Changes

View changes from to
On December 2, 2024 at 9:59:54 PM UTC, admin:
Changed title to Penn Treebank (previously Penn TreeBank)
Set author of Penn Treebank to Mitchell P Marcus (previously Penn TreeBank)
Updated description of Penn Treebank from
The dataset used for parsing tasks is the Penn TreeBank containing syntactic annotations used for training parsing models.
to
The Penn Treebank dataset contains one million words of 1989 Wall Street Journal material annotated in Treebank II style, with 42k sentences of varying lengths.
Added the following tags to Penn Treebank
Changed value of field defined_in to https://doi.org/10.48550/arXiv.1808.05908 in Penn Treebank
Changed value of field citation to ['https://doi.org/10.48550/arXiv.1511.06349', 'https://doi.org/10.48550/arXiv.1708.08863', 'https://doi.org/10.48550/arXiv.2106.10704', 'https://doi.org/10.48550/arXiv.2001.03294', 'https://doi.org/10.48550/arXiv.1706.03993', 'https://doi.org/10.48550/arXiv.1909.03004', 'https://doi.org/10.48550/arXiv.2107.08382', 'https://doi.org/10.1109/IJCNN.2019.8852464', 'https://doi.org/10.48550/arXiv.1711.09873', 'https://doi.org/10.48550/arXiv.1807.09830', 'https://doi.org/10.48550/arXiv.1802.02116', 'https://doi.org/10.48550/arXiv.2005.00054', 'https://doi.org/10.48550/arXiv.1711.04755', 'https://doi.org/10.48550/arXiv.1809.03702', 'https://doi.org/10.48550/arXiv.1606.01280', 'https://doi.org/10.48550/arXiv.1704.02798', 'https://doi.org/10.48550/arXiv.1909.03569'] in Penn Treebank
Changed value of field landing_page to https://www.ling.upenn.edu/courses/Fall_2003/ling001/penn_treebank.html in Penn Treebank
Deleted resource Original Metadata from Penn Treebank
              
    
          
          
        
        
            f 1 { f 1 {
            2   "access_rights": "", 2   "access_rights": "",
            n 3   "author": "Penn TreeBank", n 3   "author": "Mitchell P Marcus",
            4   "author_email": "", 4   "author_email": "",
            n 5   "citation": [], n 5   "citation": [
            6     "https://doi.org/10.48550/arXiv.1511.06349",
            7     "https://doi.org/10.48550/arXiv.1708.08863",
            8     "https://doi.org/10.48550/arXiv.2106.10704",
            9     "https://doi.org/10.48550/arXiv.2001.03294",
            10     "https://doi.org/10.48550/arXiv.1706.03993",
            11     "https://doi.org/10.48550/arXiv.1909.03004",
            12     "https://doi.org/10.48550/arXiv.2107.08382",
            13     "https://doi.org/10.1109/IJCNN.2019.8852464",
            14     "https://doi.org/10.48550/arXiv.1711.09873",
            15     "https://doi.org/10.48550/arXiv.1807.09830",
            16     "https://doi.org/10.48550/arXiv.1802.02116",
            17     "https://doi.org/10.48550/arXiv.2005.00054",
            18     "https://doi.org/10.48550/arXiv.1711.04755",
            19     "https://doi.org/10.48550/arXiv.1809.03702",
            20     "https://doi.org/10.48550/arXiv.1606.01280",
            21     "https://doi.org/10.48550/arXiv.1704.02798",
            22     "https://doi.org/10.48550/arXiv.1909.03569"
            23   ],
            6   "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700", 24   "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
            n 7   "defined_in": "https://doi.org/10.48550/arXiv.1904.02954", n 25   "defined_in": "https://doi.org/10.48550/arXiv.1808.05908",
            8   "doi": "10.57702/u5gg4t6i", 26   "doi": "10.57702/u5gg4t6i",
            9   "doi_date_published": "2024-11-25", 27   "doi_date_published": "2024-11-25",
            10   "doi_publisher": "TIB", 28   "doi_publisher": "TIB",
            11   "doi_status": true, 29   "doi_status": true,
            12   "domain": "https://service.tib.eu/ldmservice", 30   "domain": "https://service.tib.eu/ldmservice",
            n n 31   "extra_authors": [
            32     {
            33       "extra_author": "Mary Ann Marcinkiewicz",
            34       "orcid": ""
            35     },
            36     {
            37       "extra_author": "Beatrice Santorini",
            38       "orcid": ""
            39     }
            40   ],
            13   "groups": [], 41   "groups": [
            42     {
            43       "description": "",
            44       "display_name": "Corpus",
            45       "id": "05845d32-256e-4036-82db-8a7f9cd22a67",
            46       "image_display_url": "",
            47       "name": "corpus",
            48       "title": "Corpus"
            49     },
            50     {
            51       "description": "",
            52       "display_name": "Corpus Linguistics",
            53       "id": "03b364f0-9f20-4a15-8435-570289fd8fec",
            54       "image_display_url": "",
            55       "name": "corpus-linguistics",
            56       "title": "Corpus Linguistics"
            57     },
            58     {
            59       "description": "",
            60       "display_name": "Dependency Parsing",
            61       "id": "1ecacb33-7101-45bc-a2d1-2521d320a1a3",
            62       "image_display_url": "",
            63       "name": "dependency-parsing",
            64       "title": "Dependency Parsing"
            65     },
            66     {
            67       "description": "",
            68       "display_name": "Language Modeling",
            69       "id": "f0c89329-f1ed-4ba3-90d2-5113fff9bf72",
            70       "image_display_url": "",
            71       "name": "language-modeling",
            72       "title": "Language Modeling"
            73     },
            74     {
            75       "description": "",
            76       "display_name": "Machine Translation",
            77       "id": "a24abd43-64a1-496d-a2a8-613ae21d7e33",
            78       "image_display_url": "",
            79       "name": "machine-translation",
            80       "title": "Machine Translation"
            81     },
            82     {
            83       "description": "",
            84       "display_name": "Natural Language Processing",
            85       "id": "5b974bcc-8f79-40fc-a05d-75b861d55ed0",
            86       "image_display_url": "",
            87       "name": "natural-language-processing",
            88       "title": "Natural Language Processing"
            89     },
            90     {
            91       "description": "",
            92       "display_name": "Semantics",
            93       "id": "7dd6c44f-a80e-4e93-a9de-d9816a8698f7",
            94       "image_display_url": "",
            95       "name": "semantics",
            96       "title": "Semantics"
            97     },
            98     {
            99       "description": "",
            100       "display_name": "Sequence Processing",
            101       "id": "c1437f98-a8fb-43db-8d6a-dd088c8fdf2f",
            102       "image_display_url": "",
            103       "name": "sequence-processing",
            104       "title": "Sequence Processing"
            105     },
            106     {
            107       "description": "",
            108       "display_name": "Syntax",
            109       "id": "950ac35d-266d-494e-a5b1-b1fcaa9fbd2f",
            110       "image_display_url": "",
            111       "name": "syntax",
            112       "title": "Syntax"
            113     },
            114     {
            115       "description": "",
            116       "display_name": "Text Analysis",
            117       "id": "c6e4118d-2ceb-49cc-97b8-1ddd4db9ffaa",
            118       "image_display_url": "",
            119       "name": "text-analysis",
            120       "title": "Text Analysis"
            121     },
            122     {
            123       "description": "",
            124       "display_name": "Text Classification",
            125       "id": "0707d099-de73-41dc-85f6-93e4efa6bf14",
            126       "image_display_url": "",
            127       "name": "text-classification",
            128       "title": "Text Classification"
            129     }
            130   ],
            14   "id": "28120075-5efa-457d-955e-985dcb7efa86", 131   "id": "28120075-5efa-457d-955e-985dcb7efa86",
            15   "isopen": false, 132   "isopen": false,
            n 16   "landing_page": "", n 133   "landing_page": 
            134 ps://www.ling.upenn.edu/courses/Fall_2003/ling001/penn_treebank.html",
            17   "license_title": null, 135   "license_title": null,
            18   "link_orkg": "", 136   "link_orkg": "",
            19   "metadata_created": "2024-11-25T14:17:46.965003", 137   "metadata_created": "2024-11-25T14:17:46.965003",
            n 20   "metadata_modified": "2024-11-25T14:39:49.069487", n 138   "metadata_modified": "2024-12-02T21:59:53.319161",
            21   "name": "penn-treebank", 139   "name": "penn-treebank",
            n 22   "notes": "The dataset used for parsing tasks is the Penn TreeBank  n 140   "notes": "The Penn Treebank dataset contains one million words of 
            23 containing syntactic annotations used for training parsing models.", 141 1989 Wall Street Journal material annotated in Treebank II style, with 
            142 42k sentences of varying lengths.",
            24   "num_resources": 1, 143   "num_resources": 0,
            25   "num_tags": 0, 144   "num_tags": 24,
            26   "organization": { 145   "organization": {
            27     "approval_status": "approved", 146     "approval_status": "approved",
            28     "created": "2024-11-25T12:11:38.292601", 147     "created": "2024-11-25T12:11:38.292601",
            29     "description": "", 148     "description": "",
            30     "id": "079d46db-32df-4b48-91f3-0a8bc8f69559", 149     "id": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            31     "image_url": "", 150     "image_url": "",
            32     "is_organization": true, 151     "is_organization": true,
            33     "name": "no-organization", 152     "name": "no-organization",
            34     "state": "active", 153     "state": "active",
            35     "title": "No Organization", 154     "title": "No Organization",
            36     "type": "organization" 155     "type": "organization"
            37   }, 156   },
            38   "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559", 157   "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            39   "private": false, 158   "private": false,
            40   "relationships_as_object": [], 159   "relationships_as_object": [],
            41   "relationships_as_subject": [], 160   "relationships_as_subject": [],
            n 42   "resources": [ n 161   "resources": [],
            43     { 162   "services_used_list": "",
            44       "cache_last_updated": null, 
            45       "cache_url": null, 
            46       "created": "2024-11-25T15:30:26", 
            47       "data": [ 
            48         "dcterms:title", 
            49         "dcterms:accessRights", 
            50         "dcterms:creator", 
            51         "dcterms:description", 
            52         "dcterms:issued", 
            53         "dcterms:language", 
            54         "dcterms:identifier", 
            55         "dcat:theme", 
            56         "dcterms:type", 
            57         "dcat:keyword", 
            58         "dcat:landingPage", 
            59         "dcterms:hasVersion", 
            60         "dcterms:format", 
            61         "mls:task", 
            62         "datacite:isDescribedBy" 
            63       ], 
            64       "description": "The json representation of the dataset with its  
            65 distributions based on DCAT.", 
            66       "format": "JSON", 
            67       "hash": "", 
            68       "id": "938b91bb-e17c-4c25-8785-f76edc8897dd", 
            69       "last_modified": "2024-11-25T14:39:49.062367", 
            70       "metadata_modified": "2024-11-25T14:39:49.073018", 
            71       "mimetype": "application/json", 
            72       "mimetype_inner": null, 
            73       "name": "Original Metadata", 
            74       "package_id": "28120075-5efa-457d-955e-985dcb7efa86", 
            75       "position": 0, 
            76       "resource_type": null, 
            77       "size": 683, 
            78       "state": "active", 163   "state": "active",
            79       "url":  164   "tags": [
            80 resource/938b91bb-e17c-4c25-8785-f76edc8897dd/download/metadata.json", 165     {
            81       "url_type": "upload" 166       "display_name": "Corpus",
            167       "id": "5e434f4b-89f6-489e-9e6e-d2ff6003d493",
            168       "name": "Corpus",
            169       "state": "active",
            170       "vocabulary_id": null
            171     },
            172     {
            173       "display_name": "Corpus Linguistics",
            174       "id": "a8e6be92-68ba-48fe-94a9-5e2ce13a0922",
            175       "name": "Corpus Linguistics",
            176       "state": "active",
            177       "vocabulary_id": null
            178     },
            179     {
            180       "display_name": "Dependency Parsing",
            181       "id": "e761a658-bada-4efd-8fca-ccf035ef9e6d",
            182       "name": "Dependency Parsing",
            183       "state": "active",
            184       "vocabulary_id": null
            185     },
            186     {
            187       "display_name": "LSTM",
            188       "id": "f8beea4d-2f51-405b-819f-60cd25199524",
            189       "name": "LSTM",
            190       "state": "active",
            191       "vocabulary_id": null
            192     },
            193     {
            194       "display_name": "Language Modeling",
            195       "id": "150cb2f3-fcd6-4438-b775-4b37bc942ea7",
            196       "name": "Language Modeling",
            197       "state": "active",
            198       "vocabulary_id": null
            199     },
            200     {
            201       "display_name": "Linguistics",
            202       "id": "ca6eeb69-5671-4b85-9c0d-2805025d78ce",
            203       "name": "Linguistics",
            204       "state": "active",
            205       "vocabulary_id": null
            206     },
            207     {
            208       "display_name": "Machine Translation",
            209       "id": "55f5baba-6c20-44c5-b149-da1768badaf4",
            210       "name": "Machine Translation",
            211       "state": "active",
            212       "vocabulary_id": null
            213     },
            214     {
            215       "display_name": "Natural Language",
            216       "id": "4686b8e4-6c75-42f6-85db-76afd6760dd6",
            217       "name": "Natural Language",
            218       "state": "active",
            219       "vocabulary_id": null
            220     },
            221     {
            222       "display_name": "Natural Language Processing",
            223       "id": "035ca6e6-7473-43c7-82b3-cb1c2b4131fe",
            224       "name": "Natural Language Processing",
            225       "state": "active",
            226       "vocabulary_id": null
            227     },
            228     {
            229       "display_name": "Penn Treebank",
            230       "id": "ff36f647-095b-4f4c-a93f-5b5efc80ba39",
            231       "name": "Penn Treebank",
            232       "state": "active",
            233       "vocabulary_id": null
            234     },
            235     {
            236       "display_name": "Regularization",
            237       "id": "cfd9d695-1792-4c53-ab4f-d699e486842c",
            238       "name": "Regularization",
            239       "state": "active",
            240       "vocabulary_id": null
            241     },
            242     {
            243       "display_name": "Semantics",
            244       "id": "c8f21da9-cc97-4387-842a-3aabc9b6c189",
            245       "name": "Semantics",
            246       "state": "active",
            247       "vocabulary_id": null
            248     },
            249     {
            250       "display_name": "Sentiment Analysis",
            251       "id": "8523cc06-351a-4eef-b126-04451cbc0d13",
            252       "name": "Sentiment Analysis",
            253       "state": "active",
            254       "vocabulary_id": null
            255     },
            256     {
            257       "display_name": "Stanford Dependencies",
            258       "id": "c70e284f-ac24-4a2e-9272-9f5778329e4c",
            259       "name": "Stanford Dependencies",
            260       "state": "active",
            261       "vocabulary_id": null
            262     },
            263     {
            264       "display_name": "Syntax",
            265       "id": "a98dc667-2474-4532-bb2c-a3161ca91a26",
            266       "name": "Syntax",
            267       "state": "active",
            268       "vocabulary_id": null
            269     },
            270     {
            271       "display_name": "Text",
            272       "id": "74f5b2bc-c290-4e26-a01d-cce9fdf6e957",
            273       "name": "Text",
            274       "state": "active",
            275       "vocabulary_id": null
            276     },
            277     {
            278       "display_name": "Text Analysis",
            279       "id": "1e046b3d-9150-4494-a56a-5c6eeea2423e",
            280       "name": "Text Analysis",
            281       "state": "active",
            282       "vocabulary_id": null
            283     },
            284     {
            285       "display_name": "Text Classification",
            286       "id": "daa24bd4-9e49-4ef5-870a-f51681ab0a20",
            287       "name": "Text Classification",
            288       "state": "active",
            289       "vocabulary_id": null
            290     },
            291     {
            292       "display_name": "Treebank",
            293       "id": "b12b06aa-7604-4297-b991-b1e80d11645c",
            294       "name": "Treebank",
            295       "state": "active",
            296       "vocabulary_id": null
            297     },
            298     {
            299       "display_name": "Treebank II",
            300       "id": "57e193b2-bad5-4f46-9709-6a1ee30cb25a",
            301       "name": "Treebank II",
            302       "state": "active",
            303       "vocabulary_id": null
            304     },
            305     {
            306       "display_name": "dependency parsing",
            307       "id": "eac3deb0-18d7-464e-baf3-4ec41b1c15bc",
            308       "name": "dependency parsing",
            309       "state": "active",
            310       "vocabulary_id": null
            311     },
            312     {
            313       "display_name": "natural language processing",
            314       "id": "8af9c93a-1d87-41e0-83d9-f5d01a2bbd0c",
            315       "name": "natural language processing",
            316       "state": "active",
            317       "vocabulary_id": null
            318     },
            319     {
            320       "display_name": "text analysis",
            321       "id": "8dede2ad-b59f-4a39-b2b2-4259c7ebcaea",
            322       "name": "text analysis",
            323       "state": "active",
            324       "vocabulary_id": null
            325     },
            326     {
            327       "display_name": "text classification",
            328       "id": "98d3b2df-ea96-4826-971b-6c5bf64c999d",
            329       "name": "text classification",
            330       "state": "active",
            331       "vocabulary_id": null
            82     } 332     }
            83   ], 333   ],
            t 84   "services_used_list": "", t 
            85   "state": "active", 
            86   "tags": [], 
            87   "title": "Penn TreeBank", 334   "title": "Penn Treebank",
            88   "type": "dataset", 335   "type": "dataset",
            89   "version": "" 336   "version": ""
            90 } 337 }