{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,3]],"date-time":"2026-01-03T06:48:01Z","timestamp":1767422881413,"version":"3.37.3"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U19A2057","61876223"],"award-info":[{"award-number":["U19A2057","61876223"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["WK3480000010","WK3480000008"],"award-info":[{"award-number":["WK3480000010","WK3480000008"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/taslp.2021.3121986","type":"journal-article","created":{"date-parts":[[2021,11,4]],"date-time":"2021-11-04T19:25:49Z","timestamp":1636053949000},"page":"3307-3320","source":"Crossref","is-referenced-by-count":13,"title":["Review and Arrange: Curriculum Learning for Natural Language Understanding"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8090-4883","authenticated-orcid":false,"given":"Licheng","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5739-8126","authenticated-orcid":false,"given":"Zhendong","family":"Mao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Benfeng","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1151-1792","authenticated-orcid":false,"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"year":"0","key":"ref73","article-title":"CLUE"},{"year":"0","key":"ref72","article-title":"PyCLUE"},{"key":"ref71","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Proc Int Conf Learn Representations"},{"article-title":"Huggingface's transformers: State-of-the-art natural language processing","year":"2019","author":"wolf","key":"ref70"},{"key":"ref74","first-page":"657","article-title":"Revisiting pre-trained models for Chinese natural language processing","author":"cui","year":"2020","journal-title":"Proc Findings Empirical Methods Natural Lang Process"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299188"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.344"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.41"},{"key":"ref32","first-page":"5238","article-title":"Curriculum learning by transfer learning: Theory and experiments with deep networks","author":"weinshall","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"article-title":"An empirical exploration of curriculum learning for neural machine translation","year":"2018","author":"zhang","key":"ref31"},{"key":"ref30","first-page":"1","article-title":"Learning to teach","author":"fan","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6244"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.52"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.689"},{"key":"ref34","first-page":"6934","article-title":"Uncertainty-aware curriculum learning for neural machine translation","author":"zhou","year":"0","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref60","first-page":"5886","article-title":"OCNLI: Original Chinese natural language inference","author":"cui","year":"2019","journal-title":"Proc Conf Empirical Methods Natural Lang Process 9th Int Joint Conf Natural Lang Process"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00305"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1075"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1101"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00512"},{"article-title":"First quora dataset release: Question pairs","year":"0","author":"iyer","key":"ref64"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1058"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00290"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S17-2001"},{"key":"ref29","first-page":"1311","article-title":"Automated curriculum learning for neural networks","author":"graves","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref67","first-page":"9","article-title":"Automatically constructing a corpus of sentential paraphrases","author":"dolan","year":"2005","journal-title":"Proc 3rd Int Workshop Paraphrasing"},{"key":"ref68","first-page":"1","article-title":"The fifth PASCAL recognizing textual entailment challenge","author":"bentivogli","year":"0","journal-title":"Proc TAC"},{"key":"ref69","first-page":"552","article-title":"The winograd schema challenge","author":"levesque","year":"2012","journal-title":"Proc 13th Int Conf Princ Knowl Representation Reasoning"},{"key":"ref2","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"devlin","year":"2019","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"article-title":"Improving language understanding by generative pre-training","year":"2018","author":"radford","key":"ref1"},{"key":"ref20","first-page":"5493","article-title":"Few-shot text classification with triplet networks, data augmentation, and curriculum learning","author":"wei","year":"2021","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.542"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018577"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.168"},{"key":"ref23","first-page":"2379","article-title":"Self-paced learning for long-term tracking","author":"supancic","year":"2013","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref26","first-page":"1189","article-title":"Self-paced learning for latent variable models","author":"kumar","year":"2010","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1043"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4302"},{"key":"ref51","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","author":"houlsby","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref59","first-page":"3512","article-title":"OCNLI: Original Chinese natural language inference","author":"hu","year":"2020","journal-title":"Proc Findings Empirical Methods Natural Lang Process"},{"year":"0","key":"ref58","article-title":"AFQMC"},{"year":"0","key":"ref57","article-title":"IFLYTEK"},{"year":"0","key":"ref56","article-title":"TNEWS"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.419"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5801"},{"key":"ref52","first-page":"191","article-title":"NewsQA: A machine comprehension dataset","author":"trischler","year":"2016","journal-title":"Proc 2th Workshop Representation Learn NLP"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1901\/jeab.2004.82-317"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2008.11.014"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"3732","DOI":"10.1109\/TNNLS.2019.2934906","article-title":"Teacher-student curriculum learning","volume":"31","author":"tambet","year":"2020","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3069908"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1013"},{"key":"ref15","first-page":"2304","article-title":"MentorNet: Learning data-driven curriculum for very deep neural networks on corrupted labels","author":"jiang","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_9"},{"key":"ref17","first-page":"2535","article-title":"On the power of curriculum learning in training deep networks","author":"hacohen","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1119"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1486"},{"article-title":"RoBERTa: A robustly optimized BERT pretraining approach","year":"2019","author":"liu","key":"ref4"},{"key":"ref3","first-page":"5753","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","author":"yang","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"raffel","year":"2020","journal-title":"J Mach Learn Res"},{"key":"ref5","first-page":"1","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","author":"lan","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1037\/h0049039"},{"key":"ref7","first-page":"1631","article-title":"Recursive deep models for semantic compositionality over a sentiment treebank","author":"socher","year":"2013","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.197"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0277(93)90058-4"},{"key":"ref46","first-page":"784","article-title":"Know what you don’t know: Unanswerable questions for squad","author":"rajpurkar","year":"2018","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref48","first-page":"1","article-title":"FreeLB: Enhanced adversarial training for natural language understanding","author":"zhu","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1441"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.02.028"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.306"},{"key":"ref44","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_23"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09583843.pdf?arnumber=9583843","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:54:00Z","timestamp":1652194440000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9583843\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3121986","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2021]]}}}