{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00236266","sets":["6504:11678:11689"]},"path":["11689"],"owner":"44499","recid":"236266","title":["Evaluating the Effect of Sub-Word Training on Syntactic Language Models -A Linguistic Perspective-"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-03-01"},"_buckets":{"deposit":"688b85b1-61f7-43ae-9131-d16c407e1e7a"},"_deposit":{"id":"236266","pid":{"type":"depid","value":"236266","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Evaluating the Effect of Sub-Word Training on Syntactic Language Models -A Linguistic Perspective-","author_link":["645775"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Evaluating the Effect of Sub-Word Training on Syntactic Language Models -A Linguistic Perspective-"}]},"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":"2024-03-01","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"}]},"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/236266/files/IPSJ-Z86-1W-06.pdf","label":"IPSJ-Z86-1W-06.pdf"},"date":[{"dateType":"Available","dateValue":"2024-07-03"}],"format":"application/pdf","filename":"IPSJ-Z86-1W-06.pdf","filesize":[{"value":"416.2 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"4e7be981-860a-4371-b7ec-fe3c6c9b9d68","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"岡村, 康平"}],"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":"This study evaluates the effect of incorporating sub-word units (morphemes) in training large language models (LLMs), highlighting its role in reducing vocabulary size and managing unknown and compound words more effectively. Beyond these established benefits, the research also emphasises the importance of considering the hierarchical morphological structures of languages and their generative capacities. It addresses how simplistic assumptions underpinning syntactic competence, which focus solely on surface linear strings, struggle to resolve　linguistic problems such as ambiguities (e.g., un-lockable versus unlock-able) and long-dependencies (e.g., en-joy-able versus *joy-able). The research posits that an improved understanding of morphological structures, grounded in the Hierarchical Morphological Processing Hypothesis, can enhance the performance and accuracy of LLMs.","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"868","bibliographic_titles":[{"bibliographic_title":"第86回全国大会講演論文集"}],"bibliographicPageStart":"867","bibliographicIssueDates":{"bibliographicIssueDate":"2024-03-01","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2024"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":236266,"updated":"2025-01-19T09:19:39.274927+00:00","links":{},"created":"2025-01-19T01:38:13.414732+00:00"}