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.2306.15550",
6
    "https://doi.org/10.48550/arXiv.2306.15550",
            
7
    "https://doi.org/10.48550/arXiv.2010.03813"
7
    "https://doi.org/10.48550/arXiv.2010.03813"
            
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.2201.06642",
10
  "defined_in": "https://doi.org/10.48550/arXiv.2201.06642",
            
11
  "doi": "10.57702/10zu2mjt",
11
  "doi": "10.57702/10zu2mjt",
            
n
12
  "doi_date_published": null,
n
12
  "doi_date_published": "2024-12-02",
            
13
  "doi_publisher": "TIB",
13
  "doi_publisher": "TIB",
            
n
14
  "doi_status": false,
n
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": "Elena Tommasone",
18
      "extra_author": "Elena Tommasone",
            
19
      "orcid": ""
19
      "orcid": ""
            
20
    },
20
    },
            
21
    {
21
    {
            
22
      "extra_author": "Baptiste Pannier",
22
      "extra_author": "Baptiste Pannier",
            
23
      "orcid": ""
23
      "orcid": ""
            
24
    },
24
    },
            
25
    {
25
    {
            
26
      "extra_author": "Fran\u00e7ois Boniface",
26
      "extra_author": "Fran\u00e7ois Boniface",
            
27
      "orcid": ""
27
      "orcid": ""
            
28
    },
28
    },
            
29
    {
29
    {
            
30
      "extra_author": "Am\u00e9lie Chatelain",
30
      "extra_author": "Am\u00e9lie Chatelain",
            
31
      "orcid": ""
31
      "orcid": ""
            
32
    },
32
    },
            
33
    {
33
    {
            
34
      "extra_author": "Alessandro Cappelli",
34
      "extra_author": "Alessandro Cappelli",
            
35
      "orcid": ""
35
      "orcid": ""
            
36
    },
36
    },
            
37
    {
37
    {
            
38
      "extra_author": "Iacopo Poli",
38
      "extra_author": "Iacopo Poli",
            
39
      "orcid": ""
39
      "orcid": ""
            
40
    },
40
    },
            
41
    {
41
    {
            
42
      "extra_author": "Djam\u00e9 Seddah",
42
      "extra_author": "Djam\u00e9 Seddah",
            
43
      "orcid": ""
43
      "orcid": ""
            
44
    }
44
    }
            
45
  ],
45
  ],
            
46
  "groups": [
46
  "groups": [
            
47
    {
47
    {
            
48
      "description": "",
48
      "description": "",
            
49
      "display_name": "Biomedical Text",
49
      "display_name": "Biomedical Text",
            
50
      "id": "7f266b67-3b2e-4343-8384-7f66d9ec26a5",
50
      "id": "7f266b67-3b2e-4343-8384-7f66d9ec26a5",
            
51
      "image_display_url": "",
51
      "image_display_url": "",
            
52
      "name": "biomedical-text",
52
      "name": "biomedical-text",
            
53
      "title": "Biomedical Text"
53
      "title": "Biomedical Text"
            
54
    },
54
    },
            
55
    {
55
    {
            
56
      "description": "",
56
      "description": "",
            
57
      "display_name": "Language Modeling",
57
      "display_name": "Language Modeling",
            
58
      "id": "f0c89329-f1ed-4ba3-90d2-5113fff9bf72",
58
      "id": "f0c89329-f1ed-4ba3-90d2-5113fff9bf72",
            
59
      "image_display_url": "",
59
      "image_display_url": "",
            
60
      "name": "language-modeling",
60
      "name": "language-modeling",
            
61
      "title": "Language Modeling"
61
      "title": "Language Modeling"
            
62
    },
62
    },
            
63
    {
63
    {
            
64
      "description": "",
64
      "description": "",
            
65
      "display_name": "Multilingual Corpora",
65
      "display_name": "Multilingual Corpora",
            
66
      "id": "0f464674-1466-4769-bd5e-14d665407425",
66
      "id": "0f464674-1466-4769-bd5e-14d665407425",
            
67
      "image_display_url": "",
67
      "image_display_url": "",
            
68
      "name": "multilingual-corpora",
68
      "name": "multilingual-corpora",
            
69
      "title": "Multilingual Corpora"
69
      "title": "Multilingual Corpora"
            
70
    },
70
    },
            
71
    {
71
    {
            
72
      "description": "",
72
      "description": "",
            
73
      "display_name": "Multilingual Web Corpus",
73
      "display_name": "Multilingual Web Corpus",
            
74
      "id": "993a8b69-57e9-4cb2-aa93-bdf061c19338",
74
      "id": "993a8b69-57e9-4cb2-aa93-bdf061c19338",
            
75
      "image_display_url": "",
75
      "image_display_url": "",
            
76
      "name": "multilingual-web-corpus",
76
      "name": "multilingual-web-corpus",
            
77
      "title": "Multilingual Web Corpus"
77
      "title": "Multilingual Web Corpus"
            
78
    },
78
    },
            
79
    {
79
    {
            
80
      "description": "",
80
      "description": "",
            
81
      "display_name": "Text Data",
81
      "display_name": "Text Data",
            
82
      "id": "30d52e93-891a-463b-a577-99a00396f012",
82
      "id": "30d52e93-891a-463b-a577-99a00396f012",
            
83
      "image_display_url": "",
83
      "image_display_url": "",
            
84
      "name": "text-data",
84
      "name": "text-data",
            
85
      "title": "Text Data"
85
      "title": "Text Data"
            
86
    }
86
    }
            
87
  ],
87
  ],
            
88
  "id": "b6a9812f-e3fd-4f97-b970-4c536dc6db85",
88
  "id": "b6a9812f-e3fd-4f97-b970-4c536dc6db85",
            
89
  "isopen": false,
89
  "isopen": false,
            
90
  "landing_page": "https://oscar.nlp.stanford.edu/",
90
  "landing_page": "https://oscar.nlp.stanford.edu/",
            
91
  "license_title": null,
91
  "license_title": null,
            
92
  "link_orkg": "",
92
  "link_orkg": "",
            
93
  "metadata_created": "2024-12-02T18:01:55.377030",
93
  "metadata_created": "2024-12-02T18:01:55.377030",
            
n
94
  "metadata_modified": "2024-12-02T18:01:55.377035",
n
94
  "metadata_modified": "2024-12-02T18:01:55.723222",
            
95
  "name": "oscar",
95
  "name": "oscar",
            
96
  "notes": "The OSCAR corpus is a multilingual web corpus that is used 
96
  "notes": "The OSCAR corpus is a multilingual web corpus that is used 
            
97
for pre-training large generative language models. It is a 
97
for pre-training large generative language models. It is a 
            
98
document-oriented corpus that is comparable in size and language size 
98
document-oriented corpus that is comparable in size and language size 
            
99
distribution to OSCAR 21.09.",
99
distribution to OSCAR 21.09.",
            
n
100
  "num_resources": 0,
n
100
  "num_resources": 1,
            
101
  "num_tags": 10,
101
  "num_tags": 10,
            
102
  "organization": {
102
  "organization": {
            
103
    "approval_status": "approved",
103
    "approval_status": "approved",
            
104
    "created": "2024-11-25T12:11:38.292601",
104
    "created": "2024-11-25T12:11:38.292601",
            
105
    "description": "",
105
    "description": "",
            
106
    "id": "079d46db-32df-4b48-91f3-0a8bc8f69559",
106
    "id": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            
107
    "image_url": "",
107
    "image_url": "",
            
108
    "is_organization": true,
108
    "is_organization": true,
            
109
    "name": "no-organization",
109
    "name": "no-organization",
            
110
    "state": "active",
110
    "state": "active",
            
111
    "title": "No Organization",
111
    "title": "No Organization",
            
112
    "type": "organization"
112
    "type": "organization"
            
113
  },
113
  },
            
114
  "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559",
114
  "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            
115
  "private": false,
115
  "private": false,
            
116
  "relationships_as_object": [],
116
  "relationships_as_object": [],
            
117
  "relationships_as_subject": [],
117
  "relationships_as_subject": [],
            
t
118
  "resources": [],
t
118
  "resources": [
            
119
    {
            
120
      "cache_last_updated": null,
            
121
      "cache_url": null,
            
122
      "created": "2024-12-02T18:38:42",
            
123
      "data": [
            
124
        "dcterms:title",
            
125
        "dcterms:accessRights",
            
126
        "dcterms:creator",
            
127
        "dcterms:description",
            
128
        "dcterms:issued",
            
129
        "dcterms:language",
            
130
        "dcterms:identifier",
            
131
        "dcat:theme",
            
132
        "dcterms:type",
            
133
        "dcat:keyword",
            
134
        "dcat:landingPage",
            
135
        "dcterms:hasVersion",
            
136
        "dcterms:format",
            
137
        "mls:task",
            
138
        "datacite:isDescribedBy"
            
139
      ],
            
140
      "description": "The json representation of the dataset with its 
            
141
distributions based on DCAT.",
            
142
      "format": "JSON",
            
143
      "hash": "",
            
144
      "id": "7b9cd67c-7ec5-4f16-9e2b-0926770e7b1d",
            
145
      "last_modified": "2024-12-02T18:01:55.715046",
            
146
      "metadata_modified": "2024-12-02T18:01:55.726168",
            
147
      "mimetype": "application/json",
            
148
      "mimetype_inner": null,
            
149
      "name": "Original Metadata",
            
150
      "package_id": "b6a9812f-e3fd-4f97-b970-4c536dc6db85",
            
151
      "position": 0,
            
152
      "resource_type": null,
            
153
      "size": 1228,
            
154
      "state": "active",
            
155
      "url": 
            
156
resource/7b9cd67c-7ec5-4f16-9e2b-0926770e7b1d/download/metadata.json",
            
157
      "url_type": "upload"
            
158
    }
            
159
  ],
            
119
  "services_used_list": "",
160
  "services_used_list": "",
            
120
  "state": "active",
161
  "state": "active",
            
121
  "tags": [
162
  "tags": [
            
122
    {
163
    {
            
123
      "display_name": "Common Crawl",
164
      "display_name": "Common Crawl",
            
124
      "id": "daa1be46-b81f-4d1d-b2bf-19549a1660a5",
165
      "id": "daa1be46-b81f-4d1d-b2bf-19549a1660a5",
            
125
      "name": "Common Crawl",
166
      "name": "Common Crawl",
            
126
      "state": "active",
167
      "state": "active",
            
127
      "vocabulary_id": null
168
      "vocabulary_id": null
            
128
    },
169
    },
            
129
    {
170
    {
            
130
      "display_name": "French Language",
171
      "display_name": "French Language",
            
131
      "id": "b23bb708-4f24-4781-a647-058c0476999b",
172
      "id": "b23bb708-4f24-4781-a647-058c0476999b",
            
132
      "name": "French Language",
173
      "name": "French Language",
            
133
      "state": "active",
174
      "state": "active",
            
134
      "vocabulary_id": null
175
      "vocabulary_id": null
            
135
    },
176
    },
            
136
    {
177
    {
            
137
      "display_name": "French biomedical data",
178
      "display_name": "French biomedical data",
            
138
      "id": "b0dfead7-c0b8-40d0-b5e7-194d8b34d281",
179
      "id": "b0dfead7-c0b8-40d0-b5e7-194d8b34d281",
            
139
      "name": "French biomedical data",
180
      "name": "French biomedical data",
            
140
      "state": "active",
181
      "state": "active",
            
141
      "vocabulary_id": null
182
      "vocabulary_id": null
            
142
    },
183
    },
            
143
    {
184
    {
            
144
      "display_name": "OSCAR",
185
      "display_name": "OSCAR",
            
145
      "id": "cd2bd943-2178-4ed7-b348-9fefa15e096e",
186
      "id": "cd2bd943-2178-4ed7-b348-9fefa15e096e",
            
146
      "name": "OSCAR",
187
      "name": "OSCAR",
            
147
      "state": "active",
188
      "state": "active",
            
148
      "vocabulary_id": null
189
      "vocabulary_id": null
            
149
    },
190
    },
            
150
    {
191
    {
            
151
      "display_name": "Text Data",
192
      "display_name": "Text Data",
            
152
      "id": "a72366d9-3035-43be-8190-608b1c5c787b",
193
      "id": "a72366d9-3035-43be-8190-608b1c5c787b",
            
153
      "name": "Text Data",
194
      "name": "Text Data",
            
154
      "state": "active",
195
      "state": "active",
            
155
      "vocabulary_id": null
196
      "vocabulary_id": null
            
156
    },
197
    },
            
157
    {
198
    {
            
158
      "display_name": "biomedical text",
199
      "display_name": "biomedical text",
            
159
      "id": "1a5d487a-3f29-48c1-b8dd-b3757f9bc9b0",
200
      "id": "1a5d487a-3f29-48c1-b8dd-b3757f9bc9b0",
            
160
      "name": "biomedical text",
201
      "name": "biomedical text",
            
161
      "state": "active",
202
      "state": "active",
            
162
      "vocabulary_id": null
203
      "vocabulary_id": null
            
163
    },
204
    },
            
164
    {
205
    {
            
165
      "display_name": "language modeling",
206
      "display_name": "language modeling",
            
166
      "id": "44eb2c4c-e2cd-4698-bf3c-28ebbd5e3e42",
207
      "id": "44eb2c4c-e2cd-4698-bf3c-28ebbd5e3e42",
            
167
      "name": "language modeling",
208
      "name": "language modeling",
            
168
      "state": "active",
209
      "state": "active",
            
169
      "vocabulary_id": null
210
      "vocabulary_id": null
            
170
    },
211
    },
            
171
    {
212
    {
            
172
      "display_name": "multilingual",
213
      "display_name": "multilingual",
            
173
      "id": "ee7200c1-f044-4a4e-9c0d-3244e46c833d",
214
      "id": "ee7200c1-f044-4a4e-9c0d-3244e46c833d",
            
174
      "name": "multilingual",
215
      "name": "multilingual",
            
175
      "state": "active",
216
      "state": "active",
            
176
      "vocabulary_id": null
217
      "vocabulary_id": null
            
177
    },
218
    },
            
178
    {
219
    {
            
179
      "display_name": "multilingual corpora",
220
      "display_name": "multilingual corpora",
            
180
      "id": "4e539a01-eb7a-4913-8041-64cd93e643fc",
221
      "id": "4e539a01-eb7a-4913-8041-64cd93e643fc",
            
181
      "name": "multilingual corpora",
222
      "name": "multilingual corpora",
            
182
      "state": "active",
223
      "state": "active",
            
183
      "vocabulary_id": null
224
      "vocabulary_id": null
            
184
    },
225
    },
            
185
    {
226
    {
            
186
      "display_name": "web corpus",
227
      "display_name": "web corpus",
            
187
      "id": "f524634f-15ba-4bd7-85fe-83bfac06e04f",
228
      "id": "f524634f-15ba-4bd7-85fe-83bfac06e04f",
            
188
      "name": "web corpus",
229
      "name": "web corpus",
            
189
      "state": "active",
230
      "state": "active",
            
190
      "vocabulary_id": null
231
      "vocabulary_id": null
            
191
    }
232
    }
            
192
  ],
233
  ],
            
193
  "title": "OSCAR",
234
  "title": "OSCAR",
            
194
  "type": "dataset",
235
  "type": "dataset",
            
195
  "version": ""
236
  "version": ""
            
196
}
237
}