Changes
On 9 Ağustos 2022 15:24:35 UTC, Alp Öktem:
-
Updated description of Şalom Ladino articles text corpus from
397 articles from the Judeo-Espanyol section of Şalom newspaper. https://www.salom.com.tr/haberler/17/judeo-espanyol Original sentences and articles belong to Şalom. Corpus is compiled by Col·lectivaT. 176,843 words
to397 articles from the Judeo-Espanyol section of Şalom newspaper. https://www.salom.com.tr/haberler/17/judeo-espanyol Original sentences and articles belong to Şalom. Corpus is compiled by Col·lectivaT. Size: 176,843 words This dataset is created as part of project "Judeo-Spanish: Connecting the two ends of the Mediterranean" carried out by Col·lectivaT and Sephardic Center of Istanbul within the framework of the “Grant Scheme for Common Cultural Heritage: Preservation and Dialogue between Turkey and the EU–II (CCH-II)” implemented by the Ministry of Culture and Tourism of the Republic of Turkey with the financial support of the European Union. The content of this website is the sole responsibility of Col·lectivaT and does not necessarily reflect the views of the European Union.
f | 1 | { | f | 1 | { |
2 | "author": "", | 2 | "author": "", | ||
3 | "author_email": "", | 3 | "author_email": "", | ||
4 | "creator_user_id": "e2c0a7cf-664c-4ccf-9ab5-93c9eb1458b1", | 4 | "creator_user_id": "e2c0a7cf-664c-4ccf-9ab5-93c9eb1458b1", | ||
5 | "extras": [ | 5 | "extras": [ | ||
6 | { | 6 | { | ||
7 | "key": "image_url", | 7 | "key": "image_url", | ||
8 | "value": | 8 | "value": | ||
9 | //sefarad.com.tr/wp-content/uploads/2020/05/salom-makaleleri-yazi.png" | 9 | //sefarad.com.tr/wp-content/uploads/2020/05/salom-makaleleri-yazi.png" | ||
10 | } | 10 | } | ||
11 | ], | 11 | ], | ||
12 | "groups": [], | 12 | "groups": [], | ||
13 | "id": "d3a7700c-aa5d-4d45-8a55-c9bdf137e448", | 13 | "id": "d3a7700c-aa5d-4d45-8a55-c9bdf137e448", | ||
14 | "isopen": true, | 14 | "isopen": true, | ||
15 | "license_id": "cc-by", | 15 | "license_id": "cc-by", | ||
16 | "license_title": "Creative Commons Attribution", | 16 | "license_title": "Creative Commons Attribution", | ||
17 | "license_url": "http://www.opendefinition.org/licenses/cc-by", | 17 | "license_url": "http://www.opendefinition.org/licenses/cc-by", | ||
18 | "maintainer": "", | 18 | "maintainer": "", | ||
19 | "maintainer_email": "", | 19 | "maintainer_email": "", | ||
20 | "metadata_created": "2022-08-09T08:55:49.053157", | 20 | "metadata_created": "2022-08-09T08:55:49.053157", | ||
n | 21 | "metadata_modified": "2022-08-09T15:01:32.983045", | n | 21 | "metadata_modified": "2022-08-09T15:24:35.815391", |
22 | "name": "salom-ladino-articles-text-corpus", | 22 | "name": "salom-ladino-articles-text-corpus", | ||
23 | "notes": "397 articles from the Judeo-Espanyol section of \u015ealom | 23 | "notes": "397 articles from the Judeo-Espanyol section of \u015ealom | ||
24 | newspaper. | 24 | newspaper. | ||
25 | https://www.salom.com.tr/haberler/17/judeo-espanyol\r\nOriginal | 25 | https://www.salom.com.tr/haberler/17/judeo-espanyol\r\nOriginal | ||
26 | sentences and articles belong to \u015ealom. Corpus is compiled by | 26 | sentences and articles belong to \u015ealom. Corpus is compiled by | ||
t | 27 | Col\u00b7lectivaT. \r\n176,843 words", | t | 27 | Col\u00b7lectivaT. \r\n\r\nSize: 176,843 words\r\n\r\nThis dataset is |
28 | created as part of project \"Judeo-Spanish: Connecting the two ends of | ||||
29 | the Mediterranean\" carried out by Col\u00b7lectivaT and Sephardic | ||||
30 | Center of Istanbul within the framework of the \u201cGrant Scheme for | ||||
31 | Common Cultural Heritage: Preservation and Dialogue between Turkey and | ||||
32 | the EU\u2013II (CCH-II)\u201d implemented by the Ministry of Culture | ||||
33 | and Tourism of the Republic of Turkey with the financial support of | ||||
34 | the European Union. The content of this website is the sole | ||||
35 | responsibility of Col\u00b7lectivaT and does not necessarily reflect | ||||
36 | the views of the European Union.", | ||||
28 | "num_resources": 2, | 37 | "num_resources": 2, | ||
29 | "num_tags": 0, | 38 | "num_tags": 0, | ||
30 | "organization": { | 39 | "organization": { | ||
31 | "approval_status": "approved", | 40 | "approval_status": "approved", | ||
32 | "created": "2022-08-09T08:55:19.044966", | 41 | "created": "2022-08-09T08:55:19.044966", | ||
33 | "description": "Col\u00b7lectivaT is a non-profit cooperative | 42 | "description": "Col\u00b7lectivaT is a non-profit cooperative | ||
34 | formed by knowledge workers that provides all-around services of | 43 | formed by knowledge workers that provides all-around services of | ||
35 | cultural translation, research and technological services for | 44 | cultural translation, research and technological services for | ||
36 | collaborative and linguistic work.", | 45 | collaborative and linguistic work.", | ||
37 | "id": "0510debc-4a80-4144-b198-def8e40d28d9", | 46 | "id": "0510debc-4a80-4144-b198-def8e40d28d9", | ||
38 | "image_url": "https://collectivat.cat/img/logo_sm.png", | 47 | "image_url": "https://collectivat.cat/img/logo_sm.png", | ||
39 | "is_organization": true, | 48 | "is_organization": true, | ||
40 | "name": "col-lectivat", | 49 | "name": "col-lectivat", | ||
41 | "state": "active", | 50 | "state": "active", | ||
42 | "title": "Col\u00b7lectivaT", | 51 | "title": "Col\u00b7lectivaT", | ||
43 | "type": "organization" | 52 | "type": "organization" | ||
44 | }, | 53 | }, | ||
45 | "owner_org": "0510debc-4a80-4144-b198-def8e40d28d9", | 54 | "owner_org": "0510debc-4a80-4144-b198-def8e40d28d9", | ||
46 | "private": false, | 55 | "private": false, | ||
47 | "relationships_as_object": [], | 56 | "relationships_as_object": [], | ||
48 | "relationships_as_subject": [], | 57 | "relationships_as_subject": [], | ||
49 | "resources": [ | 58 | "resources": [ | ||
50 | { | 59 | { | ||
51 | "cache_last_updated": null, | 60 | "cache_last_updated": null, | ||
52 | "cache_url": null, | 61 | "cache_url": null, | ||
53 | "created": "2022-08-09T08:56:20.635252", | 62 | "created": "2022-08-09T08:56:20.635252", | ||
54 | "description": "", | 63 | "description": "", | ||
55 | "format": "TXT", | 64 | "format": "TXT", | ||
56 | "hash": "", | 65 | "hash": "", | ||
57 | "id": "65f63f6d-7091-43fe-a4bc-319eba2d238e", | 66 | "id": "65f63f6d-7091-43fe-a4bc-319eba2d238e", | ||
58 | "last_modified": "2022-08-09T08:56:20.616483", | 67 | "last_modified": "2022-08-09T08:56:20.616483", | ||
59 | "metadata_modified": "2022-08-09T15:01:32.985954", | 68 | "metadata_modified": "2022-08-09T15:01:32.985954", | ||
60 | "mimetype": "text/plain", | 69 | "mimetype": "text/plain", | ||
61 | "mimetype_inner": null, | 70 | "mimetype_inner": null, | ||
62 | "name": "Salom text corpus", | 71 | "name": "Salom text corpus", | ||
63 | "package_id": "d3a7700c-aa5d-4d45-8a55-c9bdf137e448", | 72 | "package_id": "d3a7700c-aa5d-4d45-8a55-c9bdf137e448", | ||
64 | "position": 0, | 73 | "position": 0, | ||
65 | "resource_type": null, | 74 | "resource_type": null, | ||
66 | "size": 991480, | 75 | "size": 991480, | ||
67 | "state": "active", | 76 | "state": "active", | ||
68 | "url": | 77 | "url": | ||
69 | ba2d238e/download/salom-ladino-2022-01-ext-04_segmented_shuffled.txt", | 78 | ba2d238e/download/salom-ladino-2022-01-ext-04_segmented_shuffled.txt", | ||
70 | "url_type": "upload" | 79 | "url_type": "upload" | ||
71 | }, | 80 | }, | ||
72 | { | 81 | { | ||
73 | "cache_last_updated": null, | 82 | "cache_last_updated": null, | ||
74 | "cache_url": null, | 83 | "cache_url": null, | ||
75 | "created": "2022-08-09T15:01:13.471068", | 84 | "created": "2022-08-09T15:01:13.471068", | ||
76 | "description": "", | 85 | "description": "", | ||
77 | "format": "TXT", | 86 | "format": "TXT", | ||
78 | "hash": "", | 87 | "hash": "", | ||
79 | "id": "13c1287b-971d-4e38-a376-5c7a297e6e49", | 88 | "id": "13c1287b-971d-4e38-a376-5c7a297e6e49", | ||
80 | "last_modified": null, | 89 | "last_modified": null, | ||
81 | "metadata_modified": "2022-08-09T15:01:13.466631", | 90 | "metadata_modified": "2022-08-09T15:01:13.466631", | ||
82 | "mimetype": "text/plain", | 91 | "mimetype": "text/plain", | ||
83 | "mimetype_inner": null, | 92 | "mimetype_inner": null, | ||
84 | "name": "Salom text corpus (External link)", | 93 | "name": "Salom text corpus (External link)", | ||
85 | "package_id": "d3a7700c-aa5d-4d45-8a55-c9bdf137e448", | 94 | "package_id": "d3a7700c-aa5d-4d45-8a55-c9bdf137e448", | ||
86 | "position": 1, | 95 | "position": 1, | ||
87 | "resource_type": null, | 96 | "resource_type": null, | ||
88 | "size": null, | 97 | "size": null, | ||
89 | "state": "active", | 98 | "state": "active", | ||
90 | "url": | 99 | "url": | ||
91 | ectivat.cat/share/Salom-ladino-2022-01-ext-04_segmented_shuffled.txt", | 100 | ectivat.cat/share/Salom-ladino-2022-01-ext-04_segmented_shuffled.txt", | ||
92 | "url_type": null | 101 | "url_type": null | ||
93 | } | 102 | } | ||
94 | ], | 103 | ], | ||
95 | "state": "active", | 104 | "state": "active", | ||
96 | "tags": [], | 105 | "tags": [], | ||
97 | "title": "\u015ealom Ladino articles text corpus", | 106 | "title": "\u015ealom Ladino articles text corpus", | ||
98 | "type": "dataset", | 107 | "type": "dataset", | ||
99 | "url": "", | 108 | "url": "", | ||
100 | "version": "" | 109 | "version": "" | ||
101 | } | 110 | } |