{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00216958","sets":["1164:4619:10826:10881"]},"path":["10881"],"owner":"44499","recid":"216958","title":["ガウス過程を用いた周波数スペクトル分析による副詞の理解"],"pubdate":{"attribute_name":"公開日","attribute_value":"2022-03-03"},"_buckets":{"deposit":"0e83e2ed-a158-4832-9426-01f2d20c54d4"},"_deposit":{"id":"216958","pid":{"type":"depid","value":"216958","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"ガウス過程を用いた周波数スペクトル分析による副詞の理解","author_link":["561131","561128","561132","561124","561129","561130","561127","561119","561126","561121","561122","561125","561123","561120"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"ガウス過程を用いた周波数スペクトル分析による副詞の理解"},{"subitem_title":"Understanding Adverbs Expressing Human Actions by Frequency Spectrum Analysis Using Gaussian Processes","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"セッション5-A","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2022-03-03","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"お茶の水女子大学"},{"subitem_text_value":"統計数理研究所"},{"subitem_text_value":"電気通信大学"},{"subitem_text_value":"電気通信大学"},{"subitem_text_value":"大阪大学"},{"subitem_text_value":"国立情報学研究所"},{"subitem_text_value":"お茶の水女子大学"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Department of Information Science, Ochanomizu University","subitem_text_language":"en"},{"subitem_text_value":"The Institute of Statistical Mathematics","subitem_text_language":"en"},{"subitem_text_value":"Department of Mechanical Engineering and Intelligent Systems, The University of Electro-Communications","subitem_text_language":"en"},{"subitem_text_value":"Department of Mechanical Engineering and Intelligent Systems, The University of Electro-Communications","subitem_text_language":"en"},{"subitem_text_value":"Department of Systems Science, Osaka University","subitem_text_language":"en"},{"subitem_text_value":"National Institute of Informatics::Department of Information Science, Ochanomizu 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/216958/files/IPSJ-CVIM22229027.pdf","label":"IPSJ-CVIM22229027.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CVIM22229027.pdf","filesize":[{"value":"3.2 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"20"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"ac247446-836f-4e09-9bb3-8dbc69385def","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2022 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":"谷口, 巴"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"持橋, 大地"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"長野, 匡隼"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"中村, 友昭"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"長井, 隆行"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"稲邑, 哲也"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"小林, 一郎"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Tomoe, Taniguchi","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Daichi, Mochihashi","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Masatoshi, Nagano","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Tomoaki, Nakamura","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Takayuki, Nagai","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Tetsunari, Inamura","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Ichiro, Kobayashi","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11131797","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":"2188-8701","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":" 近年，汎用言語モデルの出現などにより自然言語処理には大きな革新がもたらされ，記述されたテキストに対する意味理解の研究は飛躍的に進んだと言える．一方で，実世界における言葉の意味理解に対しては，未だ十分に研究が進んでいるとは言えない．今後，ロボットなどが家庭に導入された際に，ロボットは日常生活でより充実したサービスを提供するために，言語を通じて人と同じ実世界における感覚を共有した動作が期待される．よって，実世界環境における現象を説明するための言語の意味を理解することは，重要な課題と言える．本研究では，中でも実世界環境で用いられる副詞の意味に着目し，特に人の動作を対象として理解することを目的とする．具体的に，3 つの手法を用いて課題に取り組む．(i) Gaussian Process Latent Variable Model を用いて潜在空間における副詞表現と人の動作対応関係を捉え，(ii) 人の動作を Spectral Mixture Kernel を用いたガウス過程により解析を行い，特定の副詞を表現する動作に共通する周波数カーネルを発見する．(iii) 動作の特徴を表す周波数カーネルとその動作を表現する副詞の共通トピックを同時に学習することにより，副詞と動作の対応関係を捉えるモデルを提案する．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"In this study, we attempt to understand the meaning of adverbs through the features of human actions. Specifically, the trajectories in the nonlinear latent space obtained by compressing human actions with a Gaussian process latent variable model (GPLVM) are represented by a Gaussian process with a Spectral Mixture kernel. We also propose a multimodal topic model in frequency space that captures the correspondence between adverbs and the multiple frequency components that make up the trajectories in each dimension.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告コンピュータビジョンとイメージメディア（CVIM）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2022-03-03","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"27","bibliographicVolumeNumber":"2022-CVIM-229"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":216958,"updated":"2025-01-19T15:40:29.493125+00:00","links":{},"created":"2025-01-19T01:17:28.135049+00:00"}