{"updated":"2025-01-21T22:14:16.153966+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00061960","sets":["1164:4179:5613:5676"]},"path":["5676"],"owner":"10","recid":"61960","title":["ベイズ階層言語モデルによる教師なし形態素解析"],"pubdate":{"attribute_name":"公開日","attribute_value":"2009-03-18"},"_buckets":{"deposit":"0b6753ce-92e7-4fb8-bc20-d32d4ebc8ea5"},"_deposit":{"id":"61960","pid":{"type":"depid","value":"61960","revision_id":0},"owners":[10],"status":"published","created_by":10},"item_title":"ベイズ階層言語モデルによる教師なし形態素解析","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"ベイズ階層言語モデルによる教師なし形態素解析"},{"subitem_title":"Bayesian Unsupervised Word Segmentation with Hierarchical Language Modeling","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2009-03-18","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"NTT コミュニケーション科学基礎研究所"},{"subitem_text_value":"NTT コミュニケーション科学基礎研究所"},{"subitem_text_value":"NTT コミュニケーション科学基礎研究所"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"NTT Communication Science Laboratories","subitem_text_language":"en"},{"subitem_text_value":"NTT Communication Science Laboratories","subitem_text_language":"en"},{"subitem_text_value":"NTT Communication Science Laboratories","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/61960/files/IPSJ-NL09190008.pdf","label":"IPSJ-NL09190008"},"date":[{"dateType":"Available","dateValue":"2011-03-18"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-NL09190008.pdf","filesize":[{"value":"163.4 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"5"},{"tax":["include_tax"],"price":"0","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"23"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"f2e1b042-7166-47fa-a136-e2e5878c35e1","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":"持橋, 大地"},{"creatorName":"山田, 武士"},{"creatorName":"上田, 修功"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Daichi, Mochihashi","creatorNameLang":"en"},{"creatorName":"Takeshi, Yamada","creatorNameLang":"en"},{"creatorName":"Naonori, Ueda","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":"本論文では，教師データや辞書を全く必要とせず，あらゆる言語に適用できる教師なし形態素解析器および言語モデルを提案する。観測された文字列を，文字 n グラム ‐ 単語 n グラムをノンパラメトリックベイズ法の枠組で統合した確率モデルからの出力とみなし，MCMC 法と動的計画法を用いて，繰り返し 「単語」 を推定する。提案法は，あらゆる言語の生文字列から直接，高精度で未知語のない n グラム言語モデルを構築する方法ともみなすことができる。","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"This paper proposes a novel unsupervised morphological analyzer of arbitrary language that does not need any supervised segmentation nor dictionary. Assuming a string as the output from a nonparametric Bayesian hierarchical n-gram language model of words and characters, \"words\" are iteratively estimated during inference by a combination of MCMC and an efficient dynamic programming. This model can also be considered as a method to learn an accurate n-gram language model directly from characters without any \"word\" information.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"49","bibliographic_titles":[{"bibliographic_title":"研究報告自然言語処理（NL）"}],"bibliographicPageStart":"49","bibliographicIssueDates":{"bibliographicIssueDate":"2009-03-18","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"36(2009-NL-190)","bibliographicVolumeNumber":"2009"}]},"relation_version_is_last":true,"weko_creator_id":"10"},"created":"2025-01-18T23:24:00.719191+00:00","id":61960,"links":{}}