{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00048454","sets":["1164:4179:4229:4230"]},"path":["4230"],"owner":"1","recid":"48454","title":["PPM法を用いたかな漢字変換の学習モデル"],"pubdate":{"attribute_name":"公開日","attribute_value":"2001-11-20"},"_buckets":{"deposit":"c85cc55f-b63a-4fc9-896d-67be93b70b2f"},"_deposit":{"id":"48454","pid":{"type":"depid","value":"48454","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"PPM法を用いたかな漢字変換の学習モデル","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"PPM法を用いたかな漢字変換の学習モデル"},{"subitem_title":"A Learning Model for Kana - Kanji Conversion Systems based on PPM Method","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2001-11-20","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情報工学専攻"},{"subitem_text_value":"東京大学大学院情報学環"},{"subitem_text_value":"東京大学大学院情報理工学系研究科数理情報学専攻"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Department of Information Engineering, School of Engineering University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"Interfaculty Initiative in Information Studies, Graduate School of The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"Mathematical Informatics, Graduate School of Information Science and Technology, University of Tokyo","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/48454/files/IPSJ-NL01146002.pdf"},"date":[{"dateType":"Available","dateValue":"2003-11-20"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-NL01146002.pdf","filesize":[{"value":"933.6 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":"23"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"6e254ac1-0321-449d-927d-5dc45f80282c","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2001 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"丸山, 卓久"},{"creatorName":"田中（石井）, 久美子"},{"creatorName":"武市, 正人"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Takahisa, Maruyama","creatorNameLang":"en"},{"creatorName":"Kumiko, Tanaka-Ishii","creatorNameLang":"en"},{"creatorName":"Masato, Takeichi","creatorNameLang":"en"}],"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_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"かな漢字変換では、ユーザが過去に入力した文章中の情報を学習する。学習手法には、1.前に入力した単語を次回先頭候補にする、2.単語の頻度情報を登録する、3.単語の共起情報を登録する、4.単語のn-gram情報を登録する、のような手法が考えられる。1?3までの手法を用いた学習モデルは、既に存在するが、4の単語n-gram情報を用いたモデルはあまり例が無いと思われる。そこで、本研究では、単語n-gram情報を用い、圧縮の分野で用いられている学習手法であるPPM(Prediction by Partial Matching)法を用いたかな漢字変換の学習手モデルを提案し、その性能評価を行った。","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"The efficiency of kana-kanji conversion systems can be improved dynamically by the user's personal corpus accumulated while the user processes text. The learning of such corpus is performed in real time by updating either of the following informations of the candidate preferences: frequency, co-occurrence, or n-gram.  In this paper, we first propose a learning model based on PPM (Prediction by Partial Match), that is one of the learning methods based on n-grams.  Then, we report its efficiency by comparing the result with those of other models.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"14","bibliographic_titles":[{"bibliographic_title":"情報処理学会研究報告自然言語処理（NL）"}],"bibliographicPageStart":"9","bibliographicIssueDates":{"bibliographicIssueDate":"2001-11-20","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"112(2001-NL-146)","bibliographicVolumeNumber":"2001"}]},"relation_version_is_last":true,"weko_creator_id":"1"},"id":48454,"updated":"2025-01-22T08:29:24.190474+00:00","links":{},"created":"2025-01-18T23:13:41.826540+00:00"}