{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00234918","sets":["1164:2735:11468:11669"]},"path":["11669"],"owner":"44499","recid":"234918","title":["自己組織化によるWord Embedding手法の提案"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-06-13"},"_buckets":{"deposit":"3677595d-9866-418e-b08b-1299bcccf8f2"},"_deposit":{"id":"234918","pid":{"type":"depid","value":"234918","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"自己組織化によるWord Embedding手法の提案","author_link":["641108","641109","641107","641106"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"自己組織化によるWord Embedding手法の提案"},{"subitem_title":"Self-Organizing Method for Word Embedding","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"ニューロコンピューティング1","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2024-06-13","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"日本大学大学院生産工学研究科"},{"subitem_text_value":"日本大学生産工学部"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Industrial Engineering, Nihon University","subitem_text_language":"en"},{"subitem_text_value":"College of Industrial Technology, Nihon University","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/234918/files/IPSJ-MPS24148031.pdf","label":"IPSJ-MPS24148031.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-MPS24148031.pdf","filesize":[{"value":"1.5 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"17"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"180b33c0-6131-4c2b-8ea2-550aa6051c6e","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Institute of Electronics, Information and Communication Engineers This SIG report is only available to those in membership of the SIG."}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"張, 宏毅"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"山内, ゆかり"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Hongyi, Zhang","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yukari, Yamauchi","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10505667","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":"2188-8833","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"自然言語処理において，単語の特徴量をベクトル化する Word Embedding が必要である．Mikolov らはニューラルネットワークを用いて，大量のテキストデータから単語間の関係を学習する Word2vec を提案した． Word2Vec は高速で効率的な学習が特徴だが，小規模なデータセットで Embedding すると過学習の恐れがある．本研究では自己組織的手法による Word Embedding を提案し，自己組織化の特性により小規模なデータセットで局所的な知識の構築に有効な手法の構築を目指す．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"In natural language processing, word embedding is essential for vectorizing word features. Mikolov et al. proposed Word2vec, which uses neural networks to learn relationships between words from large text corpora. Word2vec is known for its fast and efficient learning, but there is a risk of overfitting when embedding with small datasets. In this study, we propose a word embedding method based on self-organizing techniques. By leveraging the properties of self-organization, we aim to develop an effective method for constructing local knowledge in small datasets.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告数理モデル化と問題解決（MPS）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2024-06-13","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"31","bibliographicVolumeNumber":"2024-MPS-148"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":234918,"updated":"2025-01-19T09:40:16.422730+00:00","links":{},"created":"2025-01-19T01:36:48.934058+00:00"}