{"links":{},"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00107388","sets":["6164:6165:6630:7761"]},"path":["7761"],"owner":"11","recid":"107388","title":["活字資料のコーパス化における外字チェックと処理"],"pubdate":{"attribute_name":"公開日","attribute_value":"2014-12-06"},"_buckets":{"deposit":"6371d7ae-a84a-4cd7-9412-e2a6c48a737e"},"_deposit":{"id":"107388","pid":{"type":"depid","value":"107388","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"活字資料のコーパス化における外字チェックと処理","author_link":["17038","17037","17039","17036"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"活字資料のコーパス化における外字チェックと処理"},{"subitem_title":"Extracting and processing external characters upon constructing corpora of printed documents","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"文字情報;;コーパス ","subitem_subject_scheme":"Other"}]},"item_type_id":"18","publish_date":"2014-12-06","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_18_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"昭和女子大学"},{"subitem_text_value":"東京農工大学"}]},"item_18_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Showa Wemen's University","subitem_text_language":"en"},{"subitem_text_value":"Tokyo University of Agriculture and Technology","subitem_text_language":"en"}]},"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/107388/files/IPSJ-S-CH2014011.pdf"},"date":[{"dateType":"Available","dateValue":"2015-12-06"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-S-CH2014011.pdf","filesize":[{"value":"502.0 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"630","billingrole":"5"},{"tax":["include_tax"],"price":"315","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"24"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"3f668b2e-09ca-42ce-8751-ef93b6212265","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2014 by the Information Processing Society of Japan"}]},"item_18_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"須永, 哲矢"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"堤, 智昭"}],"nameIdentifiers":[{}]}]},"item_18_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Tetsuya, Sunaga","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Tomoaki, Tsutsumi","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_5794","resourcetype":"conference paper"}]},"item_18_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"歴史的作品の活字資料からコーパスを作るときの文字処理の方法を定めた．活字資料の電子化にあたっては，外字処理・字体包摂の２つが中心課題となるが，両者をまとめて処理できるツールを利用し，作業方式を確立することにより，もとになるテキストの特性によらず，統一的な処理を可能にした．本作業のために開発したツールと本稿で提案した一連の作業手順は，コーパス構築という作業のみならず，活字研究にも適用可能である．研究利用の例として，小学館新編日本古典文学全集 『日本霊異記』等の漢字活字を調査し，JIS X0213 や UniCode でどの程度再現できるかを明らかにした．","subitem_description_type":"Other"}]},"item_18_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"The paper proposes a new processing procedure of external characters included in printed historical texts, which is essential to constructing an electronic corpus of historical documents. Digitization of printed historical documents so far has two major problems to be dealt with: representation of external characters and establishment of unification standard. We present a solution to the problems, introducing a new software tool which handles the two problems altogether. By applying the tool, the characters can be processed uniformly, regardless of the document variation. Furthermore, the processing tool and a series of procedures or our proposal can also be applied to character research. In the paper, we present a small sample investigation on the external characters of SNKBZ, Shogakukan, revealing what percentage of the total printing types JIS X0213 and Unicode respectively can represent.","subitem_description_type":"Other"}]},"item_18_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"74","bibliographic_titles":[{"bibliographic_title":"じんもんこん2014論文集"}],"bibliographicPageStart":"69","bibliographicIssueDates":{"bibliographicIssueDate":"2014-12-06","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"3","bibliographicVolumeNumber":"2014"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"created":"2025-01-18T23:50:34.766642+00:00","updated":"2025-01-21T09:02:18.212296+00:00","id":107388}