{"updated":"2025-01-20T08:46:19.574414+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00169985","sets":["1164:4179:8454:8862"]},"path":["8862"],"owner":"11","recid":"169985","title":["業績変動を考慮した決算短信からの重要文抽出"],"pubdate":{"attribute_name":"公開日","attribute_value":"2016-07-22"},"_buckets":{"deposit":"ec8c2060-87d6-40c0-8369-b5d8f93fc4d6"},"_deposit":{"id":"169985","pid":{"type":"depid","value":"169985","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"業績変動を考慮した決算短信からの重要文抽出","author_link":["342231","342234","342235","342233","342232","342236","342230"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"業績変動を考慮した決算短信からの重要文抽出"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"言語処理応用","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2016-07-22","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東京大学大学院工学系研究科技術経営戦略学専攻"},{"subitem_text_value":"東京大学大学院新領域創成科学研究科人間環境学専攻"},{"subitem_text_value":"東京大学医学部医学科"},{"subitem_text_value":"東京大学大学院医学系研究科生体物理医学専攻"},{"subitem_text_value":"東京大学大学院工学系研究科技術経営戦略学専攻"},{"subitem_text_value":"東京大学大学院工学系研究科技術経営戦略学専攻"},{"subitem_text_value":"東京大学大学院工学系研究科技術経営戦略学専攻"}]},"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/169985/files/IPSJ-NL16227006.pdf","label":"IPSJ-NL16227006.pdf"},"date":[{"dateType":"Available","dateValue":"2018-07-22"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-NL16227006.pdf","filesize":[{"value":"3.5 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"23"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"c3274886-8534-4f63-b98e-84acb407faaf","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2016 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"磯沼, 大"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"藤野, 暢"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"浮田, 純平"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"村上, 遥"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"浅谷, 公威"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"森, 純一郎"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"坂田, 一郎"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10115061","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_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-8779","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"近年,記事生成などへの自動要約技術の適用が注目されている.本研究で対象とする決算記事は,どの事業や事象が企業全体の業績変動に大きな影響を及ぼすかといった記者の知見をもとに作成される.したがって自動要約においてはこうした記者の知見を抽出し,情報抽出・要約に適用する技術が必要である.本研究では過去の決算短信と決算記事から業績変動と短信文の掲載パターンを学習し,記事に掲載されるべき文を決算短信から抽出する手法を提案する.提案手法は 2 パートに分かれ,第 1 パートでは各事業セグメントの業績変動と,記事掲載パターンを学習することにより,各事業セグメントの重要度を判定する.第 2 パートでは,判定した各事業セグメントの重要度と極性判定を用いることで各文の重要度を評価し,抽出を行う.極性判定では,決算記事中の各表現に関する極性を自動で獲得し,非負値行列因子分解 (NMF) による極性値推定を行うことで,決算記事に未出現の表現も含めた多様な表現に関する極性の獲得を可能にした.提案手法を適用して決算短信から抽出された文と実際の決算記事を比較した実験において,重要文抽出精度の評価を行い,事業セグメントの重要度判定と NMF による極性推定の有用性を確認した.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告自然言語処理(NL)"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2016-07-22","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"6","bibliographicVolumeNumber":"2016-NL-227"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"created":"2025-01-19T00:40:42.222282+00:00","id":169985,"links":{}}