{"id":17416,"updated":"2025-01-22T23:20:55.234514+00:00","links":{},"created":"2025-01-18T22:50:25.428618+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00017416","sets":["934:1022:1029:1031"]},"path":["1031"],"owner":"1","recid":"17416","title":["抜粋による複数文書要約を評価するためのコーパスと評価指標"],"pubdate":{"attribute_name":"公開日","attribute_value":"2007-09-15"},"_buckets":{"deposit":"fe4ef45f-49dc-4093-b3f8-6b63cdaaf235"},"_deposit":{"id":"17416","pid":{"type":"depid","value":"17416","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"抜粋による複数文書要約を評価するためのコーパスと評価指標","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"抜粋による複数文書要約を評価するためのコーパスと評価指標"},{"subitem_title":"Corpus and Evaluation Measures for Extractive Multiple Document Summarization","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":"2007-09-15","item_3_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"日本電信電話株式会社NTTコミュニケーション科学基礎研究所"},{"subitem_text_value":"東京工業大学精密工学研究所"},{"subitem_text_value":"追手門学院大学国際教養学部英語コミュニケーション学科"},{"subitem_text_value":"広島市立大学情報科学研究科"},{"subitem_text_value":"マンチェスター大学計算機科学科"},{"subitem_text_value":"日本電信電話株式会社NTTコミュニケーション科学基礎研究所"}]},"item_3_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"NTT Communication Science Laboratories, NTT Corporation","subitem_text_language":"en"},{"subitem_text_value":"Precision and Intelligence Laboratory, Tokyo Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Department of English, Faculty of International Liberal Arts, Otemon Gakuin Univsersity","subitem_text_language":"en"},{"subitem_text_value":"Faculty of Information Science, Hiroshima City Univsersity","subitem_text_language":"en"},{"subitem_text_value":"School of Computer Science, University of Manchester, UK","subitem_text_language":"en"},{"subitem_text_value":"NTT Communication Science Laboratories, NTT 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/17416/files/IPSJ-TOD4814006.pdf"},"date":[{"dateType":"Available","dateValue":"2009-09-15"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-TOD4814006.pdf","filesize":[{"value":"289.5 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":"7b7d05bf-2fca-4945-93c8-d5afeff519b1","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2007 by the Information Processing Society of Japan"}]},"item_3_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"平尾, 努"},{"creatorName":"奥村, 学"},{"creatorName":"福島, 孝博"},{"creatorName":"難波, 英嗣"},{"creatorName":"野畑, 周"},{"creatorName":"磯崎, 秀樹"}],"nameIdentifiers":[{}]}]},"item_3_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Tsutomu, Hirao","creatorNameLang":"en"},{"creatorName":"Manabu, Okumura","creatorNameLang":"en"},{"creatorName":"Takahiro, Fukushima","creatorNameLang":"en"},{"creatorName":"Hidetsugu, Nanba","creatorNameLang":"en"},{"creatorName":"Chikashi, Nobata","creatorNameLang":"en"},{"creatorName":"Hideki, Isozaki","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":"複数文書要約の対象となる文書群には，ある文に対して，意味的に似通った文やまったく同じ文が含まれていることが多い．こうした傾向は，要約のための文書群を複数の情報源から得た場合に特に顕著である．しかし，従来のコーパスには，このようなよく似た文，あるいは同一の文の間に注釈付けが存在しない．これは，抜粋を評価するための指標を定義するうえで致命的な問題となる．本稿では，こうした冗長性を考慮したコーパスへの注釈付けの枠組みを提案し，それに基づき，抜粋の情報量を測る指標である被覆率，抜粋に含まれる重要文の冗長度を測る指標である重要文冗長率を提案する．これらの指標による抜粋の順位付けと被験者による順位付けとの間の順位相関係数は，ともに0.7以上であり，人間の順位付けとの間に高い相関があることが分かった．","subitem_description_type":"Other"}]},"item_3_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"In multiple document summarization, input documents have many similar (or even identical)sentences. However, conventional corpora for multiple document summarization do not include links between similar sentences. This is a critical problem with regard to the definition of evaluation measures for sentence extraction. In this paper, we propose both annotation scheme for corpus and evaluation measures, “coverage” and “redundancy.” “Coverage” measures the content information of the system extract and “redundancy” measures the redundancy of the important sentences contained in system extract. We evaluate “coverage” and “redundancy” by comparing their ranking correlation coefficients with subjective human rankings. The results show that both measure attained enough high correlation coefficients, which were more  than 0.7 correlation coefficients.","subitem_description_type":"Other"}]},"item_3_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"68","bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌データベース（TOD）"}],"bibliographicPageStart":"60","bibliographicIssueDates":{"bibliographicIssueDate":"2007-09-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"SIG14(TOD35)","bibliographicVolumeNumber":"48"}]},"relation_version_is_last":true,"weko_creator_id":"1"}}