{"created":"2021-03-01T06:06:45.816082+00:00","id":3020,"links":{},"metadata":{"_buckets":{"deposit":"9bd9e7d0-fe71-4bd2-a146-a7091baf7994"},"_deposit":{"id":"3020","owners":[],"pid":{"revision_id":0,"type":"depid","value":"3020"},"status":"published"},"_oai":{"id":"oai:niigata-u.repo.nii.ac.jp:00003020","sets":["423:424:425","453:454"]},"item_5_alternative_title_1":{"attribute_name":"その他のタイトル","attribute_value_mlt":[{"subitem_alternative_title":"Classification of Language Knowledge for Meaning Analysis in Machine Translation"}]},"item_5_biblio_info_6":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"1993-08","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"8","bibliographicPageEnd":"1704","bibliographicPageStart":"1692","bibliographicVolumeNumber":"34","bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌"},{"bibliographic_title":"情報処理学会論文誌","bibliographic_titleLang":"en"}]}]},"item_5_description_4":{"attribute_name":"抄録","attribute_value_mlt":[{"subitem_description":"自然言語処理において意味処理を実現するには，意味処理の目的と範囲を明確にすること，また，それに合わせて必要な知識の種類とその分解能を見定めて収集整理することが大切である．本論文では，言語過程説の立場から言語表現の意味を「表現」に結びつけられた「対象」と話者の「認識」の関係と捉え，「意味処理」を言語表現に用いられた言語規範の種類を判別する「意味解析」と，話者と対象世界とを関係づける「意味理解」の二つに分けることを提案した．このうち日本語の「意味解析技術」を実現するために必要な言語知識について，さらに語彙に関する知識と用言を核とした表現構造に関する知識に分け，それぞれ単語意味辞書（名詞語数約37万語），構文意味辞書（文型数約1.3万文型）として収集整理することを試みた．両者は名詞の単語意味属性による記述を介して相互に結合されるため，それら辞書の記述能力は単語意味属性の分解精度で決まる．そこで，単語意味属性の分解精度と用言文型の記述能力との関係を調べると，従来の50〜500種の意味属性分類では記述不能な用言の文型が頻出するのに対して，約3,000種に分類した場合は，一部の用言（補助用言など抽象度の大きいもの）を除いて，訳し分けに必要な文型がほぼ記述できることがわかった．文型記述能力向上の効果は，和語系の用言と専門用語の持つ文型において著しく，記述能力はいずれも数倍以上となった．また，これによって記述された言語知識は機械翻訳において，用言と体言の訳し分けに効果があるだけでなく，複合語解析や文脈処理，訳しやすい日本文への自動書き換えなどの実現に有効であることがわかった．","subitem_description_type":"Abstract"},{"subitem_description":"In the translation process, various types of ambiguities arise, but this is regarded as a lacking the knowledge that is required. To overcome such ambiguity, there is a need to study what knowledge is lacking and to have such knowledge established as the rule or as a dictionary. Separation of meaning processing into meaning analysis and meaning understanding was proposed. And 2 major types of knowledge for meaning analysis are compiled into a form of dictionary for the purpose of solving ambiguity of sentence structure and of the meaning of individual words. The one is a semantic word dictionary (370,000 words) for knowledge related to semantic use of words. The other is a semantic structure dictionary (13,000 sentence patterns) for knowledge related to meanings of expression structures. As a means of describing these knowledge, the use of the meaning of words were compiled into a semantic attribute system with 3,000 attributes. The examinations shows that, in Japanese to English Machine Translation, precision level for some 3,000 types of semantic attributes are necessary for differentiation of translation for verbs. However, this is not sufficient for translation of nouns.","subitem_description_type":"Abstract"}]},"item_5_full_name_3":{"attribute_name":"著者別名","attribute_value_mlt":[{"nameIdentifiers":[{"nameIdentifier":"40439","nameIdentifierScheme":"WEKO"}],"names":[{"name":"Ikehara, Satoru"}]},{"nameIdentifiers":[{"nameIdentifier":"40440","nameIdentifierScheme":"WEKO"}],"names":[{"name":"Miyazaki, Masahiro"}]},{"nameIdentifiers":[{"nameIdentifier":"40441","nameIdentifierScheme":"WEKO"}],"names":[{"name":"Yokoo, Akio"}]}]},"item_5_publisher_7":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会"}]},"item_5_select_19":{"attribute_name":"著者版フラグ","attribute_value_mlt":[{"subitem_select_item":"publisher"}]},"item_5_source_id_11":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00116647","subitem_source_identifier_type":"NCID"}]},"item_5_source_id_9":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"03875806","subitem_source_identifier_type":"ISSN"}]},"item_creator":{"attribute_name":"著者","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"池原, 悟"}],"nameIdentifiers":[{"nameIdentifier":"40436","nameIdentifierScheme":"WEKO"}]},{"creatorNames":[{"creatorName":"宮崎, 正弘"}],"nameIdentifiers":[{"nameIdentifier":"40437","nameIdentifierScheme":"WEKO"}]},{"creatorNames":[{"creatorName":"横尾, 昭男"}],"nameIdentifiers":[{"nameIdentifier":"40438","nameIdentifierScheme":"WEKO"}]}]},"item_files":{"attribute_name":"ファイル情報","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_date","date":[{"dateType":"Available","dateValue":"2019-07-30"}],"displaytype":"detail","filename":"34(8)_1692-1704.pdf","filesize":[{"value":"1.2 MB"}],"format":"application/pdf","licensetype":"license_note","mimetype":"application/pdf","url":{"label":"34(8)_1692-1704.pdf","url":"https://niigata-u.repo.nii.ac.jp/record/3020/files/34(8)_1692-1704.pdf"},"version_id":"1789c1c3-2e76-46cc-9147-1893a79db267"}]},"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":"journal article","resourceuri":"http://purl.org/coar/resource_type/c_6501"}]},"item_title":"日英機械翻訳のための意味解析用の知識とその分解能","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"日英機械翻訳のための意味解析用の知識とその分解能"},{"subitem_title":"日英機械翻訳のための意味解析用の知識とその分解能","subitem_title_language":"en"}]},"item_type_id":"5","owner":"1","path":["454","425"],"pubdate":{"attribute_name":"公開日","attribute_value":"2009-07-17"},"publish_date":"2009-07-17","publish_status":"0","recid":"3020","relation_version_is_last":true,"title":["日英機械翻訳のための意味解析用の知識とその分解能"],"weko_creator_id":"1","weko_shared_id":null},"updated":"2022-12-15T04:12:05.101079+00:00"}