Changes

On December 2, 2024 at 6:14:06 PM UTC, admin:
Set author of BookCorpus to Shuai Tang (previously Zhu, Y.; Kiros, R.; Zemel, R. S.; Salakhutdinov, R.; Urtasun, R.; Torralba, A.; Fidler, S.)
Updated description of BookCorpus from
The BookCorpus dataset used in pre-training contains a wide range of English books, providing a rich source of textual data for masking language modeling tasks.
to
The dataset used in this paper for unsupervised sentence representation learning, consisting of paragraphs from unlabeled text.
Added the following tags to BookCorpus
Changed value of field defined_in to https://doi.org/10.48550/arXiv.2305.18239 in BookCorpus
Changed value of field citation to ['https://doi.org/10.48550/arXiv.1806.04480', 'https://doi.org/10.48550/arXiv.2407.18698', 'https://doi.org/10.48550/arXiv.2206.08919', 'https://doi.org/10.48550/arXiv.1706.03146', 'https://doi.org/10.48550/arXiv.1705.00557'] in BookCorpus
Changed value of field landing_page to https://books.nlp.stanford.edu/datasets/bookcorpus.html in BookCorpus
Deleted resource Original Metadata from BookCorpus
              
    
          
          
        
        
            f 1 { f 1 {
            2   "access_rights": "", 2   "access_rights": "",
            n 3   "author": "Zhu, Y.; Kiros, R.; Zemel, R. S.; Salakhutdinov, R.;  n 3   "author": "Shuai Tang",
            4 Urtasun, R.; Torralba, A.; Fidler, S.", 
            5   "author_email": "", 4   "author_email": "",
            n 6   "citation": [], n 5   "citation": [
            6     "https://doi.org/10.48550/arXiv.1806.04480",
            7     "https://doi.org/10.48550/arXiv.2407.18698",
            8     "https://doi.org/10.48550/arXiv.2206.08919",
            9     "https://doi.org/10.48550/arXiv.1706.03146",
            10     "https://doi.org/10.48550/arXiv.1705.00557"
            11   ],
            7   "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700", 12   "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
            n 8   "defined_in": "https://doi.org/10.48550/arXiv.2004.14996", n 13   "defined_in": "https://doi.org/10.48550/arXiv.2305.18239",
            9   "doi": "10.57702/wgy6lj2h", 14   "doi": "10.57702/wgy6lj2h",
            10   "doi_date_published": "2024-11-25", 15   "doi_date_published": "2024-11-25",
            11   "doi_publisher": "TIB", 16   "doi_publisher": "TIB",
            12   "doi_status": true, 17   "doi_status": true,
            13   "domain": "https://service.tib.eu/ldmservice", 18   "domain": "https://service.tib.eu/ldmservice",
            n n 19   "extra_authors": [
            20     {
            21       "extra_author": "Hailin Jin",
            22       "orcid": ""
            23     },
            24     {
            25       "extra_author": "Chen Fang",
            26       "orcid": ""
            27     },
            28     {
            29       "extra_author": "Zhaowen Wang",
            30       "orcid": ""
            31     },
            32     {
            33       "extra_author": "Virginia R. de Sa",
            34       "orcid": ""
            35     }
            36   ],
            14   "groups": [], 37   "groups": [
            38     {
            39       "description": "",
            40       "display_name": "Natural Language Processing",
            41       "id": "5b974bcc-8f79-40fc-a05d-75b861d55ed0",
            42       "image_display_url": "",
            43       "name": "natural-language-processing",
            44       "title": "Natural Language Processing"
            45     },
            46     {
            47       "description": "",
            48       "display_name": "Text Analysis",
            49       "id": "c6e4118d-2ceb-49cc-97b8-1ddd4db9ffaa",
            50       "image_display_url": "",
            51       "name": "text-analysis",
            52       "title": "Text Analysis"
            53     },
            54     {
            55       "description": "",
            56       "display_name": "Text Classification",
            57       "id": "0707d099-de73-41dc-85f6-93e4efa6bf14",
            58       "image_display_url": "",
            59       "name": "text-classification",
            60       "title": "Text Classification"
            61     },
            62     {
            63       "description": "",
            64       "display_name": "Text Corpus",
            65       "id": "402a6ef9-4d35-48c4-8e4a-f95ce45e5215",
            66       "image_display_url": "",
            67       "name": "text-corpus",
            68       "title": "Text Corpus"
            69     },
            70     {
            71       "description": "",
            72       "display_name": "Text Generation",
            73       "id": "e9d4b27d-4658-4981-ac71-43ba61d3f4fb",
            74       "image_display_url": "",
            75       "name": "text-generation",
            76       "title": "Text Generation"
            77     },
            78     {
            79       "description": "",
            80       "display_name": "Vision-Language Pre-training",
            81       "id": "58ef4f39-fe42-4d9a-9f40-3951b2551069",
            82       "image_display_url": "",
            83       "name": "vision-language-pre-training",
            84       "title": "Vision-Language Pre-training"
            85     }
            86   ],
            15   "id": "6f5e003a-d5fb-4b57-8178-c7acdac4a0f8", 87   "id": "6f5e003a-d5fb-4b57-8178-c7acdac4a0f8",
            16   "isopen": false, 88   "isopen": false,
            n 17   "landing_page": "https://yknzhu.wixsite.com/mbweb", n 89   "landing_page": 
            90 "https://books.nlp.stanford.edu/datasets/bookcorpus.html",
            18   "license_title": null, 91   "license_title": null,
            19   "link_orkg": "", 92   "link_orkg": "",
            20   "metadata_created": "2024-11-25T14:27:46.658217", 93   "metadata_created": "2024-11-25T14:27:46.658217",
            n 21   "metadata_modified": "2024-11-25T14:41:42.281134", n 94   "metadata_modified": "2024-12-02T18:14:05.261173",
            22   "name": "bookcorpus", 95   "name": "bookcorpus",
            n 23   "notes": "The BookCorpus dataset used in pre-training contains a  n 96   "notes": "The dataset used in this paper for unsupervised sentence 
            24 wide range of English books, providing a rich source of textual data  97 representation learning, consisting of paragraphs from unlabeled 
            25 for masking language modeling tasks.", 98 text.",
            26   "num_resources": 1, 99   "num_resources": 0,
            27   "num_tags": 0, 100   "num_tags": 16,
            28   "organization": { 101   "organization": {
            29     "approval_status": "approved", 102     "approval_status": "approved",
            30     "created": "2024-11-25T12:11:38.292601", 103     "created": "2024-11-25T12:11:38.292601",
            31     "description": "", 104     "description": "",
            32     "id": "079d46db-32df-4b48-91f3-0a8bc8f69559", 105     "id": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            33     "image_url": "", 106     "image_url": "",
            34     "is_organization": true, 107     "is_organization": true,
            35     "name": "no-organization", 108     "name": "no-organization",
            36     "state": "active", 109     "state": "active",
            37     "title": "No Organization", 110     "title": "No Organization",
            38     "type": "organization" 111     "type": "organization"
            39   }, 112   },
            40   "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559", 113   "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            41   "private": false, 114   "private": false,
            42   "relationships_as_object": [], 115   "relationships_as_object": [],
            43   "relationships_as_subject": [], 116   "relationships_as_subject": [],
            n 44   "resources": [ n 117   "resources": [],
            45     { 
            46       "cache_last_updated": null, 
            47       "cache_url": null, 
            48       "created": "2024-11-25T15:30:26", 
            49       "data": [ 
            50         "dcterms:title", 
            51         "dcterms:accessRights", 
            52         "dcterms:creator", 
            53         "dcterms:description", 
            54         "dcterms:issued", 
            55         "dcterms:language", 
            56         "dcterms:identifier", 
            57         "dcat:theme", 
            58         "dcterms:type", 
            59         "dcat:keyword", 
            60         "dcat:landingPage", 
            61         "dcterms:hasVersion", 
            62         "dcterms:format", 
            63         "mls:task", 
            64         "datacite:isDescribedBy" 
            65       ], 
            66       "description": "The json representation of the dataset with its  
            67 distributions based on DCAT.", 
            68       "format": "JSON", 
            69       "hash": "", 
            70       "id": "1510187e-4819-4cb0-8ecf-16a7942c45fc", 
            71       "last_modified": "2024-11-25T14:41:42.272527", 
            72       "metadata_modified": "2024-11-25T14:41:42.284461", 
            73       "mimetype": "application/json", 
            74       "mimetype_inner": null, 
            75       "name": "Original Metadata", 
            76       "package_id": "6f5e003a-d5fb-4b57-8178-c7acdac4a0f8", 
            77       "position": 0, 
            78       "resource_type": null, 
            79       "size": 1003, 
            80       "state": "active", 
            81       "url":  
            82 resource/1510187e-4819-4cb0-8ecf-16a7942c45fc/download/metadata.json", 
            83       "url_type": "upload" 
            84     } 
            85   ], 
            86   "services_used_list": "", 118   "services_used_list": "",
            87   "state": "active", 119   "state": "active",
            t 88   "tags": [], t 120   "tags": [
            121     {
            122       "display_name": "BookCorpus",
            123       "id": "9bfecee5-d291-47af-ad33-5c28721cf61e",
            124       "name": "BookCorpus",
            125       "state": "active",
            126       "vocabulary_id": null
            127     },
            128     {
            129       "display_name": "Text Corpus",
            130       "id": "c16c9fb4-c655-4508-98f1-48ddc76ef1a2",
            131       "name": "Text Corpus",
            132       "state": "active",
            133       "vocabulary_id": null
            134     },
            135     {
            136       "display_name": "bookcorpus",
            137       "id": "45e22248-95c5-4677-acfb-8a66e6ddb2e2",
            138       "name": "bookcorpus",
            139       "state": "active",
            140       "vocabulary_id": null
            141     },
            142     {
            143       "display_name": "books",
            144       "id": "8258ad03-c27c-4873-a300-d484b0f60262",
            145       "name": "books",
            146       "state": "active",
            147       "vocabulary_id": null
            148     },
            149     {
            150       "display_name": "language models",
            151       "id": "4729dde2-7c2d-4139-a4a4-277eb803d093",
            152       "name": "language models",
            153       "state": "active",
            154       "vocabulary_id": null
            155     },
            156     {
            157       "display_name": "natural language processing",
            158       "id": "8af9c93a-1d87-41e0-83d9-f5d01a2bbd0c",
            159       "name": "natural language processing",
            160       "state": "active",
            161       "vocabulary_id": null
            162     },
            163     {
            164       "display_name": "paragraphs",
            165       "id": "d4043b95-5f14-468c-8020-b081ee210b42",
            166       "name": "paragraphs",
            167       "state": "active",
            168       "vocabulary_id": null
            169     },
            170     {
            171       "display_name": "sentence representation",
            172       "id": "32331d99-a5c8-45ce-9d31-d41ccf9e9592",
            173       "name": "sentence representation",
            174       "state": "active",
            175       "vocabulary_id": null
            176     },
            177     {
            178       "display_name": "sentence representation learning",
            179       "id": "2c7288ff-c359-4b19-8561-cb098666b971",
            180       "name": "sentence representation learning",
            181       "state": "active",
            182       "vocabulary_id": null
            183     },
            184     {
            185       "display_name": "sentences",
            186       "id": "654108de-c661-4562-acd1-f308553acc6b",
            187       "name": "sentences",
            188       "state": "active",
            189       "vocabulary_id": null
            190     },
            191     {
            192       "display_name": "text analysis",
            193       "id": "8dede2ad-b59f-4a39-b2b2-4259c7ebcaea",
            194       "name": "text analysis",
            195       "state": "active",
            196       "vocabulary_id": null
            197     },
            198     {
            199       "display_name": "text classification",
            200       "id": "98d3b2df-ea96-4826-971b-6c5bf64c999d",
            201       "name": "text classification",
            202       "state": "active",
            203       "vocabulary_id": null
            204     },
            205     {
            206       "display_name": "text generation",
            207       "id": "064311a6-1694-4cd5-9b57-9a33271b140e",
            208       "name": "text generation",
            209       "state": "active",
            210       "vocabulary_id": null
            211     },
            212     {
            213       "display_name": "unlabeled text",
            214       "id": "9190952a-e881-4ab8-89d8-164ee178ad7f",
            215       "name": "unlabeled text",
            216       "state": "active",
            217       "vocabulary_id": null
            218     },
            219     {
            220       "display_name": "unpaired learning",
            221       "id": "2586ff50-5fc6-4dee-9b2b-792e507bfbf6",
            222       "name": "unpaired learning",
            223       "state": "active",
            224       "vocabulary_id": null
            225     },
            226     {
            227       "display_name": "vision-language pre-training",
            228       "id": "fd01e9f9-7fca-46ce-83d8-ff81c76d8e7a",
            229       "name": "vision-language pre-training",
            230       "state": "active",
            231       "vocabulary_id": null
            232     }
            233   ],
            89   "title": "BookCorpus", 234   "title": "BookCorpus",
            90   "type": "dataset", 235   "type": "dataset",
            91   "version": "" 236   "version": ""
            92 } 237 }