{"created":"2023-05-15T14:23:55.247341+00:00","id":2201,"links":{},"metadata":{"_buckets":{"deposit":"99999922-dad7-4d1d-ac5c-750f368cc42e"},"_deposit":{"created_by":3,"id":"2201","owners":[3],"pid":{"revision_id":0,"type":"depid","value":"2201"},"status":"published"},"_oai":{"id":"oai:repository.ninjal.ac.jp:00002201","sets":["289:312"]},"author_link":["7406","7414","7416","7405","7412","7407","7417","7404","7409","7411","7415","7410","7408","7413"],"item_10002_biblio_info_40":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"2007-10-25","bibliographicIssueDateType":"Issued"},"bibliographicPageEnd":"123","bibliographicPageStart":"101","bibliographicVolumeNumber":"22","bibliographic_titles":[{"bibliographic_title":"日本語科学"},{"bibliographic_title":"Japanese Linguistics","bibliographic_titleLang":"en"}]}]},"item_10002_description_34":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_description":"千葉大学","subitem_description_type":"Other"},{"subitem_description":"国立国語研究所","subitem_description_type":"Other"},{"subitem_description":"国立国語研究所","subitem_description_type":"Other"},{"subitem_description":"京都高度技術研究所","subitem_description_type":"Other"},{"subitem_description":"東京大学","subitem_description_type":"Other"},{"subitem_description":"情報通信研究機構","subitem_description_type":"Other"},{"subitem_description":"国立国語研究所","subitem_description_type":"Other"}]},"item_10002_description_35":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_description":"Chiba University","subitem_description_type":"Other"},{"subitem_description":"The National Institute for Japanese Language","subitem_description_type":"Other"},{"subitem_description":"The National Institute for Japanese Language","subitem_description_type":"Other"},{"subitem_description":"ASTEM","subitem_description_type":"Other"},{"subitem_description":"The University of Tokyo","subitem_description_type":"Other"},{"subitem_description":"National Institute of Information and Communications Technology","subitem_description_type":"Other"},{"subitem_description":"The National Institute for Japanese Language","subitem_description_type":"Other"}]},"item_10002_description_36":{"attribute_name":"抄録","attribute_value_mlt":[{"subitem_description":"コーパス日本語学への応用を指向した形態素解析用電子化辞書UniDicを開発した。大規模コーパスに対する形態論情報付与作業には,計算機を用いた形態素解析システムの利用が不可欠であるが,既存の形態素解析システム用辞書には,コーパス日本語学への応用を考える上でさまざまな不都合がある。1つは,単位の認定がある場合には長く,ある場合には短いといった不揃いがあることであり,もう1つは,異表記や異形態に対して同一の見出しが与えられないということである。言語研究で重要な要件となる,このような単位の斉一性や見出しの同一性への対処といったことを中心に,本電子化辞書の設計方針とそれを実装した辞書データベースシステムについて述べる。さらに,この設計の有用性を示すため,表記や語形の変異に関するコーパス分析の事例を紹介する。","subitem_description_type":"Abstract"}]},"item_10002_description_37":{"attribute_name":"抄録(英)","attribute_value_mlt":[{"subitem_description":"In this paper, we describe the design and the implementation of an electronic dictionary for morphological analysis, UniDic, which aims particularly at application to Japanese corpus linguistics. It has been indispensable for the development of a large-scale corpus to utilize an automatic morphological analyzer on computer. The existing dictionaries for morphological analyzers, however, reveal lots of problems when used in corpus linguistics, such as unevenness in defining a unit and failure in handling allomorphs and orthographic variants. Our dictionary, in contrast, deals with the uniformity of units and the identity of indexes, which are important requirements for linguistic analysis of corpora. We adopt multi-level definition of word units, consisting of short-, middle-, and long-unit words, and structured representation of indexes, composed of lemma, word form, orthography, and pronunciation. We develop a database system that straight-forwardly implements this design of the dictionary and a friendly user-interface for dictionary builders to be capable of searching and registering entries with grasping the complex structure of the indexes. We also show how this structured representation benefits us in analyzing morphologically annotated corpora, presenting case studies that investigate the variation of word form in spoken language corpus and the variation of orthography in written language corpus.","subitem_description_type":"Other"}]},"item_10002_description_51":{"attribute_name":"フォーマット","attribute_value_mlt":[{"subitem_description":"application/pdf","subitem_description_type":"Other"}]},"item_10002_identifier_registration":{"attribute_name":"ID登録","attribute_value_mlt":[{"subitem_identifier_reg_text":"10.15084/00002185","subitem_identifier_reg_type":"JaLC"}]},"item_10002_publisher_39":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"国書刊行会"}]},"item_10002_version_type_52":{"attribute_name":"著者版フラグ","attribute_value_mlt":[{"subitem_version_resource":"http://purl.org/coar/version/c_970fb48d4fbd8a85","subitem_version_type":"VoR"}]},"item_creator":{"attribute_name":"著者","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"伝, 康晴"},{"creatorName":"デン, ヤスハル","creatorNameLang":"ja-Kana"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"小木曽, 智信"},{"creatorName":"オギソ, トシノブ","creatorNameLang":"ja-Kana"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"小椋, 秀樹"},{"creatorName":"オグラ, ヒデキ","creatorNameLang":"ja-Kana"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"山田, 篤"},{"creatorName":"ヤマダ, アツシ","creatorNameLang":"ja-Kana"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"峯松, 信明"},{"creatorName":"ミネマツ, ノブアキ","creatorNameLang":"ja-Kana"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"内元, 清貴"},{"creatorName":"ウチモト, キヨタカ","creatorNameLang":"ja-Kana"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"小磯, 花絵"},{"creatorName":"コイソ, ハナエ","creatorNameLang":"ja-Kana"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"DEN, Yasuharu","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"OGISO, Toshinobu","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"OGURA, Hideki","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"YAMADA, Atsushi","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"MINEMATSU, Nobuaki","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"UCHIMOTO, Kiyotaka","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"KOISO, Hanae","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_files":{"attribute_name":"ファイル情報","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_date","date":[{"dateType":"Available","dateValue":"2019-03-25"}],"displaytype":"detail","filename":"kk_ngkgk_022_07.pdf","filesize":[{"value":"1.8 MB"}],"format":"application/pdf","licensetype":"license_note","mimetype":"application/pdf","url":{"label":"kk_ngkgk_022_07.pdf","url":"https://repository.ninjal.ac.jp/record/2201/files/kk_ngkgk_022_07.pdf"},"version_id":"aa22f10e-cd41-4fb1-9ce2-fb203f26f9a6"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"電子化辞書","subitem_subject_scheme":"Other"},{"subitem_subject":"形態素解析","subitem_subject_scheme":"Other"},{"subitem_subject":"データベース","subitem_subject_scheme":"Other"},{"subitem_subject":"単位の斉一性","subitem_subject_scheme":"Other"},{"subitem_subject":"見出しの同一性","subitem_subject_scheme":"Other"},{"subitem_subject":"electronic dictionary","subitem_subject_language":"en","subitem_subject_scheme":"Other"},{"subitem_subject":"morphological analysis","subitem_subject_language":"en","subitem_subject_scheme":"Other"},{"subitem_subject":"database system","subitem_subject_language":"en","subitem_subject_scheme":"Other"},{"subitem_subject":"uniformity of units","subitem_subject_language":"en","subitem_subject_scheme":"Other"},{"subitem_subject":"identity of indexes","subitem_subject_language":"en","subitem_subject_scheme":"Other"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourcetype":"departmental bulletin paper","resourceuri":"http://purl.org/coar/resource_type/c_6501"}]},"item_title":"コーパス日本語学のための言語資源 : 形態素解析用電子化辞書の開発とその応用","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"コーパス日本語学のための言語資源 : 形態素解析用電子化辞書の開発とその応用"},{"subitem_title":"The development of an electronic dictionary for morphological analysis and its application to Japanese corpus linguistics","subitem_title_language":"en"}]},"item_type_id":"10002","owner":"3","path":["312"],"pubdate":{"attribute_name":"公開日","attribute_value":"2019-03-25"},"publish_date":"2019-03-25","publish_status":"0","recid":"2201","relation_version_is_last":true,"title":["コーパス日本語学のための言語資源 : 形態素解析用電子化辞書の開発とその応用"],"weko_creator_id":"3","weko_shared_id":-1},"updated":"2023-05-15T15:59:36.863535+00:00"}