{"updated":"2025-01-22T03:01:10.060235+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00060731","sets":["934:1022:5596:5597"]},"path":["5597"],"owner":"10","recid":"60731","title":["学術文献の潜在トピックに着目したタンパク質相互関係に関する知識の抽出"],"pubdate":{"attribute_name":"公開日","attribute_value":"2009-06-29"},"_buckets":{"deposit":"4cf61caf-6c22-4215-aa56-921f13cad93d"},"_deposit":{"id":"60731","pid":{"type":"depid","value":"60731","revision_id":0},"owners":[10],"status":"published","created_by":10},"item_title":"学術文献の潜在トピックに着目したタンパク質相互関係に関する知識の抽出","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"学術文献の潜在トピックに着目したタンパク質相互関係に関する知識の抽出"},{"subitem_title":"Extracting Knowledge on Protein-Protein Relationships Using Latent Topics of Literature","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":"2009-06-29","item_3_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"神戸大学大学院工学研究科情報知能学専攻"},{"subitem_text_value":"神戸大学大学院工学研究科情報知能学専攻"}]},"item_3_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Engineering, Kobe University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Engineering, Kobe University","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/60731/files/IPSJ-TOD0202008.pdf"},"date":[{"dateType":"Available","dateValue":"2011-06-29"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-TOD0202008.pdf","filesize":[{"value":"497.1 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":"6e62ee9c-d375-455a-a440-f5376d5c50e9","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2009 by the Information Processing Society of Japan"}]},"item_3_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"麻生, 竜矢"},{"creatorName":"江口, 浩二"}],"nameIdentifiers":[{}]}]},"item_3_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Tatsuya, Aso","creatorNameLang":"en"},{"creatorName":"Koji, Eguchi","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":"近年，医学生物学分野をはじめとする様々な領域において，電子化された大量の文献に蓄積された知見を組織化し，潜在的な仮説を生成する技術への高度化への要求が高まっている．この目的の下で，生物学的知識，特にタンパク質間相互関係に関する知識の抽出のため，確率的トピックモデルを適用する．潜在的ディリクレ配分法 （LDA） による確率的トピックモデルは，上述のようなタスクに関する有効性という観点からはこれまで検討されてこなかった．本論文では，LDA の推定手法として Collapsed 変分ベイズ法を適用し，テストセットの対数尤度，分類精度ならびにランキング精度の観点から評価し，Collapsed Gibbs Sampling 法による LDA と確率的潜在意味インデクシング法 （pLSI） との比較を行う．現実的なタスクを想定した分類精度とランキング精度による評価では，Collapsed 変分ベイズ法に基づく LDA によって良好な結果が得られることを示す．","subitem_description_type":"Other"}]},"item_3_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Recently, technologies for organizing knowledge accumulated in a growing number of digitized documents and for generating potential hypotheses have been highly requested, such as in biomedical fields. For these objectives, we investigate applying statistical topic models to predict relationships between biological entities, especially protein mentions. A statistical topic model, Latent Dirichlet Allocation (LDA) has not been investigated for such a task. In this paper, we apply the state-of-the-art Collapsed Variational Bayesian inference to estimating the LDA model, and compared it with the LDA model estimated via Collapsed Gibbs Sampling and probabilistic Latent Semantic Indexing (pLSI) from the viewpoints of test-set log-likelihood, classification accuracy and ranking effectiveness. We demonstrate through experiments that the Collapsed Variational LDA gives better results than the others, especially in terms of classification accuracy and ranking effectiveness.","subitem_description_type":"Other"}]},"item_3_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"95","bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌データベース（TOD）"}],"bibliographicPageStart":"86","bibliographicIssueDates":{"bibliographicIssueDate":"2009-06-29","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"2","bibliographicVolumeNumber":"2"}]},"relation_version_is_last":true,"weko_creator_id":"10"},"created":"2025-01-18T23:23:05.968070+00:00","id":60731,"links":{}}