Ändringar

View changes from to

9 augusti 2022 15.58.31 UTC, Alp Öktem:

Ändrade titel till Synthetic parallel corpora LAD-EN, TR (tidigare Synthetic parallel corpora LAD-EN, TR, ES)

Uppdaterade beskrivningen av Synthetic parallel corpora LAD-EN, TR från
Synthetically produced parallel data using rule-based Spanish-Ladino translation. Sizes: Ladino-Spanish: 10,322,033 sentences Ladino-Turkish: 4,574,021 sentences Ladino-English: 5,748,012 sentences Paper: https://arxiv.org/abs/2205.15599 This dataset is created as part of project "Judeo-Spanish: Connecting the two ends of the Mediterranean" carried out by Col·lectivaT and Sephardic Center of Istanbul within the framework of the “Grant Scheme for Common Cultural Heritage: Preservation and Dialogue between Turkey and the EU–II (CCH-II)” implemented by the Ministry of Culture and Tourism of the Republic of Turkey with the financial support of the European Union. The content of this website is the sole responsibility of Col·lectivaT and does not necessarily reflect the views of the European Union.
till
Synthetically produced parallel data using rule-based Spanish-Ladino translation. Sizes: Ladino-Turkish: 4,574,021 sentences Ladino-English: 5,748,012 sentences Total Ladino-Spanish: 10,322,033 sentences (This is basically combination of the two corpora) Paper: https://arxiv.org/abs/2205.15599 This dataset is created as part of project "Judeo-Spanish: Connecting the two ends of the Mediterranean" carried out by Col·lectivaT and Sephardic Center of Istanbul within the framework of the “Grant Scheme for Common Cultural Heritage: Preservation and Dialogue between Turkey and the EU–II (CCH-II)” implemented by the Ministry of Culture and Tourism of the Republic of Turkey with the financial support of the European Union. The content of this website is the sole responsibility of Col·lectivaT and does not necessarily reflect the views of the European Union.

              
    
          
          
        
        
            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     } 9     }
            10   ],  10   ], 
            11   "groups": [],  11   "groups": [], 
            12   "id": "5801010b-181a-45f2-b3d2-05861953ac63",  12   "id": "5801010b-181a-45f2-b3d2-05861953ac63", 
            13   "isopen": true,  13   "isopen": true, 
            14   "license_id": "cc-by",  14   "license_id": "cc-by", 
            15   "license_title": "Creative Commons Attribution",  15   "license_title": "Creative Commons Attribution", 
            16   "license_url": "http://www.opendefinition.org/licenses/cc-by",  16   "license_url": "http://www.opendefinition.org/licenses/cc-by", 
            17   "maintainer": "",  17   "maintainer": "", 
            18   "maintainer_email": "",  18   "maintainer_email": "", 
            19   "metadata_created": "2022-08-09T15:56:40.059317",  19   "metadata_created": "2022-08-09T15:56:40.059317", 
            n 20   "metadata_modified": "2022-08-09T15:57:38.727511",  n 20   "metadata_modified": "2022-08-09T15:58:31.481725", 
            21   "name": "synthetic-parallel-data",  21   "name": "synthetic-parallel-data", 
            22   "notes": "Synthetically produced parallel data using rule-based  22   "notes": "Synthetically produced parallel data using rule-based 
            n 23 Spanish-Ladino translation.\r\n\r\nSizes:\r\n\r\nLadino-Spanish:  n 23 Spanish-Ladino translation.\r\n\r\nSizes:\r\n\r\nLadino-Turkish: 
            24 10,322,033 sentences\r\n\r\nLadino-Turkish: 4,574,021  24 4,574,021 sentences\r\n\r\nLadino-English: 5,748,012 
            25 sentences\r\n\r\nLadino-English: 5,748,012 sentences\r\n\r\nPaper:  25 sentences\r\n\r\nTotal Ladino-Spanish: 10,322,033 sentences (This is 
            26 basically combination of the two corpora)\r\n\r\nPaper: 
            26 https://arxiv.org/abs/2205.15599\r\n\r\nThis dataset is created as  27 https://arxiv.org/abs/2205.15599\r\n\r\nThis dataset is created as 
            27 part of project \"Judeo-Spanish: Connecting the two ends of the  28 part of project \"Judeo-Spanish: Connecting the two ends of the 
            28 Mediterranean\" carried out by Col\u00b7lectivaT and Sephardic Center  29 Mediterranean\" carried out by Col\u00b7lectivaT and Sephardic Center 
            29 of Istanbul within the framework of the \u201cGrant Scheme for Common  30 of Istanbul within the framework of the \u201cGrant Scheme for Common 
            30 Cultural Heritage: Preservation and Dialogue between Turkey and the  31 Cultural Heritage: Preservation and Dialogue between Turkey and the 
            31 EU\u2013II (CCH-II)\u201d implemented by the Ministry of Culture and  32 EU\u2013II (CCH-II)\u201d implemented by the Ministry of Culture and 
            32 Tourism of the Republic of Turkey with the financial support of the  33 Tourism of the Republic of Turkey with the financial support of the 
            33 European Union. The content of this website is the sole responsibility  34 European Union. The content of this website is the sole responsibility 
            34 of Col\u00b7lectivaT and does not necessarily reflect the views of the  35 of Col\u00b7lectivaT and does not necessarily reflect the views of the 
            35 European Union.",  36 European Union.", 
            36   "num_resources": 2,  37   "num_resources": 2, 
            37   "num_tags": 1,  38   "num_tags": 1, 
            38   "organization": { 39   "organization": {
            39     "approval_status": "approved",  40     "approval_status": "approved", 
            40     "created": "2022-08-09T08:55:19.044966",  41     "created": "2022-08-09T08:55:19.044966", 
            41     "description": "Col\u00b7lectivaT is a non-profit cooperative  42     "description": "Col\u00b7lectivaT is a non-profit cooperative 
            42 formed by knowledge workers that provides all-around services of  43 formed by knowledge workers that provides all-around services of 
            43 cultural translation, research and technological services for  44 cultural translation, research and technological services for 
            44 collaborative and linguistic work.",  45 collaborative and linguistic work.", 
            45     "id": "0510debc-4a80-4144-b198-def8e40d28d9",  46     "id": "0510debc-4a80-4144-b198-def8e40d28d9", 
            46     "image_url": "https://collectivat.cat/img/logo_sm.png",  47     "image_url": "https://collectivat.cat/img/logo_sm.png", 
            47     "is_organization": true,  48     "is_organization": true, 
            48     "name": "col-lectivat",  49     "name": "col-lectivat", 
            49     "state": "active",  50     "state": "active", 
            50     "title": "Col\u00b7lectivaT",  51     "title": "Col\u00b7lectivaT", 
            51     "type": "organization" 52     "type": "organization"
            52   },  53   }, 
            53   "owner_org": "0510debc-4a80-4144-b198-def8e40d28d9",  54   "owner_org": "0510debc-4a80-4144-b198-def8e40d28d9", 
            54   "private": false,  55   "private": false, 
            55   "relationships_as_object": [],  56   "relationships_as_object": [], 
            56   "relationships_as_subject": [],  57   "relationships_as_subject": [], 
            57   "resources": [ 58   "resources": [
            58     { 59     {
            59       "cache_last_updated": null,  60       "cache_last_updated": null, 
            60       "cache_url": null,  61       "cache_url": null, 
            61       "created": "2022-08-09T15:57:05.916509",  62       "created": "2022-08-09T15:57:05.916509", 
            62       "description": "",  63       "description": "", 
            63       "format": "ZIP",  64       "format": "ZIP", 
            64       "hash": "",  65       "hash": "", 
            65       "id": "f267ee8d-6e12-48a0-9c6f-4ce41ee11255",  66       "id": "f267ee8d-6e12-48a0-9c6f-4ce41ee11255", 
            66       "last_modified": null,  67       "last_modified": null, 
            67       "metadata_modified": "2022-08-09T15:57:05.911158",  68       "metadata_modified": "2022-08-09T15:57:05.911158", 
            68       "mimetype": "application/zip",  69       "mimetype": "application/zip", 
            69       "mimetype_inner": null,  70       "mimetype_inner": null, 
            70       "name": "Ladino - English",  71       "name": "Ladino - English", 
            71       "package_id": "5801010b-181a-45f2-b3d2-05861953ac63",  72       "package_id": "5801010b-181a-45f2-b3d2-05861953ac63", 
            72       "position": 0,  73       "position": 0, 
            73       "resource_type": null,  74       "resource_type": null, 
            74       "size": null,  75       "size": null, 
            75       "state": "active",  76       "state": "active", 
            76       "url":  77       "url": 
            77 //collectivat.cat/share/ladino_synthetic_parallel_dataset_en.csv.zip",  78 //collectivat.cat/share/ladino_synthetic_parallel_dataset_en.csv.zip", 
            78       "url_type": null 79       "url_type": null
            79     },  80     }, 
            80     { 81     {
            81       "cache_last_updated": null,  82       "cache_last_updated": null, 
            82       "cache_url": null,  83       "cache_url": null, 
            83       "created": "2022-08-09T15:57:38.631681",  84       "created": "2022-08-09T15:57:38.631681", 
            84       "description": "",  85       "description": "", 
            85       "format": "ZIP",  86       "format": "ZIP", 
            86       "hash": "",  87       "hash": "", 
            87       "id": "bac5f97b-9054-4ffe-9d8f-0022af74a508",  88       "id": "bac5f97b-9054-4ffe-9d8f-0022af74a508", 
            88       "last_modified": null,  89       "last_modified": null, 
            89       "metadata_modified": "2022-08-09T15:57:38.626254",  90       "metadata_modified": "2022-08-09T15:57:38.626254", 
            90       "mimetype": "application/zip",  91       "mimetype": "application/zip", 
            91       "mimetype_inner": null,  92       "mimetype_inner": null, 
            92       "name": "Ladino - Turkish",  93       "name": "Ladino - Turkish", 
            93       "package_id": "5801010b-181a-45f2-b3d2-05861953ac63",  94       "package_id": "5801010b-181a-45f2-b3d2-05861953ac63", 
            94       "position": 1,  95       "position": 1, 
            95       "resource_type": null,  96       "resource_type": null, 
            96       "size": null,  97       "size": null, 
            97       "state": "active",  98       "state": "active", 
            98       "url":  99       "url": 
            99 //collectivat.cat/share/ladino_synthetic_parallel_dataset_tr.csv.zip",  100 //collectivat.cat/share/ladino_synthetic_parallel_dataset_tr.csv.zip", 
            100       "url_type": null 101       "url_type": null
            101     } 102     }
            102   ],  103   ], 
            103   "state": "active",  104   "state": "active", 
            104   "tags": [ 105   "tags": [
            105     { 106     {
            106       "display_name": "parallel text",  107       "display_name": "parallel text", 
            107       "id": "896bbff4-e82d-4f13-9668-dd08a37eb81c",  108       "id": "896bbff4-e82d-4f13-9668-dd08a37eb81c", 
            108       "name": "parallel text",  109       "name": "parallel text", 
            109       "state": "active",  110       "state": "active", 
            110       "vocabulary_id": null 111       "vocabulary_id": null
            111     } 112     }
            112   ],  113   ], 
            t 113   "title": "Synthetic parallel corpora LAD-EN, TR, ES",  t 114   "title": "Synthetic parallel corpora LAD-EN, TR", 
            114   "type": "dataset",  115   "type": "dataset", 
            115   "url": "",  116   "url": "", 
            116   "version": "" 117   "version": ""
            117 } 118 }