{"updated":"2025-01-21T20:14:45.660410+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00079417","sets":["6164:6165:6630:6631"]},"path":["6631"],"owner":"10","recid":"79417","title":["古文テキスト解析のための文字N グラムの出現確率を利用した単語分割"],"pubdate":{"attribute_name":"公開日","attribute_value":"2011-12-09"},"_buckets":{"deposit":"21ac8892-08b3-48ec-90c8-2425fc2cd802"},"_deposit":{"id":"79417","pid":{"type":"depid","value":"79417","revision_id":0},"owners":[10],"status":"published","created_by":10},"item_title":"古文テキスト解析のための文字N グラムの出現確率を利用した単語分割","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"古文テキスト解析のための文字N グラムの出現確率を利用した単語分割"},{"subitem_title":"Term Extraction for Text Analysis of Japanese Ancient Writings Based on Probability of Character N-grams","subitem_title_language":"en"}]},"item_type_id":"18","publish_date":"2011-12-09","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_18_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"立命館大学 情報理工学部"},{"subitem_text_value":"立命館大学 情報理工学部"},{"subitem_text_value":"立命館大学 情報理工学部"}]},"item_18_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"College of Information Science and Engineering, Ritsumeikan University","subitem_text_language":"en"},{"subitem_text_value":"College of Information Science and Engineering, Ritsumeikan University","subitem_text_language":"en"},{"subitem_text_value":"College of Information Science and Engineering, Ritsumeikan University","subitem_text_language":"en"}]},"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/79417/files/IPSJ-S-CH2011041.pdf"},"date":[{"dateType":"Available","dateValue":"2011-12-09"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-S-CH2011041.pdf","filesize":[{"value":"1.2 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"5"},{"tax":["include_tax"],"price":"0","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"24"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"69ee7704-7798-499b-86cf-f854ce649b42","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2011 by the Information Processing Society of Japan"}]},"item_18_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"吉村, 衛"},{"creatorName":"木村, 文則"},{"creatorName":"前田, 亮"}],"nameIdentifiers":[{}]}]},"item_18_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Mamoru, Yoshimura","creatorNameLang":"en"},{"creatorName":"Fuminori, Kimura","creatorNameLang":"en"},{"creatorName":"Akira, Maeda","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_5794","resourcetype":"conference paper"}]},"item_18_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"現在，日本語の古文に対して汎用的に用いることができる形態素解析器は存在しない．それゆえ日本語の古文に対しては，文章を単語に分割することさえ困難である．単語分割が行えるようになると，古文テキストの解析に役立てることができる．本論文では，日本語の古文の文章を単語に分割する手法を手案する．本手法では，文字Nグラムの単語らしさを評価し，この単語らしさが高い文字Nグラムを単語として文の単語への分割を行う．今回は，「源氏物語」に対し本手法の評価実験を行い，評価・考察を行う．","subitem_description_type":"Other"}]},"item_18_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Currently, there are few available tools to separate ancient Japanese sentences into terms. Therefore, it is difficult to extract archaic Japanese terms from Japanese ancient writings. In this paper, we propose a method of term extraction for Japanese ancient writings. We calculate the likelihood of character n-grams to be a term, and extract character n-grams with higher likelihood as archaic Japanese terms. We conducted experiments of term separation using the term likelihood by the proposed method.","subitem_description_type":"Other"}]},"item_18_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"268","bibliographic_titles":[{"bibliographic_title":"じんもんこん2011論文集"}],"bibliographicPageStart":"261","bibliographicIssueDates":{"bibliographicIssueDate":"2011-12-03","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"8","bibliographicVolumeNumber":"2011"}]},"relation_version_is_last":true,"weko_creator_id":"10"},"created":"2025-01-18T23:34:09.911825+00:00","id":79417,"links":{}}