Changes

On December 2, 2024 at 11:10:35 PM UTC, admin:

Set author of Natural Questions to Tom Kwiatkowski (previously Pranav Rajpurkar)

Updated description of Natural Questions from
The Natural Questions dataset embedded real users' information-seeking needs in a realistic information retrieval context, using web search queries and corresponding Wikipedia pages as sources for question answering tasks.
to
The Natural Questions dataset consists of questions extracted from web queries, with each question accompanied by a corresponding Wikipedia article containing the answer.

Added the following tags to Natural Questions

Changed value of field defined_in to https://doi.org/10.48550/arXiv.2004.14560 in Natural Questions

Changed value of field extra_authors to [{'extra_author': 'Jennimaria Palomaki', 'orcid': ''}, {'extra_author': 'Olivia Redfield', 'orcid': ''}, {'extra_author': 'Michael Collins', 'orcid': ''}, {'extra_author': 'Ankur Parikh', 'orcid': ''}, {'extra_author': 'Chris Alberti', 'orcid': ''}, {'extra_author': 'Danielle Epstein', 'orcid': ''}, {'extra_author': 'Illia Polosukhin', 'orcid': ''}, {'extra_author': 'Jacob Devlin', 'orcid': ''}, {'extra_author': 'Kenyon Lee', 'orcid': ''}, {'extra_author': 'Kristina Toutanova', 'orcid': ''}, {'extra_author': 'Llion Jones', 'orcid': ''}, {'extra_author': 'Matthew Kelcey', 'orcid': ''}, {'extra_author': 'Ming-Wei Chang', 'orcid': ''}, {'extra_author': 'Andrew M. Dai', 'orcid': ''}, {'extra_author': 'Jakob Uszkoreit', 'orcid': ''}, {'extra_author': 'Quoc Le', 'orcid': ''}, {'extra_author': 'Slav Petrov', 'orcid': ''}] in Natural Questions

Changed value of field citation to ['https://doi.org/10.48550/arXiv.2403.14403', 'https://doi.org/10.48550/arXiv.2402.12545', 'https://doi.org/10.48550/arXiv.2202.05144', 'https://doi.org/10.48550/arXiv.2311.02834', 'https://doi.org/10.48550/arXiv.2004.02002', 'https://doi.org/10.48550/arXiv.2311.03798', 'https://doi.org/10.48550/arXiv.2211.09744', 'https://doi.org/10.48550/arXiv.2206.02743'] in Natural Questions

Changed value of field landing_page to https://arxiv.org/abs/1909.07591 in Natural Questions

Deleted resource Original Metadata from Natural Questions

              
    
          
          
        
        
            f 1 { f 1 {
            2   "access_rights": "", 2   "access_rights": "",
            n 3   "author": "Pranav Rajpurkar", n 3   "author": "Tom Kwiatkowski",
            4   "author_email": "", 4   "author_email": "",
            5   "citation": [ 5   "citation": [
            n n 6     "https://doi.org/10.48550/arXiv.2403.14403",
            7     "https://doi.org/10.48550/arXiv.2402.12545",
            8     "https://doi.org/10.48550/arXiv.2202.05144",
            6     "https://doi.org/10.48550/arXiv.1911.04156" 9     "https://doi.org/10.48550/arXiv.2311.02834",
            10     "https://doi.org/10.48550/arXiv.2004.02002",
            11     "https://doi.org/10.48550/arXiv.2311.03798",
            12     "https://doi.org/10.48550/arXiv.2211.09744",
            13     "https://doi.org/10.48550/arXiv.2206.02743"
            7   ], 14   ],
            8   "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700", 15   "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
            n 9   "defined_in": "https://doi.org/10.48550/arXiv.1910.06360", n 16   "defined_in": "https://doi.org/10.48550/arXiv.2004.14560",
            10   "doi": "10.57702/f8a604vv", 17   "doi": "10.57702/f8a604vv",
            11   "doi_date_published": "2024-11-25", 18   "doi_date_published": "2024-11-25",
            12   "doi_publisher": "TIB", 19   "doi_publisher": "TIB",
            13   "doi_status": true, 20   "doi_status": true,
            14   "domain": "https://service.tib.eu/ldmservice", 21   "domain": "https://service.tib.eu/ldmservice",
            15   "extra_authors": [ 22   "extra_authors": [
            16     { 23     {
            n n 24       "extra_author": "Jennimaria Palomaki",
            25       "orcid": ""
            26     },
            27     {
            17       "extra_author": "Robin Jia", 28       "extra_author": "Olivia Redfield",
            29       "orcid": ""
            30     },
            31     {
            32       "extra_author": "Michael Collins",
            18       "orcid": "" 33       "orcid": ""
            19     }, 34     },
            20     { 35     {
            21       "extra_author": "Ankur Parikh", 36       "extra_author": "Ankur Parikh",
            22       "orcid": "" 37       "orcid": ""
            23     }, 38     },
            24     { 39     {
            n n 40       "extra_author": "Chris Alberti",
            41       "orcid": ""
            42     },
            43     {
            44       "extra_author": "Danielle Epstein",
            45       "orcid": ""
            46     },
            47     {
            48       "extra_author": "Illia Polosukhin",
            49       "orcid": ""
            50     },
            51     {
            25       "extra_author": "Michael Collins", 52       "extra_author": "Jacob Devlin",
            53       "orcid": ""
            54     },
            55     {
            56       "extra_author": "Kenyon Lee",
            57       "orcid": ""
            58     },
            59     {
            60       "extra_author": "Kristina Toutanova",
            61       "orcid": ""
            62     },
            63     {
            64       "extra_author": "Llion Jones",
            65       "orcid": ""
            66     },
            67     {
            68       "extra_author": "Matthew Kelcey",
            69       "orcid": ""
            70     },
            71     {
            72       "extra_author": "Ming-Wei Chang",
            73       "orcid": ""
            74     },
            75     {
            76       "extra_author": "Andrew M. Dai",
            77       "orcid": ""
            78     },
            79     {
            80       "extra_author": "Jakob Uszkoreit",
            81       "orcid": ""
            82     },
            83     {
            84       "extra_author": "Quoc Le",
            85       "orcid": ""
            86     },
            87     {
            88       "extra_author": "Slav Petrov",
            26       "orcid": "" 89       "orcid": ""
            27     } 90     }
            28   ], 91   ],
            n 29   "groups": [], n 92   "groups": [
            93     {
            94       "description": "",
            95       "display_name": "Natural Language Processing",
            96       "id": "5b974bcc-8f79-40fc-a05d-75b861d55ed0",
            97       "image_display_url": "",
            98       "name": "natural-language-processing",
            99       "title": "Natural Language Processing"
            100     },
            101     {
            102       "description": "",
            103       "display_name": "Question Answering",
            104       "id": "01e9bd6b-910d-421d-bb31-799604023211",
            105       "image_display_url": "",
            106       "name": "question-answering",
            107       "title": "Question Answering"
            108     }
            109   ],
            30   "id": "ba656bde-dade-4f1d-822d-b71acb5ea3fd", 110   "id": "ba656bde-dade-4f1d-822d-b71acb5ea3fd",
            31   "isopen": false, 111   "isopen": false,
            n 32   "landing_page": "https://naturalquestions.withgoogle.com/", n 112   "landing_page": "https://arxiv.org/abs/1909.07591",
            33   "license_title": null, 113   "license_title": null,
            34   "link_orkg": "", 114   "link_orkg": "",
            35   "metadata_created": "2024-11-25T14:25:42.066286", 115   "metadata_created": "2024-11-25T14:25:42.066286",
            n 36   "metadata_modified": "2024-11-25T14:39:30.726473", n 116   "metadata_modified": "2024-12-02T23:10:35.108168",
            37   "name": "natural-questions", 117   "name": "natural-questions",
            n 38   "notes": "The Natural Questions dataset embedded real users'  n 118   "notes": "The Natural Questions dataset consists of questions 
            39 information-seeking needs in a realistic information retrieval  119 extracted from web queries, with each question accompanied by a 
            40 context, using web search queries and corresponding Wikipedia pages as  120 corresponding Wikipedia article containing the answer.",
            41 sources for question answering tasks.", 
            42   "num_resources": 1, 121   "num_resources": 0,
            43   "num_tags": 0, 122   "num_tags": 12,
            44   "organization": { 123   "organization": {
            45     "approval_status": "approved", 124     "approval_status": "approved",
            46     "created": "2024-11-25T12:11:38.292601", 125     "created": "2024-11-25T12:11:38.292601",
            47     "description": "", 126     "description": "",
            48     "id": "079d46db-32df-4b48-91f3-0a8bc8f69559", 127     "id": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            49     "image_url": "", 128     "image_url": "",
            50     "is_organization": true, 129     "is_organization": true,
            51     "name": "no-organization", 130     "name": "no-organization",
            52     "state": "active", 131     "state": "active",
            53     "title": "No Organization", 132     "title": "No Organization",
            54     "type": "organization" 133     "type": "organization"
            55   }, 134   },
            56   "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559", 135   "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            57   "private": false, 136   "private": false,
            58   "relationships_as_object": [], 137   "relationships_as_object": [],
            59   "relationships_as_subject": [], 138   "relationships_as_subject": [],
            n 60   "resources": [ n 139   "resources": [],
            61     { 
            62       "cache_last_updated": null, 
            63       "cache_url": null, 
            64       "created": "2024-11-25T15:30:26", 
            65       "data": [ 
            66         "dcterms:title", 
            67         "dcterms:accessRights", 
            68         "dcterms:creator", 
            69         "dcterms:description", 
            70         "dcterms:issued", 
            71         "dcterms:language", 
            72         "dcterms:identifier", 
            73         "dcat:theme", 
            74         "dcterms:type", 
            75         "dcat:keyword", 
            76         "dcat:landingPage", 
            77         "dcterms:hasVersion", 
            78         "dcterms:format", 
            79         "mls:task", 
            80         "datacite:isDescribedBy" 
            81       ], 
            82       "description": "The json representation of the dataset with its  
            83 distributions based on DCAT.", 
            84       "format": "JSON", 
            85       "hash": "", 
            86       "id": "b5b841f2-8e52-4eaa-abed-474fcef64cc5", 
            87       "last_modified": "2024-11-25T14:39:30.719542", 
            88       "metadata_modified": "2024-11-25T14:39:30.729566", 
            89       "mimetype": "application/json", 
            90       "mimetype_inner": null, 
            91       "name": "Original Metadata", 
            92       "package_id": "ba656bde-dade-4f1d-822d-b71acb5ea3fd", 
            93       "position": 0, 
            94       "resource_type": null, 
            95       "size": 1199, 
            96       "state": "active", 
            97       "url":  
            98 resource/b5b841f2-8e52-4eaa-abed-474fcef64cc5/download/metadata.json", 
            99       "url_type": "upload" 
            100     } 
            101   ], 
            102   "services_used_list": "", 140   "services_used_list": "",
            103   "state": "active", 141   "state": "active",
            t 104   "tags": [], t 142   "tags": [
            143     {
            144       "display_name": "Google search",
            145       "id": "e1249ffe-e7b0-48ed-abd3-17238a731f5f",
            146       "name": "Google search",
            147       "state": "active",
            148       "vocabulary_id": null
            149     },
            150     {
            151       "display_name": "Natural Language Processing",
            152       "id": "035ca6e6-7473-43c7-82b3-cb1c2b4131fe",
            153       "name": "Natural Language Processing",
            154       "state": "active",
            155       "vocabulary_id": null
            156     },
            157     {
            158       "display_name": "Natural Questions",
            159       "id": "3db8f1b7-016c-4f8c-a611-8e72b43a78cd",
            160       "name": "Natural Questions",
            161       "state": "active",
            162       "vocabulary_id": null
            163     },
            164     {
            165       "display_name": "Question Answering",
            166       "id": "90f0a19e-b0c2-47b9-9180-dd38182c8003",
            167       "name": "Question Answering",
            168       "state": "active",
            169       "vocabulary_id": null
            170     },
            171     {
            172       "display_name": "Text Classification",
            173       "id": "daa24bd4-9e49-4ef5-870a-f51681ab0a20",
            174       "name": "Text Classification",
            175       "state": "active",
            176       "vocabulary_id": null
            177     },
            178     {
            179       "display_name": "Wikipedia",
            180       "id": "d3ff21b9-7b7f-4460-a073-b7a28c28e8ec",
            181       "name": "Wikipedia",
            182       "state": "active",
            183       "vocabulary_id": null
            184     },
            185     {
            186       "display_name": "natural language generation",
            187       "id": "436cc798-f9c9-4560-abb6-9de128af20be",
            188       "name": "natural language generation",
            189       "state": "active",
            190       "vocabulary_id": null
            191     },
            192     {
            193       "display_name": "natural language processing",
            194       "id": "8af9c93a-1d87-41e0-83d9-f5d01a2bbd0c",
            195       "name": "natural language processing",
            196       "state": "active",
            197       "vocabulary_id": null
            198     },
            199     {
            200       "display_name": "natural language understanding",
            201       "id": "4ca2fc08-fa20-49dc-8adc-e7c600bccbf1",
            202       "name": "natural language understanding",
            203       "state": "active",
            204       "vocabulary_id": null
            205     },
            206     {
            207       "display_name": "open domain",
            208       "id": "a0650408-488d-49e6-bc6c-ec8e9e359b31",
            209       "name": "open domain",
            210       "state": "active",
            211       "vocabulary_id": null
            212     },
            213     {
            214       "display_name": "question answering",
            215       "id": "d4e35d0b-ca07-4d05-bb27-50b2f30f2f00",
            216       "name": "question answering",
            217       "state": "active",
            218       "vocabulary_id": null
            219     },
            220     {
            221       "display_name": "web queries",
            222       "id": "18a7e260-8523-417f-9e27-a1a08a9759e6",
            223       "name": "web queries",
            224       "state": "active",
            225       "vocabulary_id": null
            226     }
            227   ],
            105   "title": "Natural Questions", 228   "title": "Natural Questions",
            106   "type": "dataset", 229   "type": "dataset",
            107   "version": "" 230   "version": ""
            108 } 231 }