{"created":"2025-01-19T01:39:24.438561+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00237017","sets":["6504:11678:11684"]},"path":["11684"],"owner":"44499","recid":"237017","title":["近代言語モデルを用いた近代公文書OCRの精度改善手法の提案"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-03-01"},"_buckets":{"deposit":"329c7ec5-69fe-422c-bf25-082aef54bf81"},"_deposit":{"id":"237017","pid":{"type":"depid","value":"237017","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"近代言語モデルを用いた近代公文書OCRの精度改善手法の提案","author_link":["648101","648103","648102","648099","648098","648100"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"近代言語モデルを用いた近代公文書OCRの精度改善手法の提案"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"コンピュータと人間社会","subitem_subject_scheme":"Other"}]},"item_type_id":"22","publish_date":"2024-03-01","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_22_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"中京大"},{"subitem_text_value":"中京大"},{"subitem_text_value":"中京大"},{"subitem_text_value":"中京大"},{"subitem_text_value":"中京大"},{"subitem_text_value":"中京大"}]},"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/237017/files/IPSJ-Z86-7ZK-06.pdf","label":"IPSJ-Z86-7ZK-06.pdf"},"date":[{"dateType":"Available","dateValue":"2024-07-04"}],"format":"application/pdf","filename":"IPSJ-Z86-7ZK-06.pdf","filesize":[{"value":"371.2 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"3080199b-eb1e-4f4e-bd2d-ce90cb5f0a38","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"亀山, 京右"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"山田, 雅之"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"中, 貴俊"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"兼松, 篤子"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"宮崎, 慎也"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"長谷川, 純一"}],"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_22_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00349328","subitem_source_identifier_type":"NCID"}]},"item_22_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"我々の研究チームでは，近代の文書として体系的に保管されている台湾総督府公文書を題材とした近代公文書自動認識システムの構築を進めている．その中で，公文書による学習のみでは近代文書の特徴をうまく捉えることができない点が課題としてあった．そこで本研究では，青空文庫で公開されている近代の文書データを用いて近代言語モデルの事前学習を行い，近代文書の汎用的な特徴を学習することによる近代公文書認識システムの精度向上を目指した手法の提案を行う．","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"820","bibliographic_titles":[{"bibliographic_title":"第86回全国大会講演論文集"}],"bibliographicPageStart":"819","bibliographicIssueDates":{"bibliographicIssueDate":"2024-03-01","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2024"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":237017,"updated":"2025-01-19T09:01:52.628681+00:00","links":{}}