Changes

              
    

          
          
        
        

            
f
1
{
f
1
{
            
2
  "access_rights": "",
2
  "access_rights": "",
            
3
  "author": "Julien Launay",
3
  "author": "Julien Launay",
            
4
  "author_email": "",
4
  "author_email": "",
            
5
  "citation": [
5
  "citation": [
            
6
    "https://doi.org/10.48550/arXiv.2311.04711"
6
    "https://doi.org/10.48550/arXiv.2311.04711"
            
7
  ],
7
  ],
            
8
  "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
8
  "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
            
9
  "defined_in": "https://doi.org/10.48550/arXiv.2201.06642",
9
  "defined_in": "https://doi.org/10.48550/arXiv.2201.06642",
            
10
  "doi": "10.57702/lau3rl6z",
10
  "doi": "10.57702/lau3rl6z",
            
n
11
  "doi_date_published": null,
n
11
  "doi_date_published": "2024-12-02",
            
12
  "doi_publisher": "TIB",
12
  "doi_publisher": "TIB",
            
n
13
  "doi_status": false,
n
13
  "doi_status": true,
            
14
  "domain": "https://service.tib.eu/ldmservice",
14
  "domain": "https://service.tib.eu/ldmservice",
            
15
  "extra_authors": [
15
  "extra_authors": [
            
16
    {
16
    {
            
17
      "extra_author": "Elena Tommasone",
17
      "extra_author": "Elena Tommasone",
            
18
      "orcid": ""
18
      "orcid": ""
            
19
    },
19
    },
            
20
    {
20
    {
            
21
      "extra_author": "Baptiste Pannier",
21
      "extra_author": "Baptiste Pannier",
            
22
      "orcid": ""
22
      "orcid": ""
            
23
    },
23
    },
            
24
    {
24
    {
            
25
      "extra_author": "Fran\u00e7ois Boniface",
25
      "extra_author": "Fran\u00e7ois Boniface",
            
26
      "orcid": ""
26
      "orcid": ""
            
27
    },
27
    },
            
28
    {
28
    {
            
29
      "extra_author": "Am\u00e9lie Chatelain",
29
      "extra_author": "Am\u00e9lie Chatelain",
            
30
      "orcid": ""
30
      "orcid": ""
            
31
    },
31
    },
            
32
    {
32
    {
            
33
      "extra_author": "Alessandro Cappelli",
33
      "extra_author": "Alessandro Cappelli",
            
34
      "orcid": ""
34
      "orcid": ""
            
35
    },
35
    },
            
36
    {
36
    {
            
37
      "extra_author": "Iacopo Poli",
37
      "extra_author": "Iacopo Poli",
            
38
      "orcid": ""
38
      "orcid": ""
            
39
    },
39
    },
            
40
    {
40
    {
            
41
      "extra_author": "Djam\u00e9 Seddah",
41
      "extra_author": "Djam\u00e9 Seddah",
            
42
      "orcid": ""
42
      "orcid": ""
            
43
    }
43
    }
            
44
  ],
44
  ],
            
45
  "groups": [
45
  "groups": [
            
46
    {
46
    {
            
47
      "description": "",
47
      "description": "",
            
48
      "display_name": "Language Modeling",
48
      "display_name": "Language Modeling",
            
49
      "id": "f0c89329-f1ed-4ba3-90d2-5113fff9bf72",
49
      "id": "f0c89329-f1ed-4ba3-90d2-5113fff9bf72",
            
50
      "image_display_url": "",
50
      "image_display_url": "",
            
51
      "name": "language-modeling",
51
      "name": "language-modeling",
            
52
      "title": "Language Modeling"
52
      "title": "Language Modeling"
            
53
    },
53
    },
            
54
    {
54
    {
            
55
      "description": "",
55
      "description": "",
            
56
      "display_name": "Multilingual Web Corpus",
56
      "display_name": "Multilingual Web Corpus",
            
57
      "id": "993a8b69-57e9-4cb2-aa93-bdf061c19338",
57
      "id": "993a8b69-57e9-4cb2-aa93-bdf061c19338",
            
58
      "image_display_url": "",
58
      "image_display_url": "",
            
59
      "name": "multilingual-web-corpus",
59
      "name": "multilingual-web-corpus",
            
60
      "title": "Multilingual Web Corpus"
60
      "title": "Multilingual Web Corpus"
            
61
    },
61
    },
            
62
    {
62
    {
            
63
      "description": "",
63
      "description": "",
            
64
      "display_name": "Text Data",
64
      "display_name": "Text Data",
            
65
      "id": "30d52e93-891a-463b-a577-99a00396f012",
65
      "id": "30d52e93-891a-463b-a577-99a00396f012",
            
66
      "image_display_url": "",
66
      "image_display_url": "",
            
67
      "name": "text-data",
67
      "name": "text-data",
            
68
      "title": "Text Data"
68
      "title": "Text Data"
            
69
    },
69
    },
            
70
    {
70
    {
            
71
      "description": "",
71
      "description": "",
            
72
      "display_name": "Web Crawling",
72
      "display_name": "Web Crawling",
            
73
      "id": "2d52c79d-2b7f-4fb7-a740-514f07b4c747",
73
      "id": "2d52c79d-2b7f-4fb7-a740-514f07b4c747",
            
74
      "image_display_url": "",
74
      "image_display_url": "",
            
75
      "name": "web-crawling",
75
      "name": "web-crawling",
            
76
      "title": "Web Crawling"
76
      "title": "Web Crawling"
            
77
    },
77
    },
            
78
    {
78
    {
            
79
      "description": "",
79
      "description": "",
            
80
      "display_name": "Web Pages",
80
      "display_name": "Web Pages",
            
81
      "id": "4c5024d8-a3df-4f53-b366-d11ab4bea954",
81
      "id": "4c5024d8-a3df-4f53-b366-d11ab4bea954",
            
82
      "image_display_url": "",
82
      "image_display_url": "",
            
83
      "name": "web-pages",
83
      "name": "web-pages",
            
84
      "title": "Web Pages"
84
      "title": "Web Pages"
            
85
    }
85
    }
            
86
  ],
86
  ],
            
87
  "id": "128ad2e4-ddcb-41bb-acaf-86950c817b09",
87
  "id": "128ad2e4-ddcb-41bb-acaf-86950c817b09",
            
88
  "isopen": false,
88
  "isopen": false,
            
89
  "landing_page": "https://commoncrawl.org/",
89
  "landing_page": "https://commoncrawl.org/",
            
90
  "license_title": null,
90
  "license_title": null,
            
91
  "link_orkg": "",
91
  "link_orkg": "",
            
92
  "metadata_created": "2024-12-02T18:01:50.919780",
92
  "metadata_created": "2024-12-02T18:01:50.919780",
            
n
93
  "metadata_modified": "2024-12-02T18:01:50.919785",
n
93
  "metadata_modified": "2024-12-02T18:01:51.285488",
            
94
  "name": "common-crawl",
94
  "name": "common-crawl",
            
95
  "notes": "The Common Crawl (CC) project browses and indexes all 
95
  "notes": "The Common Crawl (CC) project browses and indexes all 
            
96
content available online. It generates 200-300 TiB of data per month 
96
content available online. It generates 200-300 TiB of data per month 
            
97
(around 5% of which is in French), and constitutes the bulk of most 
97
(around 5% of which is in French), and constitutes the bulk of most 
            
98
NLP datasets nowadays.",
98
NLP datasets nowadays.",
            
n
99
  "num_resources": 0,
n
99
  "num_resources": 1,
            
100
  "num_tags": 8,
100
  "num_tags": 8,
            
101
  "organization": {
101
  "organization": {
            
102
    "approval_status": "approved",
102
    "approval_status": "approved",
            
103
    "created": "2024-11-25T12:11:38.292601",
103
    "created": "2024-11-25T12:11:38.292601",
            
104
    "description": "",
104
    "description": "",
            
105
    "id": "079d46db-32df-4b48-91f3-0a8bc8f69559",
105
    "id": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            
106
    "image_url": "",
106
    "image_url": "",
            
107
    "is_organization": true,
107
    "is_organization": true,
            
108
    "name": "no-organization",
108
    "name": "no-organization",
            
109
    "state": "active",
109
    "state": "active",
            
110
    "title": "No Organization",
110
    "title": "No Organization",
            
111
    "type": "organization"
111
    "type": "organization"
            
112
  },
112
  },
            
113
  "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559",
113
  "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            
114
  "private": false,
114
  "private": false,
            
115
  "relationships_as_object": [],
115
  "relationships_as_object": [],
            
116
  "relationships_as_subject": [],
116
  "relationships_as_subject": [],
            
t
117
  "resources": [],
t
117
  "resources": [
            
118
    {
            
119
      "cache_last_updated": null,
            
120
      "cache_url": null,
            
121
      "created": "2024-12-02T18:38:42",
            
122
      "data": [
            
123
        "dcterms:title",
            
124
        "dcterms:accessRights",
            
125
        "dcterms:creator",
            
126
        "dcterms:description",
            
127
        "dcterms:issued",
            
128
        "dcterms:language",
            
129
        "dcterms:identifier",
            
130
        "dcat:theme",
            
131
        "dcterms:type",
            
132
        "dcat:keyword",
            
133
        "dcat:landingPage",
            
134
        "dcterms:hasVersion",
            
135
        "dcterms:format",
            
136
        "mls:task",
            
137
        "datacite:isDescribedBy"
            
138
      ],
            
139
      "description": "The json representation of the dataset with its 
            
140
distributions based on DCAT.",
            
141
      "format": "JSON",
            
142
      "hash": "",
            
143
      "id": "b56fe07a-69cc-44f9-a618-a7d238668f22",
            
144
      "last_modified": "2024-12-02T18:01:51.277408",
            
145
      "metadata_modified": "2024-12-02T18:01:51.288247",
            
146
      "mimetype": "application/json",
            
147
      "mimetype_inner": null,
            
148
      "name": "Original Metadata",
            
149
      "package_id": "128ad2e4-ddcb-41bb-acaf-86950c817b09",
            
150
      "position": 0,
            
151
      "resource_type": null,
            
152
      "size": 1131,
            
153
      "state": "active",
            
154
      "url": 
            
155
resource/b56fe07a-69cc-44f9-a618-a7d238668f22/download/metadata.json",
            
156
      "url_type": "upload"
            
157
    }
            
158
  ],
            
118
  "services_used_list": "",
159
  "services_used_list": "",
            
119
  "state": "active",
160
  "state": "active",
            
120
  "tags": [
161
  "tags": [
            
121
    {
162
    {
            
122
      "display_name": "Common Crawl",
163
      "display_name": "Common Crawl",
            
123
      "id": "daa1be46-b81f-4d1d-b2bf-19549a1660a5",
164
      "id": "daa1be46-b81f-4d1d-b2bf-19549a1660a5",
            
124
      "name": "Common Crawl",
165
      "name": "Common Crawl",
            
125
      "state": "active",
166
      "state": "active",
            
126
      "vocabulary_id": null
167
      "vocabulary_id": null
            
127
    },
168
    },
            
128
    {
169
    {
            
129
      "display_name": "French Language",
170
      "display_name": "French Language",
            
130
      "id": "b23bb708-4f24-4781-a647-058c0476999b",
171
      "id": "b23bb708-4f24-4781-a647-058c0476999b",
            
131
      "name": "French Language",
172
      "name": "French Language",
            
132
      "state": "active",
173
      "state": "active",
            
133
      "vocabulary_id": null
174
      "vocabulary_id": null
            
134
    },
175
    },
            
135
    {
176
    {
            
136
      "display_name": "Text Data",
177
      "display_name": "Text Data",
            
137
      "id": "a72366d9-3035-43be-8190-608b1c5c787b",
178
      "id": "a72366d9-3035-43be-8190-608b1c5c787b",
            
138
      "name": "Text Data",
179
      "name": "Text Data",
            
139
      "state": "active",
180
      "state": "active",
            
140
      "vocabulary_id": null
181
      "vocabulary_id": null
            
141
    },
182
    },
            
142
    {
183
    {
            
143
      "display_name": "Web Crawling",
184
      "display_name": "Web Crawling",
            
144
      "id": "f38b69c4-01d1-492d-9cf6-4c584e91e7c6",
185
      "id": "f38b69c4-01d1-492d-9cf6-4c584e91e7c6",
            
145
      "name": "Web Crawling",
186
      "name": "Web Crawling",
            
146
      "state": "active",
187
      "state": "active",
            
147
      "vocabulary_id": null
188
      "vocabulary_id": null
            
148
    },
189
    },
            
149
    {
190
    {
            
150
      "display_name": "Web Pages",
191
      "display_name": "Web Pages",
            
151
      "id": "0b80ecb2-15c5-4d0b-ac33-528d883c5a75",
192
      "id": "0b80ecb2-15c5-4d0b-ac33-528d883c5a75",
            
152
      "name": "Web Pages",
193
      "name": "Web Pages",
            
153
      "state": "active",
194
      "state": "active",
            
154
      "vocabulary_id": null
195
      "vocabulary_id": null
            
155
    },
196
    },
            
156
    {
197
    {
            
157
      "display_name": "language modeling",
198
      "display_name": "language modeling",
            
158
      "id": "44eb2c4c-e2cd-4698-bf3c-28ebbd5e3e42",
199
      "id": "44eb2c4c-e2cd-4698-bf3c-28ebbd5e3e42",
            
159
      "name": "language modeling",
200
      "name": "language modeling",
            
160
      "state": "active",
201
      "state": "active",
            
161
      "vocabulary_id": null
202
      "vocabulary_id": null
            
162
    },
203
    },
            
163
    {
204
    {
            
164
      "display_name": "multilingual",
205
      "display_name": "multilingual",
            
165
      "id": "ee7200c1-f044-4a4e-9c0d-3244e46c833d",
206
      "id": "ee7200c1-f044-4a4e-9c0d-3244e46c833d",
            
166
      "name": "multilingual",
207
      "name": "multilingual",
            
167
      "state": "active",
208
      "state": "active",
            
168
      "vocabulary_id": null
209
      "vocabulary_id": null
            
169
    },
210
    },
            
170
    {
211
    {
            
171
      "display_name": "web corpus",
212
      "display_name": "web corpus",
            
172
      "id": "f524634f-15ba-4bd7-85fe-83bfac06e04f",
213
      "id": "f524634f-15ba-4bd7-85fe-83bfac06e04f",
            
173
      "name": "web corpus",
214
      "name": "web corpus",
            
174
      "state": "active",
215
      "state": "active",
            
175
      "vocabulary_id": null
216
      "vocabulary_id": null
            
176
    }
217
    }
            
177
  ],
218
  ],
            
178
  "title": "Common Crawl",
219
  "title": "Common Crawl",
            
179
  "type": "dataset",
220
  "type": "dataset",
            
180
  "version": ""
221
  "version": ""
            
181
}
222
}