{"updated":"2025-01-20T02:48:02.671018+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00185827","sets":["581:9322:9324"]},"path":["9324"],"owner":"11","recid":"185827","title":["『国語研日本語ウェブコーパス』とその検索系『梵天』"],"pubdate":{"attribute_name":"公開日","attribute_value":"2018-02-15"},"_buckets":{"deposit":"52bfd209-e2cb-4ed4-b637-8bfa4863fa12"},"_deposit":{"id":"185827","pid":{"type":"depid","value":"185827","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"『国語研日本語ウェブコーパス』とその検索系『梵天』","author_link":["414448","414450","414451","414446","414452","414445","414449","414447"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"『国語研日本語ウェブコーパス』とその検索系『梵天』"},{"subitem_title":"‘NINJAL Web Japanese Corpus’ and Its Search System ‘BonTen’","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"[特集：人文科学とコンピュータ] コーパス，ウェブアーカイブ，検索系，アノテーション，ユーザインタフェース","subitem_subject_scheme":"Other"}]},"item_type_id":"2","publish_date":"2018-02-15","item_2_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"人間文化研究機構国立国語研究所"},{"subitem_text_value":"株式会社レトリバ"},{"subitem_text_value":"株式会社万葉"},{"subitem_text_value":"人間文化研究機構国立国語研究所"}]},"item_2_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"NINJAL","subitem_text_language":"en"},{"subitem_text_value":"Retrieva, Inc.","subitem_text_language":"en"},{"subitem_text_value":"Everyleaf Corporation","subitem_text_language":"en"},{"subitem_text_value":"NINJAL","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"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/185827/files/IPSJ-JNL5902006.pdf","label":"IPSJ-JNL5902006.pdf"},"date":[{"dateType":"Available","dateValue":"2020-02-15"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-JNL5902006.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":"8"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"cea76e45-d5a2-437d-8484-2a54b95cc5e5","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2018 by the Information Processing Society of Japan"}]},"item_2_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"浅原, 正幸"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"河原, 一哉"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"大場, 寧子"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"前川, 喜久雄"}],"nameIdentifiers":[{}]}]},"item_2_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Masayuki, Asahara","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Kazuya, Kawahara","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yasuko, Ohba","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Kikuo, Maekawa","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_2_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00116647","subitem_source_identifier_type":"NCID"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_6501","resourcetype":"journal article"}]},"item_2_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"1882-7764","subitem_source_identifier_type":"ISSN"}]},"item_2_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"国立国語研究所は言語研究に資する258億語規模のウェブコーパス『国語研ウェブコーパス』を構築した．コーパスの構築は，ページ収集・言語解析・保存・検索系の構築の4種類の部分工程からなる．本稿では，『国語研ウェブコーパス』を概説するとともに，その検索系である『梵天』の機能について紹介する．この検索系は100億語規模のテキストコーパスを文字列だけでなく，形態素列・係り受け部分木に基づく問合せが可能である．","subitem_description_type":"Other"}]},"item_2_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"The National Institute for Japanese Language and Linguistics, Japan (NINJAL) compiled a web corpus for linguistic research comprising 25 billion words. The project is divided into four parts: page collection, linguistic analysis, development of the corpus concordance system, and preservation. This article presents a corpus concordance system named ‘BonTen’, which enables a ten-billion-scaled corpus to be queried by string, a sequence of morphological information or a subtree of the syntactic dependency structure. ","subitem_description_type":"Other"}]},"item_2_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"305","bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌"}],"bibliographicPageStart":"299","bibliographicIssueDates":{"bibliographicIssueDate":"2018-02-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"2","bibliographicVolumeNumber":"59"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"created":"2025-01-19T00:52:53.972601+00:00","id":185827,"links":{}}