{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T00:11:38Z","timestamp":1778544698129,"version":"3.51.4"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tai.2024.3396125","type":"journal-article","created":{"date-parts":[[2024,5,3]],"date-time":"2024-05-03T15:19:45Z","timestamp":1714749585000},"page":"6095-6108","source":"Crossref","is-referenced-by-count":10,"title":["Epi-Curriculum: Episodic Curriculum Learning for Low-Resource Domain Adaptation in Neural Machine Translation"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4894-7415","authenticated-orcid":false,"given":"Keyu","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, University of South Florida, Tampa, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4569-7123","authenticated-orcid":false,"given":"Di","family":"Zhuang","sequence":"additional","affiliation":[{"name":"University of South Florida, Tampa, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4553-9598","authenticated-orcid":false,"given":"Mingchen","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, University of South Florida, Tampa, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0660-7191","authenticated-orcid":false,"given":"J.","family":"Morris Chang","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, University of South Florida, Tampa, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Sutskever","year":"2014"},{"key":"ref2","first-page":"1","article-title":"Findings of the 2019 Conference on Machine Translation (WMT19)","volume-title":"Proc. 4th Conf. Mach. Transl.","author":"Barrault","year":"2019"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"7871","DOI":"10.18653\/v1\/2020.acl-main.703","article-title":"BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension","volume-title":"Proc. 58th Annu. Meeting Assoc. Comput. Linguistics","author":"Lewis","year":"2020"},{"issue":"140","key":"ref4","first-page":"1","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":"ref5","doi-asserted-by":"crossref","first-page":"28","DOI":"10.18653\/v1\/W17-3204","article-title":"Six challenges for neural machine translation","volume-title":"Proc. 1st Workshop Neural Mach. Transl.","author":"Koehn","year":"2017"},{"key":"ref6","first-page":"1304","article-title":"A survey of domain adaptation for neural machine translation","volume-title":"Proc. 27th Int. Conf. Comput. Linguistics","author":"Chu","year":"2018"},{"key":"ref7","first-page":"29","article-title":"Findings of the WMT 2019 biomedical translation shared task: Evaluation for MEDLINE abstracts and biomedical terminologies","volume-title":"Proc. 4th Conf. Mach. Transl. (Volume 3: Shared Task Papers, Day 2)","author":"Bawden","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1163"},{"key":"ref9","first-page":"3622","article-title":"Meta-learning for low-resource neural machine translation","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process. (EMNLP)","author":"Gu","year":"2018"},{"key":"ref10","first-page":"5191","article-title":"Improving both domain robustness and domain adaptability in machine translation","volume-title":"Proc. 29th Int. Conf. Comput. Linguistics","author":"Lai","year":"2022"},{"key":"ref11","first-page":"151","article-title":"Domain robustness in neural machine translation","volume-title":"Proc. 14th Conf. Assoc. Mach. Transl. Amer. (Volume 1: Res. rack)","author":"M\u00fcller","year":"2020"},{"key":"ref12","first-page":"76","article-title":"Stanford neural machine translation systems for spoken language domains","volume-title":"Proc. 12th Int. Workshop Spoken Lang. Transl.: Eval. Campaign","author":"Luong","year":"2015"},{"key":"ref13","first-page":"18\u2013","article-title":"Fine-tuning for neural machine translation with limited degradation across in- and out-of-domain data","volume-title":"Proc. Mach. Transl. Summit XVI, Res. Track","author":"Dakwale","year":"Sep"},{"key":"ref14","first-page":"2062","article-title":"Overcoming catastrophic forgetting during domain adaptation of neural machine translation","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Human Lang. Technol.","volume":"1","author":"Thompson","year":"2019"},{"key":"ref15","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn","year":"2017"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"43","DOI":"10.18653\/v1\/2020.ngt-1.5","article-title":"Meta-learning for few-shot NMT adaptation","volume-title":"Proc. 4th Workshop Neural Gener. Transl.","author":"Sharaf","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6339"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17683"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86383-8_46"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref21","first-page":"1538","article-title":"Simple, scalable adaptation for neural machine translation","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.\/9th Int. Joint Conf. Natural Lang. Process. (EMNLP-IJCNLP)","author":"Bapna","year":"2019"},{"key":"ref22","article-title":"Generic and specialized word embeddings for multi-domain machine translation","volume-title":"Proc. 16th Int. Workshop Spoken Lang. Transl.","author":"Pham","year":"2019"},{"key":"ref23","first-page":"451","article-title":"Discriminative instance weighting for domain adaptation in statistical machine translation","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Foster","year":"2010"},{"key":"ref24","first-page":"1259","article-title":"How to avoid unwanted pregnancies: Domain adaptation using neural network models","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Joty","year":"2015"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00153"},{"key":"ref26","first-page":"220","article-title":"Intelligent selection of language model training data","volume-title":"Proc. ACL Conf. Short Papers","author":"Moore","year":"2010"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"7711","DOI":"10.18653\/v1\/2020.acl-main.689","article-title":"Learning a multi-domain curriculum for neural machine translation","volume-title":"Proc. 58th Annu. Meeting Assoc. Comput. Linguistics","author":"Wang","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3069908"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"74","DOI":"10.18653\/v1\/W18-2709","article-title":"On the impact of various types of noise on neural machine translation","volume-title":"Proc. 2nd Workshop Neural Mach. Transl. Gener.","author":"Khayrallah","year":"2018"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"1282","DOI":"10.18653\/v1\/P19-1123","article-title":"Dynamically composing domain-data selection with clean-data selection by \u201cco-curricular learning\u201d for neural machine translation","volume-title":"Proc. 57th Annu. Meeting Assoc. Comput. Linguistics","author":"Wang","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"},{"key":"ref33","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014"},{"key":"ref34","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani","year":"2017"},{"key":"ref35","first-page":"765","article-title":"Findings of the WMT 2020 shared tasks in unsupervised MT and very low resource supervised MT","volume-title":"Proc. 5th Conf. Mach. Transl.","author":"Fraser","year":"2020"},{"key":"ref36","first-page":"1903","article-title":"Curriculum learning for domain adaptation in neural machine translation","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Human Lang. Technologies","volume":"1","author":"Zhang","year":"2019"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"3802","DOI":"10.18653\/v1\/2022.acl-long.264","article-title":"The trade-offs of domain adaptation for neural language models","volume-title":"Proc. 60th Annu. Meeting Assoc. Comput. Linguistics (Volume 1: Long Papers)","author":"Grangier","year":"2022"},{"key":"ref38","first-page":"1482","article-title":"Instance weighting for neural machine translation domain adaptation","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Wang","year":"2017"},{"key":"ref39","article-title":"On first-order meta-learning algorithms","author":"Nichol","year":"2018"},{"key":"ref40","first-page":"463","article-title":"Multi-adversarial learning for cross-lingual word embeddings","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Human Lang. Technologies","author":"Wang","year":"2021"},{"key":"ref41","first-page":"1314","article-title":"Fast lexically constrained decoding with dynamic beam allocation for neural machine translation","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Human Lang. Technologies","volume":"1","author":"Post","year":"2018"},{"key":"ref42","first-page":"1417","article-title":"Unsupervised domain adaptation for neural machine translation with domain-aware feature embeddings","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.\/9th Int. Joint Conf. Natural Lang. Process. (EMNLP-IJCNLP)","author":"Dou","year":"2019"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"40","DOI":"10.18653\/v1\/W17-3205","article-title":"Cost weighting for neural machine translation domain adaptation","volume-title":"Proc. 1st Workshop Neural Mach. Transl.","author":"Chen","year":"2017"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014951"},{"key":"ref45","first-page":"2214","article-title":"Parallel data, tools and interfaces in OPUS","volume-title":"Proc. 8th Int. Conf. Lang. Resour. Eval. (LREC\u201912)","author":"Tiedemann","year":"2012"},{"key":"ref46","first-page":"4596","article-title":"Adafactor: Adaptive learning rates with sublinear memory cost","volume-title":"Int. Conf. Mach. Learn.","author":"Shazeer","year":"2018"},{"key":"ref47","article-title":"An empirical exploration of curriculum learning for neural machine translation","author":"Zhang","year":"2018"},{"key":"ref48","first-page":"2888","article-title":"Unsupervised neural machine translation for low-resource domains via meta-learning","volume-title":"Proc. 59th Annu. Meeting Assoc. Comput. Linguistics\/11th Int. Joint Conf. Natural Lang. Process.","volume":"1","author":"Park","year":"2021"},{"key":"ref49","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","volume-title":"Proc. 5th Int. Conf. Learn. Representations (ICLR)","author":"Keskar","year":"2017"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00454"},{"key":"ref51","first-page":"18250","article-title":"Generalized federated learning via sharpness aware minimization","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Qu","year":"2022"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9078688\/10794552\/10518166.pdf?arnumber=10518166","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:09:32Z","timestamp":1755911372000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10518166\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":51,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tai.2024.3396125","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}