{"id":188715,"updated":"2025-01-20T01:54:21.693417+00:00","links":{},"created":"2025-01-19T00:54:50.242722+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00188715","sets":["6504:9465:9481"]},"path":["9481"],"owner":"6748","recid":"188715","title":["相槌・フィラー予測とのマルチタスク学習による円滑なターンテイキング"],"pubdate":{"attribute_name":"公開日","attribute_value":"2018-03-13"},"_buckets":{"deposit":"ee18fb21-4f54-4422-b2c9-5fe9155ad4cc"},"_deposit":{"id":"188715","pid":{"type":"depid","value":"188715","revision_id":0},"owners":[6748],"status":"published","created_by":6748},"item_title":"相槌・フィラー予測とのマルチタスク学習による円滑なターンテイキング","author_link":["428355","428353","428352","428354"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"相槌・フィラー予測とのマルチタスク学習による円滑なターンテイキング"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"人工知能と認知科学","subitem_subject_scheme":"Other"}]},"item_type_id":"22","publish_date":"2018-03-13","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_22_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"京大"},{"subitem_text_value":"京大"},{"subitem_text_value":"京大"},{"subitem_text_value":"京大"}]},"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/188715/files/IPSJ-Z80-6Q-07.pdf","label":"IPSJ-Z80-6Q-07.pdf"},"date":[{"dateType":"Available","dateValue":"2018-05-07"}],"format":"application/pdf","filename":"IPSJ-Z80-6Q-07.pdf","filesize":[{"value":"314.6 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"de529b3b-4c2b-4f35-b8c3-e9c3ebdef3cd","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2018 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"原, 康平"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"井上, 昂治"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"高梨, 克也"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"河原, 達也"}],"nameIdentifiers":[{}]}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_5794","resourcetype":"conference paper"}]},"item_22_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00349328","subitem_source_identifier_type":"NCID"}]},"item_22_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"人との自然な対話を指向したヒューマンロボットインタラクションにおいて,円滑なターンテイキングの実現は重要な課題である.円滑なターンテイキングを実現するためには,発話末における話者交替および継続の予測が必要である.また,これに関連するふるまいとして,相槌およびフィラーの生成が挙げられる.従来研究では,これらを予測する課題は独立に扱われてきた.本研究では,マルチタスク学習の枠組みにより,これらのふるまいの予測を同一のモデルで扱うことで,ターンテイキング予測の精度向上を目指す.自律型アンドロイドERICAを用いた対話コーパスでの実験により,提案手法の予測精度がシングルタスクの場合よりも向上することを示す.","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"410","bibliographic_titles":[{"bibliographic_title":"第80回全国大会講演論文集"}],"bibliographicPageStart":"409","bibliographicIssueDates":{"bibliographicIssueDate":"2018-03-13","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2018"}]},"relation_version_is_last":true,"weko_creator_id":"6748"}}