Changes

On December 2, 2024 at 11:52:51 PM UTC, admin:
Updated description of MS MARCO from
MS MARCO is a dataset designed for reading comprehension and retrieval tasks, containing 8.8 million passages collected from Bing's results to 1 million queries. It is used to evaluate the effectiveness of neural ranking models.
to
Large-scale passage retrieval aims to fetch relevant passages from a million- or billion-scale collection for a given query to meet users’ information needs, serving as an important role in many downstream applications including open domain question answering, search engine, and recommendation system.
Added the following tags to MS MARCO
Removed the version from MS MARCO
Changed value of field defined_in to https://doi.org/10.1145/3583780.3615123 in MS MARCO
Changed value of field citation to ['https://doi.org/10.48550/arXiv.2110.07752', 'https://doi.org/10.48550/arXiv.2208.13661', 'https://doi.org/10.48550/arXiv.2312.15503', 'https://doi.org/10.48550/arXiv.2205.03284', 'https://doi.org/10.48550/arXiv.2202.05144', 'https://doi.org/10.48550/arXiv.2311.02834', 'https://doi.org/10.48550/arXiv.2403.14541', 'https://doi.org/10.1109/IKT51791.2020.9345613', 'https://doi.org/10.48550/arXiv.2203.07735', 'https://doi.org/10.48550/arXiv.2404.13950', 'https://doi.org/10.48550/arXiv.1909.03716', 'https://doi.org/10.48550/arXiv.2303.16780', 'https://doi.org/10.48550/arXiv.2203.00537', 'https://doi.org/10.48550/arXiv.2101.06980', 'https://doi.org/10.48550/arXiv.2404.15103'] in MS MARCO
Changed value of field landing_page to https://ai.stanford.edu/~suiyue/MARCO/ in MS MARCO
Deleted resource Original Metadata from MS MARCO
              
    
          
          
        
        
            f 1 { f 1 {
            2   "access_rights": "", 2   "access_rights": "",
            3   "author": "Tri Nguyen", 3   "author": "Tri Nguyen",
            4   "author_email": "", 4   "author_email": "",
            5   "citation": [ 5   "citation": [
            n n 6     "https://doi.org/10.48550/arXiv.2110.07752",
            7     "https://doi.org/10.48550/arXiv.2208.13661",
            8     "https://doi.org/10.48550/arXiv.2312.15503",
            9     "https://doi.org/10.48550/arXiv.2205.03284",
            10     "https://doi.org/10.48550/arXiv.2202.05144",
            11     "https://doi.org/10.48550/arXiv.2311.02834",
            12     "https://doi.org/10.48550/arXiv.2403.14541",
            13     "https://doi.org/10.1109/IKT51791.2020.9345613",
            14     "https://doi.org/10.48550/arXiv.2203.07735",
            6     "https://doi.org/10.48550/arXiv.2004.12832", 15     "https://doi.org/10.48550/arXiv.2404.13950",
            7     "https://doi.org/10.48550/arXiv.1911.03407" 16     "https://doi.org/10.48550/arXiv.1909.03716",
            17     "https://doi.org/10.48550/arXiv.2303.16780",
            18     "https://doi.org/10.48550/arXiv.2203.00537",
            19     "https://doi.org/10.48550/arXiv.2101.06980",
            20     "https://doi.org/10.48550/arXiv.2404.15103"
            8   ], 21   ],
            9   "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700", 22   "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
            n 10   "defined_in": "https://doi.org/10.48550/arXiv.1904.07531", n 23   "defined_in": "https://doi.org/10.1145/3583780.3615123",
            11   "doi": "10.57702/y9ev8opk", 24   "doi": "10.57702/y9ev8opk",
            12   "doi_date_published": "2024-11-25", 25   "doi_date_published": "2024-11-25",
            13   "doi_publisher": "TIB", 26   "doi_publisher": "TIB",
            14   "doi_status": true, 27   "doi_status": true,
            15   "domain": "https://service.tib.eu/ldmservice", 28   "domain": "https://service.tib.eu/ldmservice",
            16   "extra_authors": [ 29   "extra_authors": [
            17     { 30     {
            18       "extra_author": "Mir Rosenberg", 31       "extra_author": "Mir Rosenberg",
            19       "orcid": "" 32       "orcid": ""
            20     }, 33     },
            21     { 34     {
            22       "extra_author": "Xia Song", 35       "extra_author": "Xia Song",
            23       "orcid": "" 36       "orcid": ""
            24     }, 37     },
            25     { 38     {
            26       "extra_author": "Jianfeng Gao", 39       "extra_author": "Jianfeng Gao",
            27       "orcid": "" 40       "orcid": ""
            28     }, 41     },
            29     { 42     {
            30       "extra_author": "Saurabh Tiwary", 43       "extra_author": "Saurabh Tiwary",
            31       "orcid": "" 44       "orcid": ""
            32     }, 45     },
            33     { 46     {
            34       "extra_author": "Rangan Majumder", 47       "extra_author": "Rangan Majumder",
            35       "orcid": "" 48       "orcid": ""
            36     }, 49     },
            37     { 50     {
            38       "extra_author": "Li Deng", 51       "extra_author": "Li Deng",
            39       "orcid": "" 52       "orcid": ""
            40     } 53     }
            41   ], 54   ],
            n 42   "groups": [], n 55   "groups": [
            56     {
            57       "description": "",
            58       "display_name": "Document Retrieval",
            59       "id": "530cb507-0ba5-4237-8cef-47043758c987",
            60       "image_display_url": "",
            61       "name": "document-retrieval",
            62       "title": "Document Retrieval"
            63     },
            64     {
            65       "description": "",
            66       "display_name": "Information Retrieval",
            67       "id": "2193c32a-4b35-4438-b3a0-07c44d00abbc",
            68       "image_display_url": "",
            69       "name": "information-retrieval",
            70       "title": "Information Retrieval"
            71     },
            72     {
            73       "description": "",
            74       "display_name": "Machine Reading Comprehension",
            75       "id": "d4bdf82e-a4db-400a-b364-18088a397a26",
            76       "image_display_url": "",
            77       "name": "machine-reading-comprehension",
            78       "title": "Machine Reading Comprehension"
            79     },
            80     {
            81       "description": "",
            82       "display_name": "Passage Ranking",
            83       "id": "c7fd2228-f103-41f8-8aec-17d9f5584d44",
            84       "image_display_url": "",
            85       "name": "passage-ranking",
            86       "title": "Passage Ranking"
            87     },
            88     {
            89       "description": "",
            90       "display_name": "Question Answering",
            91       "id": "01e9bd6b-910d-421d-bb31-799604023211",
            92       "image_display_url": "",
            93       "name": "question-answering",
            94       "title": "Question Answering"
            95     }
            96   ],
            43   "id": "c5a87f2c-04ef-436f-8238-7ebec5a8d9df", 97   "id": "c5a87f2c-04ef-436f-8238-7ebec5a8d9df",
            44   "isopen": false, 98   "isopen": false,
            n 45   "landing_page": "https://microsoft.github.io/msmarco/", n 99   "landing_page": "https://ai.stanford.edu/~suiyue/MARCO/",
            46   "license_title": null, 100   "license_title": null,
            47   "link_orkg": "", 101   "link_orkg": "",
            48   "metadata_created": "2024-11-25T14:23:55.046003", 102   "metadata_created": "2024-11-25T14:23:55.046003",
            n 49   "metadata_modified": "2024-11-25T14:37:35.175802", n 103   "metadata_modified": "2024-12-02T23:52:50.364344",
            50   "name": "ms-marco", 104   "name": "ms-marco",
            n 51   "notes": "MS MARCO is a dataset designed for reading comprehension  n 105   "notes": "Large-scale passage retrieval aims to fetch relevant 
            52 and retrieval tasks, containing 8.8 million passages collected from  106 passages from a million- or billion-scale collection for a given query 
            53 Bing's results to 1 million queries. It is used to evaluate the  107 to meet users\u2019 information needs, serving as an important role in 
            54 effectiveness of neural ranking models.", 108 many downstream applications including open domain question answering, 
            109 search engine, and recommendation system.",
            55   "num_resources": 1, 110   "num_resources": 0,
            56   "num_tags": 0, 111   "num_tags": 23,
            57   "organization": { 112   "organization": {
            58     "approval_status": "approved", 113     "approval_status": "approved",
            59     "created": "2024-11-25T12:11:38.292601", 114     "created": "2024-11-25T12:11:38.292601",
            60     "description": "", 115     "description": "",
            61     "id": "079d46db-32df-4b48-91f3-0a8bc8f69559", 116     "id": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            62     "image_url": "", 117     "image_url": "",
            63     "is_organization": true, 118     "is_organization": true,
            64     "name": "no-organization", 119     "name": "no-organization",
            65     "state": "active", 120     "state": "active",
            66     "title": "No Organization", 121     "title": "No Organization",
            67     "type": "organization" 122     "type": "organization"
            68   }, 123   },
            69   "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559", 124   "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            70   "private": false, 125   "private": false,
            71   "relationships_as_object": [], 126   "relationships_as_object": [],
            72   "relationships_as_subject": [], 127   "relationships_as_subject": [],
            n 73   "resources": [ n 128   "resources": [],
            74     { 
            75       "cache_last_updated": null, 
            76       "cache_url": null, 
            77       "created": "2024-11-25T15:30:26", 
            78       "data": [ 
            79         "dcterms:title", 
            80         "dcterms:accessRights", 
            81         "dcterms:creator", 
            82         "dcterms:description", 
            83         "dcterms:issued", 
            84         "dcterms:language", 
            85         "dcterms:identifier", 
            86         "dcat:theme", 
            87         "dcterms:type", 
            88         "dcat:keyword", 
            89         "dcat:landingPage", 
            90         "dcterms:hasVersion", 
            91         "dcterms:format", 
            92         "mls:task", 
            93         "datacite:isDescribedBy" 
            94       ], 
            95       "description": "The json representation of the dataset with its  
            96 distributions based on DCAT.", 
            97       "format": "JSON", 
            98       "hash": "", 
            99       "id": "cc230c72-d3ec-415e-877d-b3403398331f", 
            100       "last_modified": "2024-11-25T14:37:35.167827", 
            101       "metadata_modified": "2024-11-25T14:37:35.179092", 
            102       "mimetype": "application/json", 
            103       "mimetype_inner": null, 
            104       "name": "Original Metadata", 
            105       "package_id": "c5a87f2c-04ef-436f-8238-7ebec5a8d9df", 
            106       "position": 0, 
            107       "resource_type": null, 
            108       "size": 1337, 
            109       "state": "active", 
            110       "url":  
            111 resource/cc230c72-d3ec-415e-877d-b3403398331f/download/metadata.json", 
            112       "url_type": "upload" 
            113     } 
            114   ], 
            115   "services_used_list": "", 129   "services_used_list": "",
            116   "state": "active", 130   "state": "active",
            n 117   "tags": [], n 131   "tags": [
            132     {
            133       "display_name": "MS MARCO",
            134       "id": "6bece918-b5d4-4314-a6f7-c8c1b57956d9",
            135       "name": "MS MARCO",
            136       "state": "active",
            137       "vocabulary_id": null
            138     },
            139     {
            140       "display_name": "Machine Reading Comprehension",
            141       "id": "0bffb536-2e89-437a-898c-9e55eb8f5446",
            142       "name": "Machine Reading Comprehension",
            143       "state": "active",
            144       "vocabulary_id": null
            145     },
            146     {
            147       "display_name": "Natural Language Processing",
            148       "id": "035ca6e6-7473-43c7-82b3-cb1c2b4131fe",
            149       "name": "Natural Language Processing",
            150       "state": "active",
            151       "vocabulary_id": null
            152     },
            153     {
            154       "display_name": "QA",
            155       "id": "179724b1-43fb-44f3-b17a-ff3550071d87",
            156       "name": "QA",
            157       "state": "active",
            158       "vocabulary_id": null
            159     },
            160     {
            161       "display_name": "Question Answering",
            162       "id": "90f0a19e-b0c2-47b9-9180-dd38182c8003",
            163       "name": "Question Answering",
            164       "state": "active",
            165       "vocabulary_id": null
            166     },
            167     {
            168       "display_name": "document",
            169       "id": "796b2125-074c-41a7-be5e-7dbfa21baa11",
            170       "name": "document",
            171       "state": "active",
            172       "vocabulary_id": null
            173     },
            174     {
            175       "display_name": "document retrieval",
            176       "id": "1eb6e992-6a7d-476f-97d7-b6a295368fe2",
            177       "name": "document retrieval",
            178       "state": "active",
            179       "vocabulary_id": null
            180     },
            181     {
            182       "display_name": "human generated dataset",
            183       "id": "c5b141ba-1a91-4e2b-b350-007ebc08e3e4",
            184       "name": "human generated dataset",
            185       "state": "active",
            186       "vocabulary_id": null
            187     },
            188     {
            189       "display_name": "human-generated dataset",
            190       "id": "a29ba68d-3443-4dc9-aa39-dcf7657f2292",
            191       "name": "human-generated dataset",
            192       "state": "active",
            193       "vocabulary_id": null
            194     },
            195     {
            196       "display_name": "information retrieval",
            197       "id": "c094f269-c169-4c66-b2f1-98967cbef543",
            198       "name": "information retrieval",
            199       "state": "active",
            200       "vocabulary_id": null
            201     },
            202     {
            203       "display_name": "machine reading comprehension",
            204       "id": "81904f9d-c7ac-4a01-a208-7101b3cdaa47",
            205       "name": "machine reading comprehension",
            206       "state": "active",
            207       "vocabulary_id": null
            208     },
            209     {
            210       "display_name": "open-domain QA",
            211       "id": "49d1bdd9-0c26-46da-bbda-c4618be72681",
            212       "name": "open-domain QA",
            213       "state": "active",
            214       "vocabulary_id": null
            215     },
            216     {
            217       "display_name": "passage ranking",
            218       "id": "05530dc7-3c93-466d-a828-e76c1ab75332",
            219       "name": "passage ranking",
            220       "state": "active",
            221       "vocabulary_id": null
            222     },
            223     {
            224       "display_name": "passage retrieval",
            225       "id": "24e47c7a-fc2d-483d-82ac-f63b32303276",
            226       "name": "passage retrieval",
            227       "state": "active",
            228       "vocabulary_id": null
            229     },
            230     {
            231       "display_name": "query",
            232       "id": "5c903983-4289-498e-9ab1-969eddd7119e",
            233       "name": "query",
            234       "state": "active",
            235       "vocabulary_id": null
            236     },
            237     {
            238       "display_name": "question answering",
            239       "id": "d4e35d0b-ca07-4d05-bb27-50b2f30f2f00",
            240       "name": "question answering",
            241       "state": "active",
            242       "vocabulary_id": null
            243     },
            244     {
            245       "display_name": "ranking",
            246       "id": "b548741b-2174-4996-86fa-d8421e0f4d24",
            247       "name": "ranking",
            248       "state": "active",
            249       "vocabulary_id": null
            250     },
            251     {
            252       "display_name": "reading comprehension",
            253       "id": "d1f7f9e1-373b-4452-9427-a72e3f8af701",
            254       "name": "reading comprehension",
            255       "state": "active",
            256       "vocabulary_id": null
            257     },
            258     {
            259       "display_name": "search query logs",
            260       "id": "d2721519-dba5-4567-a1d8-6568d881b85d",
            261       "name": "search query logs",
            262       "state": "active",
            263       "vocabulary_id": null
            264     },
            265     {
            266       "display_name": "single entity",
            267       "id": "96a6dc93-4c5c-41bd-a3de-4c6eb347e168",
            268       "name": "single entity",
            269       "state": "active",
            270       "vocabulary_id": null
            271     },
            272     {
            273       "display_name": "single relation",
            274       "id": "f4b0bddd-8fab-44fb-8f93-1a8aea1a23ab",
            275       "name": "single relation",
            276       "state": "active",
            277       "vocabulary_id": null
            278     },
            279     {
            280       "display_name": "user click",
            281       "id": "2797776e-78c1-49ff-b055-b0e980f795eb",
            282       "name": "user click",
            283       "state": "active",
            284       "vocabulary_id": null
            285     },
            286     {
            287       "display_name": "zero-shot retrieval",
            288       "id": "c1e134bc-f820-427f-845b-acf9a5994f12",
            289       "name": "zero-shot retrieval",
            290       "state": "active",
            291       "vocabulary_id": null
            292     }
            293   ],
            118   "title": "MS MARCO", 294   "title": "MS MARCO",
            119   "type": "dataset", 295   "type": "dataset",
            t 120   "version": "v1.1" t 296   "version": ""
            121 } 297 }