{ "access": { "embargo": { "active": false, "reason": null }, "files": "public", "record": "public", "status": "open" }, "created": "2019-05-28T13:32:16.371887+00:00", "custom_fields": { "meeting:meeting": { "acronym": "KI 2004", "dates": "20-24 September 2004", "place": "Germany", "title": "Advances in Artificial Intelligence" } }, "deletion_status": { "is_deleted": false, "status": "P" }, "files": { "count": 1, "enabled": true, "entries": { "corpus-genre-ki-04.zip": { "checksum": "md5:c49a30e62019f90ebd1d28f7f62f9bac", "ext": "zip", "id": "acbbe613-e234-4aa8-9e02-d65865eea951", "key": "corpus-genre-ki-04.zip", "metadata": null, "mimetype": "application/zip", "size": 11515917 } }, "order": [], "total_bytes": 11515917 }, "id": "3233881", "is_draft": false, "is_published": true, "links": { "access": "https://zenodo.org/api/records/3233881/access", "access_links": "https://zenodo.org/api/records/3233881/access/links", "access_request": "https://zenodo.org/api/records/3233881/access/request", "access_users": "https://zenodo.org/api/records/3233881/access/users", "archive": "https://zenodo.org/api/records/3233881/files-archive", "archive_media": "https://zenodo.org/api/records/3233881/media-files-archive", "communities": "https://zenodo.org/api/records/3233881/communities", "communities-suggestions": "https://zenodo.org/api/records/3233881/communities-suggestions", "doi": "https://doi.org/10.5281/zenodo.3233881", "draft": "https://zenodo.org/api/records/3233881/draft", "files": "https://zenodo.org/api/records/3233881/files", "latest": "https://zenodo.org/api/records/3233881/versions/latest", "latest_html": "https://zenodo.org/records/3233881/latest", "media_files": "https://zenodo.org/api/records/3233881/media-files", "parent": "https://zenodo.org/api/records/3233880", "parent_doi": "https://zenodo.org/doi/10.5281/zenodo.3233880", "parent_html": "https://zenodo.org/records/3233880", "requests": "https://zenodo.org/api/records/3233881/requests", "reserve_doi": "https://zenodo.org/api/records/3233881/draft/pids/doi", "self": "https://zenodo.org/api/records/3233881", "self_doi": "https://zenodo.org/doi/10.5281/zenodo.3233881", "self_html": "https://zenodo.org/records/3233881", "self_iiif_manifest": "https://zenodo.org/api/iiif/record:3233881/manifest", "self_iiif_sequence": "https://zenodo.org/api/iiif/record:3233881/sequence/default", "versions": "https://zenodo.org/api/records/3233881/versions" }, "media_files": { "count": 0, "enabled": false, "entries": {}, "order": [], "total_bytes": 0 }, "metadata": { "creators": [ { "affiliations": [ { "name": "Universit\u00e4t Paderborn" } ], "person_or_org": { "family_name": "Stein", "given_name": "Benno", "identifiers": [ { "identifier": "0000-0001-9033-2217", "scheme": "orcid" } ], "name": "Stein, Benno", "type": "personal" } }, { "affiliations": [ { "name": "Universit\u00e4t Paderborn" } ], "person_or_org": { "family_name": "Meyer zu Eissen", "given_name": "Sven", "name": "Meyer zu Eissen, Sven", "type": "personal" } } ], "description": "
The web genre corpus 2004 (Genre-KI-04) is designed for the evaluation of techniques for genre classification. It consists of 1239 web documents classified into 8 genres and basic meta data for each of the files.
\n\nThe corpus consists of the HTML documents grouped into directories according to their respective genre. The first lines of each document contain the meta information for each document in a HTML comment. This information includes the URL the document was downloaded from as well as the document title and the parsed text.
\n\nA definition of the genres can be found in the paper (http://dx.doi.org/10.1007/978-3-540-30221-6_20) or in the corpus. The distribution of the documents among the genres is summarized below.
\n\nData curated by the Webis Group (webis.de)
", "title": "Webis", "type": { "id": "organization" }, "website": "https://webis.de" }, "revision_id": 1, "slug": "webis", "updated": "2023-10-16T06:20:44.424792+00:00" } ], "ids": [ "32031607-a92a-4ccf-9ca7-6cc3a8a3426f" ] }, "id": "3233880", "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.3233880", "provider": "datacite" } } }, "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.3233881", "provider": "datacite" }, "oai": { "identifier": "oai:zenodo.org:3233881", "provider": "oai" } }, "revision_id": 7, "stats": { "all_versions": { "data_volume": 886725609.0, "downloads": 77, "unique_downloads": 56, "unique_views": 466, "views": 517 }, "this_version": { "data_volume": 886725609.0, "downloads": 77, "unique_downloads": 56, "unique_views": 466, "views": 517 } }, "status": "published", "updated": "2020-01-24T19:22:56.846652+00:00", "versions": { "index": 1, "is_latest": true } }