{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:33:05Z","timestamp":1772119985301,"version":"3.50.1"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"Korean Government","doi-asserted-by":"publisher","award":["2021R1A2C2006268"],"award-info":[{"award-number":["2021R1A2C2006268"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute of Information and Communications Technology Planning and Evaluation"},{"DOI":"10.13039\/501100003621","name":"Korea Government","doi-asserted-by":"publisher","award":["2019-0-01842"],"award-info":[{"award-number":["2019-0-01842"]}],"id":[{"id":"10.13039\/501100003621","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3261884","type":"journal-article","created":{"date-parts":[[2023,3,27]],"date-time":"2023-03-27T18:54:52Z","timestamp":1679943292000},"page":"30768-30782","source":"Crossref","is-referenced-by-count":7,"title":["Exploiting All Samples in Low-Resource Sentence Classification: Early Stopping and Initialization Parameters"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3006-617X","authenticated-orcid":false,"given":"Hongseok","family":"Choi","sequence":"first","affiliation":[{"name":"School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology (GIST), Gwangju, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2389-7183","authenticated-orcid":false,"given":"Hyunju","family":"Lee","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology (GIST), Gwangju, South Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3502287"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3386252"},{"key":"ref3","first-page":"2545","article-title":"A survey on recent approaches for natural language processing in low-resource scenarios","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Hum. Lang. Technol.","author":"Hedderich"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/access.2020.3045078"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3343038"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3409565"},{"key":"ref7","first-page":"2580","article-title":"Transfer learning and distant supervision for multilingual transformer models: A study on African languages","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process. (EMNLP)","author":"Hedderich"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2018.09.034"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-018-0723-6"},{"key":"ref10","first-page":"4519","article-title":"HuRIC: A human robot interaction corpus","volume-title":"Proc. 9th Int. Conf. Lang. Resour. Eval. (LREC)","author":"Bastianelli"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2020.610139"},{"issue":"7553","key":"ref12","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref13","article-title":"Establishing baselines for text classification in low-resource languages","author":"Cruz","year":"2020","journal-title":"arXiv:2005.02068"},{"key":"ref14","first-page":"726","article-title":"Human annotated Arabic dataset of book reviews for aspect based sentiment analysis","volume-title":"Proc. 3rd Int. Conf. Future Internet Things Cloud","author":"Al-Smadi"},{"issue":"2","key":"ref15","doi-asserted-by":"crossref","first-page":"15","DOI":"10.3390\/data3020015","article-title":"Datasets for aspect-based sentiment analysis in Bangla and its baseline evaluation","volume":"3","author":"Rahman","year":"2018","journal-title":"Data"},{"key":"ref16","volume-title":"Deep Learning","volume":"1","author":"Goodfellow","year":"2016"},{"key":"ref17","first-page":"670","article-title":"Supervised learning of universal sentence representations from natural language inference data","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Conneau"},{"key":"ref18","first-page":"773","article-title":"GIST at SemEval-2018 task 12: A network transferring inference knowledge to argument reasoning comprehension task","volume-title":"Proc. 12th Int. Workshop Semantic Eval.","author":"Choi"},{"key":"ref19","article-title":"An overview of multi-task learning in deep neural networks","author":"Ruder","year":"2017","journal-title":"arXiv:1706.05098"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.02.026"},{"key":"ref21","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Finn"},{"key":"ref22","first-page":"3342","article-title":"Towards realistic practices in low-resource natural language processing: The development set","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process. 9th Int. Joint Conf. Natural Lang. Process. (EMNLP-IJCNLP)","author":"Kann"},{"key":"ref23","first-page":"2877","article-title":"Imitation learning for neural morphological string transduction","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Makarov"},{"key":"ref24","first-page":"501","article-title":"Bootstrapping transliteration with constrained discovery for low-resource languages","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Upadhyay"},{"key":"ref25","article-title":"Early stopping without a validation set","author":"Mahsereci","year":"2017","journal-title":"arXiv:1703.09580"},{"key":"ref26","first-page":"6098","article-title":"Unsupervised embedding adaptation via early-stage feature reconstruction for few-shot classification","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Lee"},{"key":"ref27","first-page":"1321","article-title":"On calibration of modern neural networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Guo"},{"key":"ref28","first-page":"1","article-title":"MetaInit: Initializing learning by learning to initialize","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Dauphin"},{"key":"ref29","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Hum. Lang. Technol.","author":"Devlin"},{"key":"ref30","first-page":"152","article-title":"Effective self-training for parsing","volume-title":"Proc. Hum. Lang. Tech. Conf. NAACL","author":"McClosky"},{"key":"ref31","first-page":"483","article-title":"WORDNET: A lexical database for English","volume-title":"Proc. Hum. Lang. Technol. Process. Workshop","author":"Miller"},{"key":"ref32","first-page":"6382","article-title":"EDA: Easy data augmentation techniques for boosting performance on text classification tasks","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process. 9th Int. Joint Conf. Natural Lang. Process. (EMNLP-IJCNLP)","author":"Wei"},{"key":"ref33","article-title":"Low resource text classification with ULMFit and backtranslation","author":"Shleifer","year":"2019","journal-title":"arXiv:1903.09244"},{"key":"ref34","first-page":"23965","article-title":"Model soups: Averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wortsman"},{"key":"ref35","first-page":"1","article-title":"Merging models with Fisher-weighted averaging","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Matena"},{"key":"ref36","first-page":"876","article-title":"Averaging weights leads to wider optima and better generalization","volume-title":"Proc. Conf. Uncertainty Artif. Intell.","author":"Izmailov"},{"key":"ref37","first-page":"1","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref38","first-page":"3436","article-title":"Mixup-transformer: Dynamic data augmentation for NLP tasks","volume-title":"Proc. 28th Int. Conf. Comput. Linguistics","author":"Sun"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-1599-1_104"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.2021.1921037"},{"key":"ref41","first-page":"708","article-title":"Early stopping based on unlabeled samples in text classification","volume-title":"Proc. 60th Annu. Meeting Assoc. Comput. Linguistics","author":"Choi"},{"key":"ref42","first-page":"3598","article-title":"RATT: Leveraging unlabeled data to guarantee generalization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Garg"},{"key":"ref43","first-page":"351","article-title":"Channel-wise early stopping without a validation set via NNK polytope interpolation","volume-title":"Proc. Asia\u2013Pacific","author":"Bonet"},{"key":"ref44","first-page":"1","article-title":"SentEval: An evaluation toolkit for universal sentence representations","volume-title":"Proc. 11th Int. Conf. Lang. Resour. Eval. (LREC)","author":"Conneau"},{"key":"ref45","first-page":"1746","article-title":"Convolutional neural networks for sentence classification","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Kim"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/1014052.1014073"},{"key":"ref47","first-page":"115","article-title":"Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales","volume-title":"Proc. 43rd Annu. Meeting Assoc. Comput. Linguistics","author":"Pang"},{"key":"ref48","first-page":"1631","article-title":"Recursive deep models for semantic compositionality over a sentiment treebank","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Socher"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-005-7880-9"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/345508.345577"},{"key":"ref51","article-title":"End to end learning for self-driving cars","author":"Bojarski","year":"2016","journal-title":"arXiv:1604.07316"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.2172\/1525811"},{"issue":"7","key":"ref53","first-page":"1","article-title":"Measuring calibration in deep learning","volume-title":"Proc. CVPR Workshops","volume":"2","author":"Nixon"},{"key":"ref54","first-page":"1","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani"},{"key":"ref55","volume-title":"Bridging Nonlinearities and Stochastic Regularizers With Gaussian Error Linear Units","author":"Hendrycks","year":"2016"},{"key":"ref56","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref57","volume-title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems","author":"Abadi","year":"2015"},{"key":"ref58","first-page":"3638","article-title":"Prompt-free and efficient few-shot learning with language models","volume-title":"Proc. 60th Annu. Meeting Assoc. Comput. Linguistics","author":"Mahabadi"},{"key":"ref59","first-page":"21199","article-title":"Uncertainty-aware self-training for few-shot text classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Mukherjee"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6233"},{"issue":"8","key":"ref61","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref62","first-page":"38","article-title":"Transformers: State-of-the-art natural language processing","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process., Syst. Demonstrations","author":"Wolf"},{"key":"ref63","first-page":"968","article-title":"A survey of data augmentation approaches for NLP","volume-title":"Proc. Findings Assoc. for Comput. Linguistics","author":"Feng"},{"key":"ref64","first-page":"1","article-title":"Reformer: The efficient transformer","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kitaev"},{"key":"ref65","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10081314.pdf?arnumber=10081314","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T18:37:42Z","timestamp":1707849462000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10081314\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3261884","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}