{"created":"2025-01-18T22:50:32.744495+00:00","updated":"2025-01-22T23:14:34.467491+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00017583","sets":["934:1022:1049:1051"]},"path":["1051"],"owner":"1","recid":"17583","title":["HTMLの表形式データの構造認識と携帯端末表示への応用"],"pubdate":{"attribute_name":"公開日","attribute_value":"2003-09-15"},"_buckets":{"deposit":"61277a2f-0bc5-47f5-9dcd-f046723135d3"},"_deposit":{"id":"17583","pid":{"type":"depid","value":"17583","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"HTMLの表形式データの構造認識と携帯端末表示への応用","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"HTMLの表形式データの構造認識と携帯端末表示への応用"},{"subitem_title":"Recognition of HTML Table Data and Its Application for Displaying on Mobile Terminal Screen","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"研究論文","subitem_subject_scheme":"Other"}]},"item_type_id":"3","publish_date":"2003-09-15","item_3_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東京電機大学工学部"},{"subitem_text_value":"東京電機大学工学部"},{"subitem_text_value":"東京電機大学工学部／現在，株式会社豆蔵"},{"subitem_text_value":"東京大学情報基盤センター"}]},"item_3_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"School of Engineering, Tokyo Denki University","subitem_text_language":"en"},{"subitem_text_value":"School of Engineering, Tokyo Denki University","subitem_text_language":"en"},{"subitem_text_value":"School of Engineering, Tokyo Denki University/Presently with Mamezou Co., Ltd.","subitem_text_language":"en"},{"subitem_text_value":"Information Technology Center, The University of Tokyo","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/17583/files/IPSJ-TOD4412004.pdf"},"date":[{"dateType":"Available","dateValue":"2005-09-15"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-TOD4412004.pdf","filesize":[{"value":"421.5 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":"13"},{"tax":["include_tax"],"price":"0","billingrole":"39"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"977de537-f9e7-4840-b809-20cb7e9a3837","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2003 by the Information Processing Society of Japan"}]},"item_3_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"増田, 英孝"},{"creatorName":"塚本, 修一"},{"creatorName":"安富, 大輔"},{"creatorName":"中川, 裕志"}],"nameIdentifiers":[{}]}]},"item_3_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Hidetaka, Masuda","creatorNameLang":"en"},{"creatorName":"Shuichi, Tsukamoto","creatorNameLang":"en"},{"creatorName":"Daisuke, Yasutomi","creatorNameLang":"en"},{"creatorName":"Hiroshi, Nakagawa","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_3_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11464847","subitem_source_identifier_type":"NCID"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_6501","resourcetype":"journal article"}]},"item_3_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"1882-7799","subitem_source_identifier_type":"ISSN"}]},"item_3_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"本研究では，HTMLの表形式データに対して表の項目名と項目データの境界を認識するシステムを実現した．携帯端末などの低解像度小画面上に表を表示する場合，スクロールすると項目名の部分が見えなくなる．また，表示領域が複数のセルに分割されるため，単語途中の折り返しが頻繁に発生し可読性が低下する．そこで，表のセル間の類似度を計算するために言語的性質を利用し，類似度が低い場合には，行間あるいは列間に内容的な切れ目があると認識するアルゴリズムを提案する．このアルゴリズムを実際のWeb上の表データに適用したところ，行方向で82%，列方向で78%の認識率を得た．認識の結果を用いて，携帯端末向けに表を項目名と項目データの組として表示変換し，表示した結果を被験者を用いて評価した．","subitem_description_type":"Other"}]},"item_3_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"We implemented a recognition system to identify the boundary between attribute names and values of a table in HTML. Users can’t see the attributes of the table by using PDA, because of its small and low resolution display when they browse the Web pages. Its low read-ability is caused by the phenomena such that only a small portion of table is shown on the screen at once, and original one line is usually broken up into many lines on display screens. We propose an algorithm to recognize the structure of tables in HTML. Our method utilizes a similarity between rows (or columns) of the table. Precisely speaking, if we find an adjacent pair of rows (or columns) having low similarity, they probably are boundaries between item name row (or column) and item data rows (or columns). We achieved 82% accuracy of recognition of lengthways (and 78% accuracy of recognition of sideways) by applying our algorithm to existing tables on the Web. By using the result, we transform the original table into the attribute-value pairs for a small screen of mobile terminal, and evaluate them by human subjects.","subitem_description_type":"Other"}]},"item_3_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"32","bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌データベース（TOD）"}],"bibliographicPageStart":"23","bibliographicIssueDates":{"bibliographicIssueDate":"2003-09-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"SIG12(TOD19)","bibliographicVolumeNumber":"44"}]},"relation_version_is_last":true,"weko_creator_id":"1"},"id":17583,"links":{}}