{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T02:51:08Z","timestamp":1774320668144,"version":"3.50.1"},"reference-count":38,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100010418","name":"Institute for Information and Communications Technology Promotion","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Korea Ministry of Science and ICT","doi-asserted-by":"publisher","award":["IITP-2026-RS-2020-II201808"],"award-info":[{"award-number":["IITP-2026-RS-2020-II201808"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Applied Soft Computing"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.asoc.2026.114991","type":"journal-article","created":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:26:21Z","timestamp":1773246381000},"page":"114991","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Improving training efficiency for length-imbalanced translation data using optimal packing point"],"prefix":"10.1016","volume":"195","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1285-7812","authenticated-orcid":false,"given":"Jeong Woo","family":"Seo","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0398-831X","authenticated-orcid":false,"given":"Ho-Young","family":"Jung","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.asoc.2026.114991_bib0005","first-page":"30","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.asoc.2026.114991_bib0010","author":"Krell"},{"key":"10.1016\/j.asoc.2026.114991_bib0015","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.asoc.2026.114991_bib0020","first-page":"1376","article-title":"LongAlign: a recipe for long context alignment of large language models","author":"Bai","year":"2024","journal-title":"Find. Assoc. Comput. Linguist.: EMNLP"},{"key":"10.1016\/j.asoc.2026.114991_bib0025","series-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)","first-page":"400","article-title":"LlamaFactory: unified efficient Fine-Tuning of 100+ language models","author":"Zheng","year":"2024"},{"key":"10.1016\/j.asoc.2026.114991_bib0030","series-title":"Proceedings of the 26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","first-page":"389","article-title":"Turbotransformers: an efficient GPU serving system for transformer models","author":"Fang","year":"2021"},{"key":"10.1016\/j.asoc.2026.114991_bib0035","series-title":"2023 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","first-page":"344","article-title":"Bytetransformer: a high-performance transformer boosted for variable-length inputs","author":"Zhai","year":"2023"},{"key":"10.1016\/j.asoc.2026.114991_bib0040","author":"Liu"},{"key":"10.1016\/j.asoc.2026.114991_bib0045","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations)","first-page":"48","article-title":"Fairseq: a fast, extensible toolkit for sequence modeling","author":"Ott","year":"2019"},{"key":"10.1016\/j.asoc.2026.114991_bib0050","series-title":"Llama 2: Open foundation and Fine-Tuned chat models","author":"Touvron","year":"2023"},{"key":"10.1016\/j.asoc.2026.114991_bib0055","author":"Pouransari"},{"key":"10.1016\/j.asoc.2026.114991_bib0060","series-title":"Third Congress on Intelligent Systems: Proceedings of CIS 2022","first-page":"145","article-title":"A study of machine translation models for Kannada-Tulu","volume":"vol. 1","author":"Hegde","year":"2023"},{"key":"10.1016\/j.asoc.2026.114991_bib0065","series-title":"Proceedings of LT4HALA 2020-1st Workshop on Language Technologies for Historical and Ancient Languages","first-page":"94","article-title":"Latin-Spanish neural machine translation: from the Bible to Saint Augustine","author":"Garcia","year":"2020"},{"issue":"4","key":"10.1016\/j.asoc.2026.114991_bib0070","doi-asserted-by":"crossref","DOI":"10.1145\/3580495","article-title":"Filtering and extended vocabulary based translation for low-resource language pair of Sanskrit-Hindi","volume":"22","author":"Jha","year":"2023","journal-title":"ACM Trans. Asian Low-Resour. Lang. Inf. Process."},{"key":"10.1016\/j.asoc.2026.114991_bib0075","series-title":"Proceedings of the Second Workshop on Language Technologies for Historical and Ancient Languages","first-page":"43","article-title":"Machine translation of 16th century letters from Latin to German","author":"Fischer","year":"2022"},{"issue":"2","key":"10.1016\/j.asoc.2026.114991_bib0080","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1016\/j.ipm.2017.08.003","article-title":"Machine translation for Arabic dialects (survey)","volume":"56","author":"Harrat","year":"2019","journal-title":"Inf. Process. Manag."},{"key":"10.1016\/j.asoc.2026.114991_bib0085","series-title":"Proceedings of the Thirteenth Language Resources and Evaluation Conference","first-page":"22","article-title":"Priming ancient Korean neural machine translation","author":"Park","year":"2022"},{"key":"10.1016\/j.asoc.2026.114991_bib0090","series-title":"2019 International Conference on Document Analysis and Recognition (ICDAR)","first-page":"607","article-title":"Kuronet: pre-modern Japanese kuzushiji character recognition with deep learning","author":"Clanuwat","year":"2019"},{"key":"10.1016\/j.asoc.2026.114991_bib0095","series-title":"Improving language understanding by generative pre-training","first-page":"1","author":"Radford","year":"2018"},{"issue":"8","key":"10.1016\/j.asoc.2026.114991_bib0100","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"10.1016\/j.asoc.2026.114991_bib0105","first-page":"1877","article-title":"Language models are Few-Shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.asoc.2026.114991_bib0110","series-title":"LLaMA: open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"10.1016\/j.asoc.2026.114991_bib0115","series-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","first-page":"7871","article-title":"BART: denoising Sequence-to-Sequence pre-training for natural language generation, translation, and comprehension","author":"Lewis","year":"2020"},{"issue":"1","key":"10.1016\/j.asoc.2026.114991_bib0120","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.asoc.2026.114991_bib0125","series-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations","first-page":"38","article-title":"Transformers: State-of-the-Art natural language processing","author":"Wolf","year":"2020"},{"key":"10.1016\/j.asoc.2026.114991_bib0130","author":"Beltagy"},{"key":"10.1016\/j.asoc.2026.114991_bib0135","author":"Child"},{"key":"10.1016\/j.asoc.2026.114991_bib0140","author":"Kitaev"},{"key":"10.1016\/j.asoc.2026.114991_bib0145","series-title":"International Conference on Machine Learning","first-page":"5156","article-title":"Transformers are RNNS: fast autoregressive transformers with linear attention","author":"Katharopoulos","year":"2020"},{"key":"10.1016\/j.asoc.2026.114991_bib0150","author":"Choromanski"},{"key":"10.1016\/j.asoc.2026.114991_bib0155","author":"Dettmers"},{"key":"10.1016\/j.asoc.2026.114991_bib0160","series-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"1715","article-title":"Neural machine translation of rare words with subword units","author":"Sennrich","year":"2016"},{"key":"10.1016\/j.asoc.2026.114991_bib0165","series-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations","first-page":"66","article-title":"SentencePiece: a simple and language independent subword tokenizer and detokenizer for neural text processing","author":"Kudo","year":"2018"},{"key":"10.1016\/j.asoc.2026.114991_bib0170","series-title":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"4031","article-title":"Restoring and mining the records of the Joseon dynasty via neural language modeling and machine translation","author":"Kang","year":"2021"},{"key":"10.1016\/j.asoc.2026.114991_bib0175","series-title":"Proceedings of the Second Conference on Machine Translation","first-page":"169","article-title":"Findings of the 2017 Conference on Machine Translation (wmt17)","author":"Bojar","year":"2017"},{"key":"10.1016\/j.asoc.2026.114991_bib0180","series-title":"Proceedings of the 11th International Workshop on Spoken Language Translation: Evaluation Campaign","first-page":"2","article-title":"Report on the 11th IWSLT evaluation campaign","author":"Cettolo","year":"2014"},{"key":"10.1016\/j.asoc.2026.114991_bib0185","author":"Gala"},{"key":"10.1016\/j.asoc.2026.114991_bib0190","series-title":"Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics","first-page":"311","article-title":"BLEU: a method for automatic evaluation of machine translation","author":"Papineni","year":"2002"}],"container-title":["Applied Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626004394?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626004394?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T01:53:07Z","timestamp":1774317187000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1568494626004394"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":38,"alternative-id":["S1568494626004394"],"URL":"https:\/\/doi.org\/10.1016\/j.asoc.2026.114991","relation":{},"ISSN":["1568-4946"],"issn-type":[{"value":"1568-4946","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Improving training efficiency for length-imbalanced translation data using optimal packing point","name":"articletitle","label":"Article Title"},{"value":"Applied Soft Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.asoc.2026.114991","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114991"}}