{"links":{},"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00221140","sets":["6504:11035:11043"]},"path":["11043"],"owner":"44499","recid":"221140","title":["和文英訳自動添削システムにおける内容誤り検出手法の検討"],"pubdate":{"attribute_name":"公開日","attribute_value":"2022-02-17"},"_buckets":{"deposit":"e3ecc576-c93c-4e3f-9095-d4b60c5ae3d3"},"_deposit":{"id":"221140","pid":{"type":"depid","value":"221140","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"和文英訳自動添削システムにおける内容誤り検出手法の検討","author_link":["578805","578803","578806","578804","578807"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"和文英訳自動添削システムにおける内容誤り検出手法の検討"}]},"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":"2022-02-17","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":"静岡大"},{"subitem_text_value":"静岡大"},{"subitem_text_value":"静岡大"},{"subitem_text_value":"静岡大"},{"subitem_text_value":"静岡大"}]},"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/221140/files/IPSJ-Z84-4W-02.pdf","label":"IPSJ-Z84-4W-02.pdf"},"date":[{"dateType":"Available","dateValue":"2022-10-22"}],"format":"application/pdf","filename":"IPSJ-Z84-4W-02.pdf","filesize":[{"value":"448.0 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"70c994fa-5abb-4754-b2a1-87edd9be8954","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2022 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"天野, 勇弥"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"松井, 颯汰"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"綱川, 隆司"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"西田, 昌史"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"西村, 雅史"}],"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":"本研究は人手による添削と同様の自動添削が行えるシステムの構築を目指し，和文英訳問題における学習者の解答文に対する誤り検出に焦点を当て，その手法について検討する．従来の和文英訳の自動添削システムは，文の長さや語彙の相違などに着目し，いかに模範解答に近いかを基準に採点を行う手法が一般的であるため，文章全体の意味を正確に理解した判定は難しい．そこで本研究では事前学習にBERTを用いたモデルを複数作成し，それぞれのモデルで2つの文章の意味の類似度を測り，文の意味が一致しているか否かによる2値分類を行った．実験の結果，Sentence-BERTを用いた2値分類においてF値で0. 817の結果が得られた．","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"808","bibliographic_titles":[{"bibliographic_title":"第84回全国大会講演論文集"}],"bibliographicPageStart":"807","bibliographicIssueDates":{"bibliographicIssueDate":"2022-02-17","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2022"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"created":"2025-01-19T01:21:09.210085+00:00","updated":"2025-01-19T14:16:57.441150+00:00","id":221140}