http://datos.gob.es/kos/sector-publico/sector/educacion", | 132 | "http://datos.gob.es/kos/sector-publico/sector/educacion", | ||
98 | "http://datos.gob.es/kos/sector-publico/sector/salud", | 133 | "http://datos.gob.es/kos/sector-publico/sector/salud", | ||
99 | "http://datos.gob.es/kos/sector-publico/sector/sector-publico" | 134 | "http://datos.gob.es/kos/sector-publico/sector/sector-publico" | ||
100 | ], | 135 | ], | ||
101 | "title": "CLARA-MeD simplified sentences", | 136 | "title": "CLARA-MeD simplified sentences", | ||
102 | "title_translated": { | 137 | "title_translated": { | ||
103 | "en": "CLARA-MeD simplified sentences", | 138 | "en": "CLARA-MeD simplified sentences", | ||
104 | "es": "CLARA-MeD simplified sentences" | 139 | "es": "CLARA-MeD simplified sentences" | ||
105 | }, | 140 | }, | ||
106 | "type": "dataset", | 141 | "type": "dataset", | ||
107 | "url": null, | 142 | "url": null, | ||
108 | "version": null | 143 | "version": null | ||
109 | } | 144 | } |