f | { | f | { |
| "author": "", | | "author": "", |
| "author_email": "", | | "author_email": "", |
| "creator_user_id": "e2c0a7cf-664c-4ccf-9ab5-93c9eb1458b1", | | "creator_user_id": "e2c0a7cf-664c-4ccf-9ab5-93c9eb1458b1", |
| "extras": [ | | "extras": [ |
| { | | { |
| "key": "image_url", | | "key": "image_url", |
| "value": | | "value": |
| //sefarad.com.tr/wp-content/uploads/2020/05/salom-makaleleri-yazi.png" | | //sefarad.com.tr/wp-content/uploads/2020/05/salom-makaleleri-yazi.png" |
| } | | } |
| ], | | ], |
n | "groups": [], | n | "groups": [ |
| | | { |
| | | "description": "Text corpora, parallel corpora", |
| | | "display_name": "Text dataset", |
| | | "id": "e6125090-f7e9-4729-9a13-e4931090508a", |
| | | "image_display_url": |
| | | .sefarad.com.tr/uploads/group/2022-08-09-171438.401553ladinotext.jpg", |
| | | "name": "text", |
| | | "title": "Text dataset" |
| | | } |
| | | ], |
| "id": "d3a7700c-aa5d-4d45-8a55-c9bdf137e448", | | "id": "d3a7700c-aa5d-4d45-8a55-c9bdf137e448", |
| "isopen": true, | | "isopen": true, |
| "license_id": "cc-by", | | "license_id": "cc-by", |
| "license_title": "Creative Commons Attribution", | | "license_title": "Creative Commons Attribution", |
| "license_url": "http://www.opendefinition.org/licenses/cc-by", | | "license_url": "http://www.opendefinition.org/licenses/cc-by", |
| "maintainer": "", | | "maintainer": "", |
| "maintainer_email": "", | | "maintainer_email": "", |
| "metadata_created": "2022-08-09T08:55:49.053157", | | "metadata_created": "2022-08-09T08:55:49.053157", |
n | "metadata_modified": "2022-08-09T15:24:35.815391", | n | "metadata_modified": "2022-09-27T11:21:59.795923", |
| "name": "salom-ladino-articles-text-corpus", | | "name": "salom-ladino-articles-text-corpus", |
| "notes": "397 articles from the Judeo-Espanyol section of \u015ealom | | "notes": "397 articles from the Judeo-Espanyol section of \u015ealom |
| newspaper. | | newspaper. |
| https://www.salom.com.tr/haberler/17/judeo-espanyol\r\nOriginal | | https://www.salom.com.tr/haberler/17/judeo-espanyol\r\nOriginal |
| sentences and articles belong to \u015ealom. Corpus is compiled by | | sentences and articles belong to \u015ealom. Corpus is compiled by |
t | Col\u00b7lectivaT. \r\n\r\nSize: 176,843 words\r\n\r\nThis dataset is | t | Col\u00b7lectivaT. \r\n\r\nSize: 176,843 words\r\n\r\nLicense: |
| | | CC-BY\r\n\r\nCitation and more information: |
| | | https://arxiv.org/abs/2205.15599\r\n\r\nThis dataset is created as |
| created as part of project \"Judeo-Spanish: Connecting the two ends of | | part of project \"Judeo-Spanish: Connecting the two ends of the |
| the Mediterranean\" carried out by Col\u00b7lectivaT and Sephardic | | Mediterranean\" carried out by Col\u00b7lectivaT and Sephardic Center |
| Center of Istanbul within the framework of the \u201cGrant Scheme for | | of Istanbul within the framework of the \u201cGrant Scheme for Common |
| Common Cultural Heritage: Preservation and Dialogue between Turkey and | | Cultural Heritage: Preservation and Dialogue between Turkey and the |
| the EU\u2013II (CCH-II)\u201d implemented by the Ministry of Culture | | EU\u2013II (CCH-II)\u201d implemented by the Ministry of Culture and |
| and Tourism of the Republic of Turkey with the financial support of | | Tourism of the Republic of Turkey with the financial support of the |
| the European Union. The content of this website is the sole | | European Union. The content of this website is the sole responsibility |
| responsibility of Col\u00b7lectivaT and does not necessarily reflect | | of Col\u00b7lectivaT and does not necessarily reflect the views of the |
| the views of the European Union.", | | European Union.", |
| "num_resources": 2, | | "num_resources": 2, |
| "num_tags": 0, | | "num_tags": 0, |
| "organization": { | | "organization": { |
| "approval_status": "approved", | | "approval_status": "approved", |
| "created": "2022-08-09T08:55:19.044966", | | "created": "2022-08-09T08:55:19.044966", |
| "description": "Col\u00b7lectivaT is a non-profit cooperative | | "description": "Col\u00b7lectivaT is a non-profit cooperative |
| formed by knowledge workers that provides all-around services of | | formed by knowledge workers that provides all-around services of |
| cultural translation, research and technological services for | | cultural translation, research and technological services for |
| collaborative and linguistic work.", | | collaborative and linguistic work.", |
| "id": "0510debc-4a80-4144-b198-def8e40d28d9", | | "id": "0510debc-4a80-4144-b198-def8e40d28d9", |
| "image_url": "https://collectivat.cat/img/logo_sm.png", | | "image_url": "https://collectivat.cat/img/logo_sm.png", |
| "is_organization": true, | | "is_organization": true, |
| "name": "col-lectivat", | | "name": "col-lectivat", |
| "state": "active", | | "state": "active", |
| "title": "Col\u00b7lectivaT", | | "title": "Col\u00b7lectivaT", |
| "type": "organization" | | "type": "organization" |
| }, | | }, |
| "owner_org": "0510debc-4a80-4144-b198-def8e40d28d9", | | "owner_org": "0510debc-4a80-4144-b198-def8e40d28d9", |
| "private": false, | | "private": false, |
| "relationships_as_object": [], | | "relationships_as_object": [], |
| "relationships_as_subject": [], | | "relationships_as_subject": [], |
| "resources": [ | | "resources": [ |
| { | | { |
| "cache_last_updated": null, | | "cache_last_updated": null, |
| "cache_url": null, | | "cache_url": null, |
| "created": "2022-08-09T08:56:20.635252", | | "created": "2022-08-09T08:56:20.635252", |
| "description": "", | | "description": "", |
| "format": "TXT", | | "format": "TXT", |
| "hash": "", | | "hash": "", |
| "id": "65f63f6d-7091-43fe-a4bc-319eba2d238e", | | "id": "65f63f6d-7091-43fe-a4bc-319eba2d238e", |
| "last_modified": "2022-08-09T08:56:20.616483", | | "last_modified": "2022-08-09T08:56:20.616483", |
| "metadata_modified": "2022-08-09T15:01:32.985954", | | "metadata_modified": "2022-08-09T15:01:32.985954", |
| "mimetype": "text/plain", | | "mimetype": "text/plain", |
| "mimetype_inner": null, | | "mimetype_inner": null, |
| "name": "Salom text corpus", | | "name": "Salom text corpus", |
| "package_id": "d3a7700c-aa5d-4d45-8a55-c9bdf137e448", | | "package_id": "d3a7700c-aa5d-4d45-8a55-c9bdf137e448", |
| "position": 0, | | "position": 0, |
| "resource_type": null, | | "resource_type": null, |
| "size": 991480, | | "size": 991480, |
| "state": "active", | | "state": "active", |
| "url": | | "url": |
| ba2d238e/download/salom-ladino-2022-01-ext-04_segmented_shuffled.txt", | | ba2d238e/download/salom-ladino-2022-01-ext-04_segmented_shuffled.txt", |
| "url_type": "upload" | | "url_type": "upload" |
| }, | | }, |
| { | | { |
| "cache_last_updated": null, | | "cache_last_updated": null, |
| "cache_url": null, | | "cache_url": null, |
| "created": "2022-08-09T15:01:13.471068", | | "created": "2022-08-09T15:01:13.471068", |
| "description": "", | | "description": "", |
| "format": "TXT", | | "format": "TXT", |
| "hash": "", | | "hash": "", |
| "id": "13c1287b-971d-4e38-a376-5c7a297e6e49", | | "id": "13c1287b-971d-4e38-a376-5c7a297e6e49", |
| "last_modified": null, | | "last_modified": null, |
| "metadata_modified": "2022-08-09T15:01:13.466631", | | "metadata_modified": "2022-08-09T15:01:13.466631", |
| "mimetype": "text/plain", | | "mimetype": "text/plain", |
| "mimetype_inner": null, | | "mimetype_inner": null, |
| "name": "Salom text corpus (External link)", | | "name": "Salom text corpus (External link)", |
| "package_id": "d3a7700c-aa5d-4d45-8a55-c9bdf137e448", | | "package_id": "d3a7700c-aa5d-4d45-8a55-c9bdf137e448", |
| "position": 1, | | "position": 1, |
| "resource_type": null, | | "resource_type": null, |
| "size": null, | | "size": null, |
| "state": "active", | | "state": "active", |
| "url": | | "url": |
| ectivat.cat/share/Salom-ladino-2022-01-ext-04_segmented_shuffled.txt", | | ectivat.cat/share/Salom-ladino-2022-01-ext-04_segmented_shuffled.txt", |
| "url_type": null | | "url_type": null |
| } | | } |
| ], | | ], |
| "state": "active", | | "state": "active", |
| "tags": [], | | "tags": [], |
| "title": "\u015ealom Ladino articles text corpus", | | "title": "\u015ealom Ladino articles text corpus", |
| "type": "dataset", | | "type": "dataset", |
| "url": "", | | "url": "", |
| "version": "" | | "version": "" |
| } | | } |