{"updated":"2025-01-22T08:27:56.770347+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00048520","sets":["1164:4179:4229:4233"]},"path":["4233"],"owner":"1","recid":"48520","title":["『日本語話し言葉コーパス』の設計の概要と書き起こし基準について"],"pubdate":{"attribute_name":"公開日","attribute_value":"2001-05-31"},"_buckets":{"deposit":"a7ed48b4-e34f-4d46-be6a-fcbae8bb2edc"},"_deposit":{"id":"48520","pid":{"type":"depid","value":"48520","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"『日本語話し言葉コーパス』の設計の概要と書き起こし基準について","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"『日本語話し言葉コーパス』の設計の概要と書き起こし基準について"},{"subitem_title":"The Corpus of Spontaneous Japanese : Its Design and Transcription Criteria","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2001-05-31","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"国立国語研究所研究開発部門第2領域"},{"subitem_text_value":"国立国語研究所研究開発部門第2領域"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Department of Language Research, National Institute for Japanese Language","subitem_text_language":"en"},{"subitem_text_value":"Department of Language Resrach, National Institute for Japanese Language","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/48520/files/IPSJ-NL01143006.pdf"},"date":[{"dateType":"Available","dateValue":"2003-05-31"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-NL01143006.pdf","filesize":[{"value":"1.6 MB"}],"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":"bac2156d-5683-42de-a7a3-a54fb95ade70","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2001 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"小磯, 花絵"},{"creatorName":"前川, 喜久雄"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Hanae, Koiso","creatorNameLang":"en"},{"creatorName":"Kikuo, Maekawa","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":"国立国語研究所，通信総合研究所，東京工業大学では，科学技術振興調整費開放的融合研究制度の下，自発性の高い話し言葉の情報処理技術の確立を目標に活動を進めている．現在国立国語研究所では，このプロジェクトの一環として，モノローグを対象とした大規模な日本語話し言葉コーパスを作成している．このコーパスには，約700時間の音声(約700万形態素に相当)，書き起こしテキスト，および形態素などの情報が含まれる予定である．本稿では，本コーパスの設計の概要および書き起こし基準の詳細について紹介する．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"A large-scale corpus of spontaneous Japanese speech is being compiled as a joint work of the National Institute for Japanese Language, the Communications  Research Laboratory, and Tokyo Institute of Technology.This corpus is designed to contain about 700 hours of speech (about 7 million morphemes), its transcription, and various tagging information such as POS information. In this paper, the transcription criteria designed specifically for CSJ is described after a brief overview of the general architecture of the corpus.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"48","bibliographic_titles":[{"bibliographic_title":"情報処理学会研究報告自然言語処理（NL）"}],"bibliographicPageStart":"41","bibliographicIssueDates":{"bibliographicIssueDate":"2001-05-31","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"54(2001-NL-143)","bibliographicVolumeNumber":"2001"}]},"relation_version_is_last":true,"weko_creator_id":"1"},"created":"2025-01-18T23:13:44.945888+00:00","id":48520,"links":{}}