{"updated":"2025-01-20T00:40:04.844489+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00191438","sets":["1164:4179:9477:9562"]},"path":["9562"],"owner":"11","recid":"191438","title":["A proposal for a unified corpus of the Ainu language"],"pubdate":{"attribute_name":"公開日","attribute_value":"2018-09-18"},"_buckets":{"deposit":"cd84c50f-7094-41cf-a367-661402a4bf3e"},"_deposit":{"id":"191438","pid":{"type":"depid","value":"191438","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"A proposal for a unified corpus of the Ainu language","author_link":["441643","441642","441641","441644","441640","441645"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"A proposal for a unified corpus of the Ainu language"},{"subitem_title":"A proposal for a unified corpus of the Ainu language","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"言語処理応用","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2018-09-18","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"Kitami Institute of Technology"},{"subitem_text_value":"Kitami Institute of Technology"},{"subitem_text_value":"Kitami Institute of Technology"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Kitami Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Kitami Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Kitami Institute of Technology","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"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/191438/files/IPSJ-NL18237002.pdf","label":"IPSJ-NL18237002.pdf"},"date":[{"dateType":"Available","dateValue":"2020-09-18"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-NL18237002.pdf","filesize":[{"value":"823.5 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":"6e332462-9d24-4c0d-976d-d8c76cca5b76","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2018 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Karol, Nowakowski"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Michal, Ptaszynski"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Fumito, Masui"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Karol, Nowakowski","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Michal, Ptaszynski","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Fumito, Masui","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_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-8779","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"Ainu is an endangered language of the Ainu people, native inhabitants of northern Japan. It has been the subject of many studies, but most scholars work on small amounts of language data. We propose a corpus of Ainu covering a wide range of documents, in a consistent structure that will enable large-scale linguistic analysis and support the development of NLP technologies for Ainu, contributing to the process of its revitalization. The corpus contains parallel text in Ainu and Japanese. Its subset includes POS annotations produced by Ainu language experts. For the remaining parts, annotations will be generated automatically. At present, resources collected for the corpus comprise 1.86M characters (410K tokens) of text in Ainu. Their utility for NLP applications has been verified by applying them in a tokenization system, which achieved average F-score above 95%.","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Ainu is an endangered language of the Ainu people, native inhabitants of northern Japan. It has been the subject of many studies, but most scholars work on small amounts of language data. We propose a corpus of Ainu covering a wide range of documents, in a consistent structure that will enable large-scale linguistic analysis and support the development of NLP technologies for Ainu, contributing to the process of its revitalization. The corpus contains parallel text in Ainu and Japanese. Its subset includes POS annotations produced by Ainu language experts. For the remaining parts, annotations will be generated automatically. At present, resources collected for the corpus comprise 1.86M characters (410K tokens) of text in Ainu. Their utility for NLP applications has been verified by applying them in a tokenization system, which achieved average F-score above 95%.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告自然言語処理（NL）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2018-09-18","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"2","bibliographicVolumeNumber":"2018-NL-237"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"created":"2025-01-19T00:57:19.536645+00:00","id":191438,"links":{}}