Veranderingen

              
    

          
          
        
        

            
f
1
{
f
1
{
            
2
  "author": "", 
2
  "author": "", 
            
3
  "author_email": "", 
3
  "author_email": "", 
            
4
  "creator_user_id": "add784a5-9327-4063-a0e3-08eb34a96d52", 
4
  "creator_user_id": "add784a5-9327-4063-a0e3-08eb34a96d52", 
            
5
  "extras": [
5
  "extras": [
            
6
    {
6
    {
            
7
      "key": "image_url", 
7
      "key": "image_url", 
            
8
      "value": 
8
      "value": 
            
9
a.sefarad.com.tr/uploads/group/2022-08-09-171438.401553ladinotext.jpg"
9
a.sefarad.com.tr/uploads/group/2022-08-09-171438.401553ladinotext.jpg"
            
10
    }
10
    }
            
11
  ], 
11
  ], 
            
n
12
  "groups": [], 
n
12
  "groups": [
            
13
    {
            
14
      "description": "Text corpora, parallel corpora", 
            
15
      "display_name": "Text dataset", 
            
16
      "id": "e6125090-f7e9-4729-9a13-e4931090508a", 
            
17
      "image_display_url": 
            
18
.sefarad.com.tr/uploads/group/2022-08-09-171438.401553ladinotext.jpg", 
            
19
      "name": "text", 
            
20
      "title": "Text dataset"
            
21
    }
            
22
  ], 
            
13
  "id": "5801010b-181a-45f2-b3d2-05861953ac63", 
23
  "id": "5801010b-181a-45f2-b3d2-05861953ac63", 
            
14
  "isopen": true, 
24
  "isopen": true, 
            
15
  "license_id": "cc-by", 
25
  "license_id": "cc-by", 
            
16
  "license_title": "Creative Commons Attribution", 
26
  "license_title": "Creative Commons Attribution", 
            
17
  "license_url": "http://www.opendefinition.org/licenses/cc-by", 
27
  "license_url": "http://www.opendefinition.org/licenses/cc-by", 
            
18
  "maintainer": "", 
28
  "maintainer": "", 
            
19
  "maintainer_email": "", 
29
  "maintainer_email": "", 
            
20
  "metadata_created": "2022-08-09T15:56:40.059317", 
30
  "metadata_created": "2022-08-09T15:56:40.059317", 
            
n
21
  "metadata_modified": "2022-08-09T17:19:14.397602", 
n
31
  "metadata_modified": "2022-09-27T11:18:26.007301", 
            
22
  "name": "synthetic-parallel-data", 
32
  "name": "synthetic-parallel-data", 
            
23
  "notes": "Synthetically produced parallel data using rule-based 
33
  "notes": "Synthetically produced parallel data using rule-based 
            
24
Spanish-Ladino translation.\r\n\r\nSizes:\r\n\r\nLadino-Turkish: 
34
Spanish-Ladino translation.\r\n\r\nSizes:\r\n\r\nLadino-Turkish: 
            
25
4,574,021 sentences\r\n\r\nLadino-English: 5,748,012 
35
4,574,021 sentences\r\n\r\nLadino-English: 5,748,012 
            
26
sentences\r\n\r\nTotal Ladino-Spanish: 10,322,033 sentences (This is 
36
sentences\r\n\r\nTotal Ladino-Spanish: 10,322,033 sentences (This is 
            
27
basically combination of the two corpora)\r\n\r\nPaper: 
37
basically combination of the two corpora)\r\n\r\nPaper: 
            
t
28
https://arxiv.org/abs/2205.15599\r\n\r\nThis dataset is created as 
t
38
https://arxiv.org/abs/2205.15599\r\n\r\nLicense: CC-BY\r\n\r\nThis 
            
29
part of project \"Judeo-Spanish: Connecting the two ends of the 
39
dataset is created as part of project \"Judeo-Spanish: Connecting the 
            
30
Mediterranean\" carried out by Col\u00b7lectivaT and Sephardic Center 
40
two ends of the Mediterranean\" carried out by Col\u00b7lectivaT and 
            
31
of Istanbul within the framework of the \u201cGrant Scheme for Common 
41
Sephardic Center of Istanbul within the framework of the \u201cGrant 
            
32
Cultural Heritage: Preservation and Dialogue between Turkey and the 
42
Scheme for Common Cultural Heritage: Preservation and Dialogue between 
            
33
EU\u2013II (CCH-II)\u201d implemented by the Ministry of Culture and 
43
Turkey and the EU\u2013II (CCH-II)\u201d implemented by the Ministry 
            
34
Tourism of the Republic of Turkey with the financial support of the 
44
of Culture and Tourism of the Republic of Turkey with the financial 
            
35
European Union. The content of this website is the sole responsibility 
45
support of the European Union. The content of this website is the sole 
            
36
of Col\u00b7lectivaT and does not necessarily reflect the views of the 
46
responsibility of Col\u00b7lectivaT and does not necessarily reflect 
            
37
European Union.", 
47
the views of the European Union.", 
            
38
  "num_resources": 2, 
48
  "num_resources": 2, 
            
39
  "num_tags": 1, 
49
  "num_tags": 1, 
            
40
  "organization": {
50
  "organization": {
            
41
    "approval_status": "approved", 
51
    "approval_status": "approved", 
            
42
    "created": "2022-08-09T08:55:19.044966", 
52
    "created": "2022-08-09T08:55:19.044966", 
            
43
    "description": "Col\u00b7lectivaT is a non-profit cooperative 
53
    "description": "Col\u00b7lectivaT is a non-profit cooperative 
            
44
formed by knowledge workers that provides all-around services of 
54
formed by knowledge workers that provides all-around services of 
            
45
cultural translation, research and technological services for 
55
cultural translation, research and technological services for 
            
46
collaborative and linguistic work.", 
56
collaborative and linguistic work.", 
            
47
    "id": "0510debc-4a80-4144-b198-def8e40d28d9", 
57
    "id": "0510debc-4a80-4144-b198-def8e40d28d9", 
            
48
    "image_url": "https://collectivat.cat/img/logo_sm.png", 
58
    "image_url": "https://collectivat.cat/img/logo_sm.png", 
            
49
    "is_organization": true, 
59
    "is_organization": true, 
            
50
    "name": "col-lectivat", 
60
    "name": "col-lectivat", 
            
51
    "state": "active", 
61
    "state": "active", 
            
52
    "title": "Col\u00b7lectivaT", 
62
    "title": "Col\u00b7lectivaT", 
            
53
    "type": "organization"
63
    "type": "organization"
            
54
  }, 
64
  }, 
            
55
  "owner_org": "0510debc-4a80-4144-b198-def8e40d28d9", 
65
  "owner_org": "0510debc-4a80-4144-b198-def8e40d28d9", 
            
56
  "private": false, 
66
  "private": false, 
            
57
  "relationships_as_object": [], 
67
  "relationships_as_object": [], 
            
58
  "relationships_as_subject": [], 
68
  "relationships_as_subject": [], 
            
59
  "resources": [
69
  "resources": [
            
60
    {
70
    {
            
61
      "cache_last_updated": null, 
71
      "cache_last_updated": null, 
            
62
      "cache_url": null, 
72
      "cache_url": null, 
            
63
      "created": "2022-08-09T15:57:05.916509", 
73
      "created": "2022-08-09T15:57:05.916509", 
            
64
      "description": "", 
74
      "description": "", 
            
65
      "format": "ZIP", 
75
      "format": "ZIP", 
            
66
      "hash": "", 
76
      "hash": "", 
            
67
      "id": "f267ee8d-6e12-48a0-9c6f-4ce41ee11255", 
77
      "id": "f267ee8d-6e12-48a0-9c6f-4ce41ee11255", 
            
68
      "last_modified": null, 
78
      "last_modified": null, 
            
69
      "metadata_modified": "2022-08-09T15:57:05.911158", 
79
      "metadata_modified": "2022-08-09T15:57:05.911158", 
            
70
      "mimetype": "application/zip", 
80
      "mimetype": "application/zip", 
            
71
      "mimetype_inner": null, 
81
      "mimetype_inner": null, 
            
72
      "name": "Ladino - English", 
82
      "name": "Ladino - English", 
            
73
      "package_id": "5801010b-181a-45f2-b3d2-05861953ac63", 
83
      "package_id": "5801010b-181a-45f2-b3d2-05861953ac63", 
            
74
      "position": 0, 
84
      "position": 0, 
            
75
      "resource_type": null, 
85
      "resource_type": null, 
            
76
      "size": null, 
86
      "size": null, 
            
77
      "state": "active", 
87
      "state": "active", 
            
78
      "url": 
88
      "url": 
            
79
//collectivat.cat/share/ladino_synthetic_parallel_dataset_en.csv.zip", 
89
//collectivat.cat/share/ladino_synthetic_parallel_dataset_en.csv.zip", 
            
80
      "url_type": null
90
      "url_type": null
            
81
    }, 
91
    }, 
            
82
    {
92
    {
            
83
      "cache_last_updated": null, 
93
      "cache_last_updated": null, 
            
84
      "cache_url": null, 
94
      "cache_url": null, 
            
85
      "created": "2022-08-09T15:57:38.631681", 
95
      "created": "2022-08-09T15:57:38.631681", 
            
86
      "description": "", 
96
      "description": "", 
            
87
      "format": "ZIP", 
97
      "format": "ZIP", 
            
88
      "hash": "", 
98
      "hash": "", 
            
89
      "id": "bac5f97b-9054-4ffe-9d8f-0022af74a508", 
99
      "id": "bac5f97b-9054-4ffe-9d8f-0022af74a508", 
            
90
      "last_modified": null, 
100
      "last_modified": null, 
            
91
      "metadata_modified": "2022-08-09T15:57:38.626254", 
101
      "metadata_modified": "2022-08-09T15:57:38.626254", 
            
92
      "mimetype": "application/zip", 
102
      "mimetype": "application/zip", 
            
93
      "mimetype_inner": null, 
103
      "mimetype_inner": null, 
            
94
      "name": "Ladino - Turkish", 
104
      "name": "Ladino - Turkish", 
            
95
      "package_id": "5801010b-181a-45f2-b3d2-05861953ac63", 
105
      "package_id": "5801010b-181a-45f2-b3d2-05861953ac63", 
            
96
      "position": 1, 
106
      "position": 1, 
            
97
      "resource_type": null, 
107
      "resource_type": null, 
            
98
      "size": null, 
108
      "size": null, 
            
99
      "state": "active", 
109
      "state": "active", 
            
100
      "url": 
110
      "url": 
            
101
//collectivat.cat/share/ladino_synthetic_parallel_dataset_tr.csv.zip", 
111
//collectivat.cat/share/ladino_synthetic_parallel_dataset_tr.csv.zip", 
            
102
      "url_type": null
112
      "url_type": null
            
103
    }
113
    }
            
104
  ], 
114
  ], 
            
105
  "state": "active", 
115
  "state": "active", 
            
106
  "tags": [
116
  "tags": [
            
107
    {
117
    {
            
108
      "display_name": "parallel text", 
118
      "display_name": "parallel text", 
            
109
      "id": "896bbff4-e82d-4f13-9668-dd08a37eb81c", 
119
      "id": "896bbff4-e82d-4f13-9668-dd08a37eb81c", 
            
110
      "name": "parallel text", 
120
      "name": "parallel text", 
            
111
      "state": "active", 
121
      "state": "active", 
            
112
      "vocabulary_id": null
122
      "vocabulary_id": null
            
113
    }
123
    }
            
114
  ], 
124
  ], 
            
115
  "title": "Synthetic parallel corpora LAD-EN, TR", 
125
  "title": "Synthetic parallel corpora LAD-EN, TR", 
            
116
  "type": "dataset", 
126
  "type": "dataset", 
            
117
  "url": "", 
127
  "url": "", 
            
118
  "version": ""
128
  "version": ""
            
119
}
129
}