{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T18:21:50Z","timestamp":1776190910043,"version":"3.50.1"},"reference-count":40,"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":[{"name":"Google TPU Research Cloud program for Cloud TPU access"},{"DOI":"10.13039\/501100013290","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2020AAA0106501"],"award-info":[{"award-number":["2020AAA0106501"]}],"id":[{"id":"10.13039\/501100013290","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976072"],"award-info":[{"award-number":["61976072"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772153"],"award-info":[{"award-number":["61772153"]}],"id":[{"id":"10.13039\/501100001809","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.2021.3124365","type":"journal-article","created":{"date-parts":[[2021,11,2]],"date-time":"2021-11-02T21:44:07Z","timestamp":1635889447000},"page":"3504-3514","source":"Crossref","is-referenced-by-count":1024,"title":["Pre-Training With Whole Word Masking for Chinese BERT"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2452-375X","authenticated-orcid":false,"given":"Yiming","family":"Cui","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3907-0335","authenticated-orcid":false,"given":"Wanxiang","family":"Che","sequence":"additional","affiliation":[]},{"given":"Ting","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Bing","family":"Qin","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0666-4409","authenticated-orcid":false,"given":"Ziqing","family":"Yang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref1","article-title":"Pre-training with whole word masking for Chinese BERT","author":"Cui","year":"2019"},{"key":"ref2","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":"ref3","first-page":"784","article-title":"Know what you dont know: Unanswerable questions for SQuAD","volume-title":"Proc. 56th Annu. Meeting Assoc. Comput. Linguistics","author":"Rajpurkar","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00266"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1241"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1082"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6502"},{"key":"ref10","article-title":"Option comparison network for multiple-choice reading comprehension","author":"Ran","year":"2019"},{"key":"ref11","article-title":"ERNIR: Enhanced representation through knowledge integration","author":"Sun","year":"2019"},{"key":"ref12","first-page":"1","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Yang","year":"2019"},{"key":"ref13","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00300"},{"key":"ref15","first-page":"1","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lan","year":"2020"},{"key":"ref16","first-page":"1","article-title":"ELECTRA: Pre-training text encoders as discriminators rather than generators","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Clark","year":"2020"},{"key":"ref17","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref18","article-title":"Googles neural machine translation system: Bridging the gap between human and machine translation","author":"Wu","year":"2016"},{"key":"ref19","first-page":"1","article-title":"A mutual information maximization perspective of language representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kong","year":"2020"},{"key":"ref20","first-page":"2672","article-title":"Generative adversarial nets","volume-title":"Advances in Neural Information Processing Systems","volume":"27","author":"Goodfellow","year":"2014"},{"key":"ref21","first-page":"13","article-title":"LTP: A chinese language technology platform","volume-title":"Proc. 23rd Int. Conf. Comput. Linguistics. Demonstrations","author":"Che","year":"2010"},{"key":"ref22","first-page":"1","article-title":"PMI-masking: Principled masking of correlated spans","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Levine","year":"2021"},{"key":"ref23","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","volume-title":"Advances in Neural Information Processing Systems","volume":"26","author":"Mikolov","year":"2013"},{"key":"ref24","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref25","first-page":"1","article-title":"Reducing BERT pre-training time from 3 days to 76 minutes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"You","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1600"},{"key":"ref27","article-title":"DRCD: A Chinese machine reading comprehension dataset","author":"Shao","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32381-3_36"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2007.05.028"},{"key":"ref30","first-page":"774","article-title":"Scalable term selection for text categorization","volume-title":"Proc. Joint Conf. Empirical Methods Natural Lang. Process. Comput. Natural Lang. Learn.","author":"Li","year":"2007"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.419"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1269"},{"key":"ref33","first-page":"1952","article-title":"LCQMC: A large-scale Chinese question matching corpus","volume-title":"Proc. 27th Int. Conf. Comput. Linguistics","author":"Liu","year":"2018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1536"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.314"},{"key":"ref36","first-page":"8968","article-title":"ERNIE 2.0: A continual pre-training framework for language understanding","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Sun","year":"2019"},{"key":"ref37","article-title":"NEZHA: Neural contextualized representation for Chinese language understanding","author":"Wei","year":"2019"},{"key":"ref38","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","volume-title":"Proc. 12th USENIX Symp. Operating Syst. Des. Implementation","author":"Abadi","year":"2016"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-3106"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09599397.pdf?arnumber=9599397","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T01:32:18Z","timestamp":1706059938000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9599397\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3124365","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}