{"created":"2025-01-19T01:29:48.574289+00:00","updated":"2025-01-19T11:15:02.580807+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00230196","sets":["6504:11436:11440"]},"path":["11440"],"owner":"44499","recid":"230196","title":["Corpus Augmentation Based on Pseudo-Chinese Generation for Chinese-Japanese Neural Machine Translation"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-02-16"},"_buckets":{"deposit":"cadb1a96-f347-4d2f-8d6a-a84ffc697f06"},"_deposit":{"id":"230196","pid":{"type":"depid","value":"230196","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Corpus Augmentation Based on Pseudo-Chinese Generation for Chinese-Japanese Neural Machine Translation","author_link":["619326","619325"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Corpus Augmentation Based on Pseudo-Chinese Generation for Chinese-Japanese Neural Machine Translation"}]},"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":"2023-02-16","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"item_22_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"筑波大"},{"subitem_text_value":"筑波大"}]},"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/230196/files/IPSJ-Z85-4W-05.pdf","label":"IPSJ-Z85-4W-05.pdf"},"date":[{"dateType":"Available","dateValue":"2023-11-17"}],"format":"application/pdf","filename":"IPSJ-Z85-4W-05.pdf","filesize":[{"value":"490.8 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"9b35b9ab-008a-464b-bb71-e14f3f3067d6","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2023 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"魏, 徴"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"関, 洋平"}],"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":"The performance of neural machine translation model depends on the size of training datasets. This paper presents a novel corpus augmentation for Chinese-Japanese neural machine translation. Unlike conventional corpus augmentation methods, we perform corpus augmentation by generating pseudo-Chinese sentences directly from Japanese monolingual corpus. Rules are set up to replace particles and auxiliaries written in kana characters with Chinese kanji words that have the same meanings. In addition, using word embedding, nouns, verbs, adjectives written in kana characters are converted into words written in kanji characters with the similar meaning. We evaluate the proposed method using BLEU evaluation metric and compare it with back-translation method.","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"822","bibliographic_titles":[{"bibliographic_title":"第85回全国大会講演論文集"}],"bibliographicPageStart":"821","bibliographicIssueDates":{"bibliographicIssueDate":"2023-02-16","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2023"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":230196,"links":{}}