{"id":47845,"created":"2025-01-18T23:13:13.648832+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00047845","sets":["1164:4179:4187:4192"]},"path":["4192"],"owner":"1","recid":"47845","title":["シソーラスを用いた複層クラス n-gram モデル"],"pubdate":{"attribute_name":"公開日","attribute_value":"2007-03-28"},"_buckets":{"deposit":"f3a41172-7000-4b76-b744-6f3dbeb18cc5"},"_deposit":{"id":"47845","pid":{"type":"depid","value":"47845","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"シソーラスを用いた複層クラス n-gram モデル","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"シソーラスを用いた複層クラス n-gram モデル"},{"subitem_title":"Multi-layer Class N-gram Model that Uses Noun Thesaurus","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2007-03-28","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"鳥取環境大学 環境情報学部 情報システム学科"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Department of Information Systems, Tottori University of Environmental Studies","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/47845/files/IPSJ-NL07178006.pdf"},"date":[{"dateType":"Available","dateValue":"2009-03-28"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-NL07178006.pdf","filesize":[{"value":"551.7 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":"5cdc11fb-5573-4931-8930-66ef45d75647","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2007 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"市丸, 夏樹"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Natsuki, ICHIMARU","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":"本稿では、携帯電話等における子音入力方式の正解率向上と打鍵数の削減のため、n-gram に名詞シソーラスを組み合わせた強力な優先付け機構を提案する。提案手法では、単語 n-gram の単語間の条件付き連接確率が、シソーラス中の様々な抽象度の先行クラス間の連接を前提条件として計算されるものと考える。一般的には、より具体的なクラス列に後接し、かつ生起頻度が高い単語候補が優先される。その結果、文節中に派生語や複合語が含まれる場合にも正しい漢字候補を自動的に選び出すことができるようになるものと考えられる。派生語変換の実験では、マルチタップ入力と品詞 bi-gram の場合と比較して、入力と変換を合わせた総合的な打鍵数を約 56％削減できることを示した。","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"In this paper, we present a strong disambiguation method that combines class n-gram and a noun thesaurus, to improve accuracy and keystroke savings of consonant-kanji conversion method that is used on mobile phone. We presume that the preceding class sequence of a word can reside on any layers in a thesaurus. In general, a high frequency word that succeeds a specific class sequence has high priority. It is supposed that our method can automatically choose correct kanji candidates, even from a phrase that contains derivative word or compound word. As an experimental result of derivative conversion, we confirmed that the keystroke savings rate was about 56％.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"40","bibliographic_titles":[{"bibliographic_title":"情報処理学会研究報告自然言語処理（NL）"}],"bibliographicPageStart":"35","bibliographicIssueDates":{"bibliographicIssueDate":"2007-03-28","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"35(2007-NL-178)","bibliographicVolumeNumber":"2007"}]},"relation_version_is_last":true,"weko_creator_id":"1"},"updated":"2025-01-22T08:47:56.130900+00:00","links":{}}