{"id":40314,"updated":"2025-01-22T12:29:27.432064+00:00","links":{},"created":"2025-01-18T23:07:27.410559+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00040314","sets":["1164:3500:3525:3528"]},"path":["3528"],"owner":"1","recid":"40314","title":["対応分析とベイジアンネットワークを用いた文書分類"],"pubdate":{"attribute_name":"公開日","attribute_value":"2003-05-22"},"_buckets":{"deposit":"9b11e930-97e0-4bc4-8ae2-fc682b3023a0"},"_deposit":{"id":"40314","pid":{"type":"depid","value":"40314","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"対応分析とベイジアンネットワークを用いた文書分類","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"対応分析とベイジアンネットワークを用いた文書分類"},{"subitem_title":"Document Categorization using Correspondence Analysis and Bayesian Networks","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2003-05-22","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"松下電器産業株式会社"},{"subitem_text_value":"松下電器産業株式会社"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Matsushita Electric Industrial Co., Ltd.","subitem_text_language":"en"},{"subitem_text_value":"Matsushita Electric Industrial Co., Ltd.","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/40314/files/IPSJ-FI03071020.pdf"},"date":[{"dateType":"Available","dateValue":"2005-05-22"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-FI03071020.pdf","filesize":[{"value":"158.4 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":"39"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"dbc5dc30-97a1-4a56-a387-1803e9ef77a1","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2003 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"福重, 貴雄"},{"creatorName":"菅野祐司"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Yoshio, Fukushige","creatorNameLang":"en"},{"creatorName":"Yuji, Kanno","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10114171","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_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"文書ベクトルのような高次元データをベイジアンネットワークを用いて分類するには、有効素性の選択による次元削減や適切な離散化が必須の課題となる。筆者らは、単語文書空間における対応分析とMDL規準に基づいた離散化をベイジアンネットワークに組み合わせて用いることによって、上記の問題の解決を図った。上記方式を二つのベイジアンネットnaive Bayes型とTAN型と組み合わせて、RWCテキストコーパスを対象として評価実験を行い、Ｆ値で平均8%（最大18%）の分類能力の向上を確認した。","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"In utilizing Bayesian networks as a categorizer, it is often problematic when the data to be categorized are represented in a vector form with very high dimension, like document vectors in a vector space model.  In this paper, we address this issue by reducing the dimensionality with correspondence analysis (CA) and an MDLP-based discretization, and using the resultant data as the input to a Bayesian network leaner. In our empirical validation with the RWC corpus, this method compares favorably with the conventional results on the same data, showing 8% improvement of F-measure on average (max. 18%)","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"174","bibliographic_titles":[{"bibliographic_title":"情報処理学会研究報告情報学基礎（FI）"}],"bibliographicPageStart":"167","bibliographicIssueDates":{"bibliographicIssueDate":"2003-05-22","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"51(2003-FI-071)","bibliographicVolumeNumber":"2003"}]},"relation_version_is_last":true,"weko_creator_id":"1"}}