{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00043121","sets":["1164:3782:3816:3820"]},"path":["3820"],"owner":"1","recid":"43121","title":["文書構造情報の抽出とメタデータ化"],"pubdate":{"attribute_name":"公開日","attribute_value":"2003-03-28"},"_buckets":{"deposit":"dd1fa8fe-7bef-49f7-b3cd-0295d09d22ec"},"_deposit":{"id":"43121","pid":{"type":"depid","value":"43121","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"文書構造情報の抽出とメタデータ化","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"文書構造情報の抽出とメタデータ化"},{"subitem_title":"Automatic Extraction of Document Metadata and its RDF - based Representation","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2003-03-28","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"株式会社ジャストシステム"},{"subitem_text_value":"法政大学エクテンションカレッジ"},{"subitem_text_value":"株式会社ジャストシステム"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Justsystem Corporation","subitem_text_language":"en"},{"subitem_text_value":"Hosei University Extension College","subitem_text_language":"en"},{"subitem_text_value":"Justsystem Corporation","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/43121/files/IPSJ-DD02038007.pdf"},"date":[{"dateType":"Available","dateValue":"2005-03-28"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-DD02038007.pdf","filesize":[{"value":"183.5 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"32"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"9f6ff13c-2f7b-4a7a-bb65-0db275a3da00","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2003 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"川崎, 洋治"},{"creatorName":"野村, 直之"},{"creatorName":"中川, 尚"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Yoji, Kawasaki","creatorNameLang":"en"},{"creatorName":"Naoyuki, Nomura","creatorNameLang":"en"},{"creatorName":"Takashi, Nakagawa","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10539261","subitem_source_identifier_type":"NCID"}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"文書はその本文内部に、自身に対する書誌データ、すなわちメタデータを含んでいることが多い。本稿では、プレーンテキストやHTML文書の内容記述部分から作者や見出し階層のようなメタデータを自動的に抽出する技術を紹介する。次に、抽出したメタデータを格納するための枠組みをRDF Schemaによって定義することで、メタデータを流通させる仕組みを提案する。最後に、文書からのメタデータ自動抽出、およびSemantic Web標準に準拠したその構造表現化による情報流通上の効果について論じる。","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Many documents have their bibliographic information in their body texts, such as creator and chapter-section hierarchy. We have developed an automatic method of extracting this kind of information which is intrinsically embedded in plain-text or HTML documents. Then, the extracted document metadata is restructured into our \"RDF Schema\"-based representation, which is to be useful in many applications for document distribution and information sharing.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"50","bibliographic_titles":[{"bibliographic_title":"情報処理学会研究報告デジタルドキュメント（DD）"}],"bibliographicPageStart":"43","bibliographicIssueDates":{"bibliographicIssueDate":"2003-03-28","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"37(2002-DD-038)","bibliographicVolumeNumber":"2003"}]},"relation_version_is_last":true,"weko_creator_id":"1"},"id":43121,"updated":"2025-01-22T11:07:19.313318+00:00","links":{},"created":"2025-01-18T23:09:36.126882+00:00"}