{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T03:05:21Z","timestamp":1772766321785,"version":"3.50.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Hong Kong Research Grants Council"},{"name":"Collaborative Research Fund","award":["C1031-18G"],"award-info":[{"award-number":["C1031-18G"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2023.3325970","type":"journal-article","created":{"date-parts":[[2023,10,19]],"date-time":"2023-10-19T18:19:12Z","timestamp":1697739552000},"page":"189-199","source":"Crossref","is-referenced-by-count":8,"title":["Enhancing Low-Resource NLP by Consistency Training With Data and Model Perturbations"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1550-2877","authenticated-orcid":false,"given":"Xiaobo","family":"Liang","sequence":"first","affiliation":[{"name":"Soochow University, Suzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1555-2436","authenticated-orcid":false,"given":"Runze","family":"Mao","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3530-590X","authenticated-orcid":false,"given":"Lijun","family":"Wu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6286-7529","authenticated-orcid":false,"given":"Juntao","family":"Li","sequence":"additional","affiliation":[{"name":"Soochow University, Suzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3895-5510","authenticated-orcid":false,"given":"Min","family":"Zhang","sequence":"additional","affiliation":[{"name":"Soochow University, Suzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3370-471X","authenticated-orcid":false,"given":"Qing","family":"Li","sequence":"additional","affiliation":[{"name":"Hong Kong Polytechnic University, Hong Kong"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-45528-0"},{"key":"ref4","first-page":"3365","article-title":"Learning with pseudo-ensembles","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Bachman","year":"2014"},{"key":"ref5","article-title":"Temporal ensembling for semi-supervised learning","author":"Laine","year":"2016"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/504"},{"key":"ref7","first-page":"6256","article-title":"Unsupervised data augmentation for consistency training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Xie","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1217"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858821"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01269"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.197"},{"key":"ref12","article-title":"Better fine-tuning by reducing representational collapse","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Aghajanyan","year":"2020"},{"key":"ref13","article-title":"CoDA: Contrast-enhanced and diversity-promoting data augmentation for natural language understanding","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Qu","year":"2021"},{"key":"ref14","article-title":"A simple but tough-to-beat data augmentation approach for natural language understanding and generation","author":"Shen","year":"2020"},{"issue":"1","key":"ref15","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref16","article-title":"Dropout with expectation-linear regularization","author":"Ma","year":"2016"},{"key":"ref17","article-title":"Fraternal dropout","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zolna","year":"2018"},{"key":"ref18","article-title":"R-drop: Regularized dropout for neural networks","author":"Liang","year":"2021"},{"key":"ref19","first-page":"1163","article-title":"Regularization with stochastic transformations and perturbations for deep semi-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Sajjadi","year":"2016"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"ref21","first-page":"1341","article-title":"Gaussian process training with input noise","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"24","author":"McHutchon","year":"2011"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.01.011"},{"key":"ref23","article-title":"Randaugment: Practical data augmentation with no separate search","author":"Cubuk","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref25","article-title":"Reducing transformer depth on demand with structured dropout","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fan","year":"2019"},{"key":"ref26","first-page":"1736","article-title":"Deep transformers with latent depth","volume":"33","author":"Li","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref28","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref30","article-title":"Incorporating BERT into neural machine translation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","year":"2019"},{"key":"ref31","first-page":"584","article-title":"Language models not just for pre-training: Fast online neural noisy channel modeling","volume-title":"Proc. 5th Conf. Mach. Transl.","author":"Bhosale","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref33","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"ref34","first-page":"142","article-title":"Introduction to the CoNLL-2003 shared task: Language-independent named entity recognition","volume-title":"Proc. 7th Conf. Natural Lang. Learn. HLT-NAACL","author":"Sang","year":"2003"},{"key":"ref35","first-page":"10","article-title":"Named entity recognition in wikipedia","volume-title":"Proc. Workshop Peoples Web Meets NLP Collaboratively Constructed Semantic Resour.","author":"Balasuriya","year":"2009"},{"key":"ref36","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","year":"2019"},{"key":"ref37","first-page":"4992","article-title":"Unsupervised data augmentation with naive augmentation and without unlabeled data","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Lowell","year":"2021"},{"key":"ref38","first-page":"5381","article-title":"Learning from noisy labels for entity-centric information extraction","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Zhou","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1045"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1009"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1555"},{"key":"ref42","article-title":"Mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2018"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref44","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Tarvainen","year":"2017"},{"key":"ref45","first-page":"1568","article-title":"Transfer learning for low-resource neural machine translation","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Zoph","year":"2016"},{"key":"ref46","doi-asserted-by":"crossref","first-page":"3461","DOI":"10.18653\/v1\/P19-1336","article-title":"Dual adversarial neural transfer for low-resource named entity recognition","volume-title":"Proc. 57th Annu. Meeting Assoc. Comput. Linguistics","author":"Zhou","year":"2019"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403149"},{"key":"ref48","doi-asserted-by":"crossref","first-page":"8118","DOI":"10.18653\/v1\/2020.acl-main.722","article-title":"Soft gazetteers for low-resource named entity recognition","volume-title":"Proc. 58th Annu. Meeting Assoc. Comput. Linguistics","author":"Rijhwani","year":"2020"},{"key":"ref49","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Finn","year":"2017"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6301"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10288035.pdf?arnumber=10288035","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T09:59:39Z","timestamp":1709373579000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10288035\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3325970","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}