{"id":61105,"updated":"2025-01-21T22:13:25.487208+00:00","links":{},"created":"2025-01-18T23:23:22.504626+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00061105","sets":["1164:3500:5611:5612"]},"path":["5612"],"owner":"10","recid":"61105","title":["CRF による係り受け解析の結果を反映させた日本語形態素解析"],"pubdate":{"attribute_name":"公開日","attribute_value":"2009-01-15"},"_buckets":{"deposit":"b002427c-80ad-4cd4-9d57-64fff9029842"},"_deposit":{"id":"61105","pid":{"type":"depid","value":"61105","revision_id":0},"owners":[10],"status":"published","created_by":10},"item_title":"CRF による係り受け解析の結果を反映させた日本語形態素解析","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"CRF による係り受け解析の結果を反映させた日本語形態素解析"},{"subitem_title":"Japanese Morphological Analysis Reflecting Result of Dependency Analysis Using CRFs","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2009-01-15","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"電気通信大学大学院電気通信学研究科情報通信工学専攻"},{"subitem_text_value":"電気通信大学電気通信学部情報通信工学科"},{"subitem_text_value":"電気通信大学電気通信学部情報通信工学科"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Dept. of Informatin and Communication Engineering, Graduate school of Electro-Cmmunications","subitem_text_language":"en"},{"subitem_text_value":"Dept. of Information and Communication Engineering, The Univ. of Electro-Communications","subitem_text_language":"en"},{"subitem_text_value":"Dept. of Information and Communication Engineering, The Univ. of Electro-Communications","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":10,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/61105/files/IPSJ-FI09093005.pdf","label":"IPSJ-FI09093005"},"date":[{"dateType":"Available","dateValue":"2011-02-14"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-FI09093005.pdf","filesize":[{"value":"950.3 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":"0de850cc-fca8-4023-913c-dc21779538aa","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2009 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"岸本, 貴之"},{"creatorName":"高橋, 治久"},{"creatorName":"堀田, 一弘"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Takayuki, Kishimoto","creatorNameLang":"en"},{"creatorName":"Haruhisa, Takahashi","creatorNameLang":"en"},{"creatorName":"Kazuhiro, Hotta","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":"本稿では，日本語形態素解析の精度を，条件付確率場 (CRF) による係り受け解析を用いて，改善する方法を提案する．従来の確率モデルによる形態素解析は，一般的に，1 個または 2 個前までの単語の品詞情報の相関関係によって，最適な候補を絞り込むというやり方を行っていた．しかし，それだけでは解析できない事例が存在しており，もっと広い範囲での単語の相関や，構文関係などを考慮に入れたモデルを考える必要がある．本稿では，形態素解析結果の候補に対し，係り受け解析を行い，その尤度を最大にする形態素解析結果により係り受け解析を選択する方法が，精度改善に有効であることを，従来法との比較実験により示す．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"This paper presents  a method of improving Japanese morphological analysis via Conditional Random Fields  (CRFs) using the dependency analysis. Many existing probabilistic methods select a correct tokens by the correlation analysis between adjoining words and their part-of-speech. However, some instances cannot be correctly analyzed only with the correlation between adjoining words. In order to improve the accuracy, it would be needed to take into account correlation of words in wider range as well as  syntactical features. We show that maximizing the likelihood of the dependency analysis for candidates of correct tokens improves the accuracy by computer experiments.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"32","bibliographic_titles":[{"bibliographic_title":"研究報告情報学基礎（FI）"}],"bibliographicPageStart":"27","bibliographicIssueDates":{"bibliographicIssueDate":"2009-01-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"2(2009-FI-93)","bibliographicVolumeNumber":"2009"}]},"relation_version_is_last":true,"weko_creator_id":"10"}}