Changes
On December 2, 2024 at 6:03:38 PM UTC,
admin:
-
Added resource Original Metadata to 20 Newsgroups dataset
| f | 1 | { | f | 1 | { |
| 2 | "access_rights": "", | 2 | "access_rights": "", | ||
| 3 | "author": "Nitish Srivastava", | 3 | "author": "Nitish Srivastava", | ||
| 4 | "author_email": "", | 4 | "author_email": "", | ||
| 5 | "citation": [ | 5 | "citation": [ | ||
| 6 | "https://doi.org/10.48550/arXiv.1611.05940", | 6 | "https://doi.org/10.48550/arXiv.1611.05940", | ||
| 7 | "https://doi.org/10.1016/j.procs.2015.03.074" | 7 | "https://doi.org/10.1016/j.procs.2015.03.074" | ||
| 8 | ], | 8 | ], | ||
| 9 | "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700", | 9 | "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700", | ||
| 10 | "defined_in": "https://doi.org/10.48550/arXiv.1907.04919", | 10 | "defined_in": "https://doi.org/10.48550/arXiv.1907.04919", | ||
| 11 | "doi": "10.57702/f4hmxqob", | 11 | "doi": "10.57702/f4hmxqob", | ||
| 12 | "doi_date_published": "2024-11-25", | 12 | "doi_date_published": "2024-11-25", | ||
| 13 | "doi_publisher": "TIB", | 13 | "doi_publisher": "TIB", | ||
| 14 | "doi_status": true, | 14 | "doi_status": true, | ||
| 15 | "domain": "https://service.tib.eu/ldmservice", | 15 | "domain": "https://service.tib.eu/ldmservice", | ||
| 16 | "extra_authors": [ | 16 | "extra_authors": [ | ||
| 17 | { | 17 | { | ||
| 18 | "extra_author": "Geo\ufb00rey Hinton", | 18 | "extra_author": "Geo\ufb00rey Hinton", | ||
| 19 | "orcid": "" | 19 | "orcid": "" | ||
| 20 | }, | 20 | }, | ||
| 21 | { | 21 | { | ||
| 22 | "extra_author": "Ruslan Salakhutdinov", | 22 | "extra_author": "Ruslan Salakhutdinov", | ||
| 23 | "orcid": "" | 23 | "orcid": "" | ||
| 24 | } | 24 | } | ||
| 25 | ], | 25 | ], | ||
| 26 | "groups": [ | 26 | "groups": [ | ||
| 27 | { | 27 | { | ||
| 28 | "description": "", | 28 | "description": "", | ||
| 29 | "display_name": "Text Categorization", | 29 | "display_name": "Text Categorization", | ||
| 30 | "id": "2d56b907-932f-4618-ba36-d173c05f6275", | 30 | "id": "2d56b907-932f-4618-ba36-d173c05f6275", | ||
| 31 | "image_display_url": "", | 31 | "image_display_url": "", | ||
| 32 | "name": "text-categorization", | 32 | "name": "text-categorization", | ||
| 33 | "title": "Text Categorization" | 33 | "title": "Text Categorization" | ||
| 34 | }, | 34 | }, | ||
| 35 | { | 35 | { | ||
| 36 | "description": "", | 36 | "description": "", | ||
| 37 | "display_name": "Text Classification", | 37 | "display_name": "Text Classification", | ||
| 38 | "id": "0707d099-de73-41dc-85f6-93e4efa6bf14", | 38 | "id": "0707d099-de73-41dc-85f6-93e4efa6bf14", | ||
| 39 | "image_display_url": "", | 39 | "image_display_url": "", | ||
| 40 | "name": "text-classification", | 40 | "name": "text-classification", | ||
| 41 | "title": "Text Classification" | 41 | "title": "Text Classification" | ||
| 42 | } | 42 | } | ||
| 43 | ], | 43 | ], | ||
| 44 | "id": "b283b5ec-82db-496b-b5e7-0e8cde168067", | 44 | "id": "b283b5ec-82db-496b-b5e7-0e8cde168067", | ||
| 45 | "isopen": false, | 45 | "isopen": false, | ||
| 46 | "landing_page": | 46 | "landing_page": | ||
| 47 | "https://www.cs.toronto.edu/~rsalakhu/20Newsgroups.html", | 47 | "https://www.cs.toronto.edu/~rsalakhu/20Newsgroups.html", | ||
| 48 | "license_title": null, | 48 | "license_title": null, | ||
| 49 | "link_orkg": "", | 49 | "link_orkg": "", | ||
| 50 | "metadata_created": "2024-11-25T14:20:44.770424", | 50 | "metadata_created": "2024-11-25T14:20:44.770424", | ||
| n | 51 | "metadata_modified": "2024-12-02T18:03:36.560018", | n | 51 | "metadata_modified": "2024-12-02T18:03:37.639224", |
| 52 | "name": "20-newsgroups-dataset", | 52 | "name": "20-newsgroups-dataset", | ||
| 53 | "notes": "The 20 Newsgroups dataset consists of 18,845 posts taken | 53 | "notes": "The 20 Newsgroups dataset consists of 18,845 posts taken | ||
| 54 | from the Usenet newsgroup collection. Each post belongs to exactly one | 54 | from the Usenet newsgroup collection. Each post belongs to exactly one | ||
| 55 | newsgroup. Following the preprocessing in [12] and [7], the data was | 55 | newsgroup. Following the preprocessing in [12] and [7], the data was | ||
| 56 | partitioned chronologically into 11,314 training and 7,531 test | 56 | partitioned chronologically into 11,314 training and 7,531 test | ||
| 57 | articles. After removing stopwords and stemming, the 2000 most | 57 | articles. After removing stopwords and stemming, the 2000 most | ||
| 58 | frequent words in the training set were used to represent the | 58 | frequent words in the training set were used to represent the | ||
| 59 | documents.", | 59 | documents.", | ||
| n | 60 | "num_resources": 0, | n | 60 | "num_resources": 1, |
| 61 | "num_tags": 8, | 61 | "num_tags": 8, | ||
| 62 | "organization": { | 62 | "organization": { | ||
| 63 | "approval_status": "approved", | 63 | "approval_status": "approved", | ||
| 64 | "created": "2024-11-25T12:11:38.292601", | 64 | "created": "2024-11-25T12:11:38.292601", | ||
| 65 | "description": "", | 65 | "description": "", | ||
| 66 | "id": "079d46db-32df-4b48-91f3-0a8bc8f69559", | 66 | "id": "079d46db-32df-4b48-91f3-0a8bc8f69559", | ||
| 67 | "image_url": "", | 67 | "image_url": "", | ||
| 68 | "is_organization": true, | 68 | "is_organization": true, | ||
| 69 | "name": "no-organization", | 69 | "name": "no-organization", | ||
| 70 | "state": "active", | 70 | "state": "active", | ||
| 71 | "title": "No Organization", | 71 | "title": "No Organization", | ||
| 72 | "type": "organization" | 72 | "type": "organization" | ||
| 73 | }, | 73 | }, | ||
| 74 | "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559", | 74 | "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559", | ||
| 75 | "private": false, | 75 | "private": false, | ||
| 76 | "relationships_as_object": [], | 76 | "relationships_as_object": [], | ||
| 77 | "relationships_as_subject": [], | 77 | "relationships_as_subject": [], | ||
| t | 78 | "resources": [], | t | 78 | "resources": [ |
| 79 | { | ||||
| 80 | "cache_last_updated": null, | ||||
| 81 | "cache_url": null, | ||||
| 82 | "created": "2024-12-02T18:38:42", | ||||
| 83 | "data": [ | ||||
| 84 | "dcterms:title", | ||||
| 85 | "dcterms:accessRights", | ||||
| 86 | "dcterms:creator", | ||||
| 87 | "dcterms:description", | ||||
| 88 | "dcterms:issued", | ||||
| 89 | "dcterms:language", | ||||
| 90 | "dcterms:identifier", | ||||
| 91 | "dcat:theme", | ||||
| 92 | "dcterms:type", | ||||
| 93 | "dcat:keyword", | ||||
| 94 | "dcat:landingPage", | ||||
| 95 | "dcterms:hasVersion", | ||||
| 96 | "dcterms:format", | ||||
| 97 | "mls:task", | ||||
| 98 | "datacite:isDescribedBy" | ||||
| 99 | ], | ||||
| 100 | "description": "The json representation of the dataset with its | ||||
| 101 | distributions based on DCAT.", | ||||
| 102 | "format": "JSON", | ||||
| 103 | "hash": "", | ||||
| 104 | "id": "321add24-8e77-45ff-88dd-7e9c58b85439", | ||||
| 105 | "last_modified": "2024-12-02T18:03:37.631321", | ||||
| 106 | "metadata_modified": "2024-12-02T18:03:37.642488", | ||||
| 107 | "mimetype": "application/json", | ||||
| 108 | "mimetype_inner": null, | ||||
| 109 | "name": "Original Metadata", | ||||
| 110 | "package_id": "b283b5ec-82db-496b-b5e7-0e8cde168067", | ||||
| 111 | "position": 0, | ||||
| 112 | "resource_type": null, | ||||
| 113 | "size": 1288, | ||||
| 114 | "state": "active", | ||||
| 115 | "url": | ||||
| 116 | resource/321add24-8e77-45ff-88dd-7e9c58b85439/download/metadata.json", | ||||
| 117 | "url_type": "upload" | ||||
| 118 | } | ||||
| 119 | ], | ||||
| 79 | "services_used_list": "", | 120 | "services_used_list": "", | ||
| 80 | "state": "active", | 121 | "state": "active", | ||
| 81 | "tags": [ | 122 | "tags": [ | ||
| 82 | { | 123 | { | ||
| 83 | "display_name": "20 Newsgroups", | 124 | "display_name": "20 Newsgroups", | ||
| 84 | "id": "e2be3fd7-6c7f-4975-9a58-c6448ed49fe1", | 125 | "id": "e2be3fd7-6c7f-4975-9a58-c6448ed49fe1", | ||
| 85 | "name": "20 Newsgroups", | 126 | "name": "20 Newsgroups", | ||
| 86 | "state": "active", | 127 | "state": "active", | ||
| 87 | "vocabulary_id": null | 128 | "vocabulary_id": null | ||
| 88 | }, | 129 | }, | ||
| 89 | { | 130 | { | ||
| 90 | "display_name": "Text Categorization", | 131 | "display_name": "Text Categorization", | ||
| 91 | "id": "475e53da-3cb9-4954-ae2b-672fb146c8ee", | 132 | "id": "475e53da-3cb9-4954-ae2b-672fb146c8ee", | ||
| 92 | "name": "Text Categorization", | 133 | "name": "Text Categorization", | ||
| 93 | "state": "active", | 134 | "state": "active", | ||
| 94 | "vocabulary_id": null | 135 | "vocabulary_id": null | ||
| 95 | }, | 136 | }, | ||
| 96 | { | 137 | { | ||
| 97 | "display_name": "Text Classification", | 138 | "display_name": "Text Classification", | ||
| 98 | "id": "daa24bd4-9e49-4ef5-870a-f51681ab0a20", | 139 | "id": "daa24bd4-9e49-4ef5-870a-f51681ab0a20", | ||
| 99 | "name": "Text Classification", | 140 | "name": "Text Classification", | ||
| 100 | "state": "active", | 141 | "state": "active", | ||
| 101 | "vocabulary_id": null | 142 | "vocabulary_id": null | ||
| 102 | }, | 143 | }, | ||
| 103 | { | 144 | { | ||
| 104 | "display_name": "document representation", | 145 | "display_name": "document representation", | ||
| 105 | "id": "9439f346-f33f-4187-a3a7-a24918f80bb4", | 146 | "id": "9439f346-f33f-4187-a3a7-a24918f80bb4", | ||
| 106 | "name": "document representation", | 147 | "name": "document representation", | ||
| 107 | "state": "active", | 148 | "state": "active", | ||
| 108 | "vocabulary_id": null | 149 | "vocabulary_id": null | ||
| 109 | }, | 150 | }, | ||
| 110 | { | 151 | { | ||
| 111 | "display_name": "newsgroups", | 152 | "display_name": "newsgroups", | ||
| 112 | "id": "3a7aba89-6881-4691-a484-0d8566f60351", | 153 | "id": "3a7aba89-6881-4691-a484-0d8566f60351", | ||
| 113 | "name": "newsgroups", | 154 | "name": "newsgroups", | ||
| 114 | "state": "active", | 155 | "state": "active", | ||
| 115 | "vocabulary_id": null | 156 | "vocabulary_id": null | ||
| 116 | }, | 157 | }, | ||
| 117 | { | 158 | { | ||
| 118 | "display_name": "text categorization", | 159 | "display_name": "text categorization", | ||
| 119 | "id": "de32a8d9-cbad-45c4-afe4-0f707d3a146b", | 160 | "id": "de32a8d9-cbad-45c4-afe4-0f707d3a146b", | ||
| 120 | "name": "text categorization", | 161 | "name": "text categorization", | ||
| 121 | "state": "active", | 162 | "state": "active", | ||
| 122 | "vocabulary_id": null | 163 | "vocabulary_id": null | ||
| 123 | }, | 164 | }, | ||
| 124 | { | 165 | { | ||
| 125 | "display_name": "text classification", | 166 | "display_name": "text classification", | ||
| 126 | "id": "98d3b2df-ea96-4826-971b-6c5bf64c999d", | 167 | "id": "98d3b2df-ea96-4826-971b-6c5bf64c999d", | ||
| 127 | "name": "text classification", | 168 | "name": "text classification", | ||
| 128 | "state": "active", | 169 | "state": "active", | ||
| 129 | "vocabulary_id": null | 170 | "vocabulary_id": null | ||
| 130 | }, | 171 | }, | ||
| 131 | { | 172 | { | ||
| 132 | "display_name": "topic modeling", | 173 | "display_name": "topic modeling", | ||
| 133 | "id": "6f8aa70c-b1e6-4882-a45f-64a53a8c16a9", | 174 | "id": "6f8aa70c-b1e6-4882-a45f-64a53a8c16a9", | ||
| 134 | "name": "topic modeling", | 175 | "name": "topic modeling", | ||
| 135 | "state": "active", | 176 | "state": "active", | ||
| 136 | "vocabulary_id": null | 177 | "vocabulary_id": null | ||
| 137 | } | 178 | } | ||
| 138 | ], | 179 | ], | ||
| 139 | "title": "20 Newsgroups dataset", | 180 | "title": "20 Newsgroups dataset", | ||
| 140 | "type": "dataset", | 181 | "type": "dataset", | ||
| 141 | "version": "" | 182 | "version": "" | ||
| 142 | } | 183 | } |