{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:27:04Z","timestamp":1782779224848,"version":"3.54.5"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030841850","type":"print"},{"value":"9783030841867","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-84186-7_31","type":"book-chapter","created":{"date-parts":[[2021,8,7]],"date-time":"2021-08-07T10:03:42Z","timestamp":1628330622000},"page":"471-484","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":207,"title":["A Robustly Optimized BERT Pre-training Approach with Post-training"],"prefix":"10.1007","author":[{"given":"Zhuang","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wayne","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ya","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,8,8]]},"reference":[{"key":"31_CR1","unstructured":"Bowman, S.R., Pavlick, E., Grave, E.: Looking for Elmo\u2019s friends: sentence-level pretraining beyond language modeling. CoRR abs\/1812.10860 (2018)"},{"key":"31_CR2","doi-asserted-by":"publisher","unstructured":"Chen, Z., Liu, B.: Lifelong Machine Learning. Synthesis Lectures on Artificial Intelligence and Machine Learning, 2nd edn. Morgan & Claypool Publishers, Williston (2018). https:\/\/doi.org\/10.2200\/S00832ED1V01Y201802AIM037","DOI":"10.2200\/S00832ED1V01Y201802AIM037"},{"key":"31_CR3","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Burstein, J., Doran, C., Solorio, T. (eds.) Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, 2\u20137 June, 2019, Volume 1 (Long and Short Papers), pp. 4171\u20134186. Association for Computational Linguistics (2019). https:\/\/doi.org\/10.18653\/v1\/n19-1423","DOI":"10.18653\/v1\/n19-1423"},{"key":"31_CR4","unstructured":"Hou, M., Chen, X., Huang, S., Xie, S., Zhou, G.: Generalizing deep multi-task learning with heterogeneous structured networks. In: Proceedings of ICLR (2020)"},{"key":"31_CR5","unstructured":"Joshi, M., Chen, D., Liu, Y., Weld, D.S., Zettlemoyer, L., Levy, O.: SpanBERT: improving pre-training by representing and predicting spans. CoRR abs\/1907.10529 (2019). http:\/\/arxiv.org\/abs\/1907.10529"},{"key":"31_CR6","doi-asserted-by":"publisher","unstructured":"Joshi, M., Choi, E., Weld, D.S., Zettlemoyer, L.: Triviaqa: a large scale distantly supervised challenge dataset for reading comprehension. In: Barzilay, R., Kan, M. (eds.) Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017, Vancouver, Canada, 30 July \u2013 4 August, Volume 1: Long Papers, pp. 1601\u20131611. Association for Computational Linguistics (2017). https:\/\/doi.org\/10.18653\/v1\/P17-1147","DOI":"10.18653\/v1\/P17-1147"},{"key":"31_CR7","doi-asserted-by":"publisher","unstructured":"Lai, G., Xie, Q., Liu, H., Yang, Y., Hovy, E.H.: RACE: large-scale reading comprehension dataset from examinations. In: Palmer, M., Hwa, R., Riedel, S. (eds.) Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017, Copenhagen, Denmark, 9\u201311 September, 2017, pp. 785\u2013794. Association for Computational Linguistics (2017). https:\/\/doi.org\/10.18653\/v1\/d17-1082","DOI":"10.18653\/v1\/d17-1082"},{"key":"31_CR8","unstructured":"Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: ALBERT: A lite BERT for self-supervised learning of language representations. In: 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26\u201330, 2020. OpenReview.net (2020), https:\/\/openreview.net\/forum?id=H1eA7AEtvS"},{"key":"31_CR9","unstructured":"Levesque, H.J., Davis, E., Morgenstern, L.: The winograd schema challenge (2012)"},{"key":"31_CR10","doi-asserted-by":"publisher","unstructured":"Liu, X., et al.: The microsoft toolkit of multi-task deep neural networks for natural language understanding. In: Celikyilmaz, A., Wen, T. (eds.) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, ACL 2020, Online, 5\u201310 July, 2020, pp. 118\u2013126. Association for Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-demos.16","DOI":"10.18653\/v1\/2020.acl-demos.16"},{"key":"31_CR11","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized BERT pretraining approach. CoRR abs\/1907.11692 (2019). http:\/\/arxiv.org\/abs\/1907.11692"},{"key":"31_CR12","doi-asserted-by":"crossref","unstructured":"Liu, Z., Huang, D., Huang, K., Li, Z., Zhao, J.: Finbert: a pre-trained financial language representation model for financial text mining. In: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI 2020, 5\u201310 January, 2021, Yokohama, Japan, pp. 4513\u20134519 (2020)","DOI":"10.24963\/ijcai.2020\/622"},{"key":"31_CR13","doi-asserted-by":"publisher","unstructured":"Liu, Z., Huang, K., Huang, D., Liu, Z., Zhao, J.: Dual head-wise coattention network for machine comprehension with multiple-choice questions. In: d\u2019Aquin, M., Dietze, S., Hauff, C., Curry, E., Cudr\u00e9-Mauroux, P. (eds.) CIKM 2020: The 29th ACM International Conference on Information and Knowledge Management, Virtual Event, Ireland, 19\u201323 October, 2020, pp. 1015\u20131024. ACM (2020). https:\/\/doi.org\/10.1145\/3340531.3412013","DOI":"10.1145\/3340531.3412013"},{"key":"31_CR14","doi-asserted-by":"publisher","unstructured":"Maia, M., et al. (eds.): Proceedings of WWW. ACM (2018). https:\/\/doi.org\/10.1145\/3184558","DOI":"10.1145\/3184558"},{"key":"31_CR15","doi-asserted-by":"crossref","unstructured":"Ohsugi, Y., Saito, I., Nishida, K., Asano, H., Tomita, J.: A simple but effective method to incorporate multi-turn context with BERT for conversational machine comprehension. CoRR abs\/1905.12848 (2019). http:\/\/arxiv.org\/abs\/1905.12848","DOI":"10.18653\/v1\/W19-4102"},{"key":"31_CR16","doi-asserted-by":"publisher","unstructured":"Parisi, G.I., Kemker, R., Part, J.L., Kanan, C., Wermter, S.: Continual lifelong learning with neural networks: a review. Neural Networks. 113, 54\u201371 (2019). https:\/\/doi.org\/10.1016\/j.neunet.2019.01.012","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"31_CR17","doi-asserted-by":"publisher","unstructured":"Peters, M.E., et al.: Deep contextualized word representations. In: Walker, M.A., Ji, H., Stent, A. (eds.) Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2018, New Orleans, Louisiana, USA, 1\u20136 June, 2018, Volume 1 (Long Papers), pp. 2227\u20132237. Association for Computational Linguistics (2018). https:\/\/doi.org\/10.18653\/v1\/n18-1202","DOI":"10.18653\/v1\/n18-1202"},{"key":"31_CR18","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding by generative pre-training. In: Proceedings of Technical Report, OpenAI (2018). https:\/\/github.com\/openai\/finetune-transformer-lm"},{"key":"31_CR19","doi-asserted-by":"publisher","unstructured":"Rajpurkar, P., Jia, R., Liang, P.: Know what you don\u2019t know: unanswerable questions for squad. In: Gurevych, I., Miyao, Y. (eds.) Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018, Melbourne, Australia, 15\u201320 July, 2018, Volume 2: Short Papers, pp. 784\u2013789. Association for Computational Linguistics (2018). https:\/\/doi.org\/10.18653\/v1\/P18-2124, https:\/\/www.aclweb.org\/anthology\/P18-2124\/","DOI":"10.18653\/v1\/P18-2124"},{"key":"31_CR20","doi-asserted-by":"publisher","unstructured":"Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P.: Squad: 100,000+ questions for machine comprehension of text. In: Su, J., Carreras, X., Duh, K. (eds.) Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, EMNLP 2016, Austin, Texas, USA, 1\u20134 November, 2016, pp. 2383\u20132392. The Association for Computational Linguistics (2016). https:\/\/doi.org\/10.18653\/v1\/d16-1264","DOI":"10.18653\/v1\/d16-1264"},{"key":"31_CR21","doi-asserted-by":"crossref","unstructured":"Reddy, S., Chen, D., Manning, C.D.: CoQA: a conversational question answering challenge. Trans. Assoc. Comput. Linguist. 7, 249\u2013266 (2019). https:\/\/transacl.org\/ojs\/index.php\/tacl\/article\/view\/1572","DOI":"10.1162\/tacl_a_00266"},{"key":"31_CR22","unstructured":"Sun, Y., Wang, S., Li, Y.: ERNIE: enhanced representation through knowledge integration. CoRR abs\/1904.09223 (2019). http:\/\/arxiv.org\/abs\/1904.09223"},{"key":"31_CR23","doi-asserted-by":"crossref","unstructured":"Trischler, A., et al.: Newsqa: a machine comprehension dataset. In: Proceedings of the 2nd Workshop on Representation Learning for NLP (2017)","DOI":"10.18653\/v1\/W17-2623"},{"key":"31_CR24","unstructured":"Wang, A., et al.: SuperGLUE: a stickier benchmark for general-purpose language understanding systems. In: Wallach, H.M., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9-Buc, F., Fox, E.B., Garnett, R. (eds.) Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, 8\u201314 December, 2019, Vancouver, BC, Canada, pp. 3261\u20133275 (2019). https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/4496bf24afe7fab6f046bf4923da8de6-Abstract.html"},{"key":"31_CR25","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.R.: GLUE: a multi-task benchmark and analysis platform for natural language understanding. In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, 6\u20139 May, 2019. OpenReview.net (2019). https:\/\/openreview.net\/forum?id=rJ4km2R5t7"},{"key":"31_CR26","doi-asserted-by":"publisher","unstructured":"Yang, W., et al.: End-to-end open-domain question answering with BERTserini. In: Ammar, W., Louis, A., Mostafazadeh, N. (eds.) Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, 2\u20137 June, 2019, Demonstrations, pp. 72\u201377. Association for Computational Linguistics (2019). https:\/\/doi.org\/10.18653\/v1\/n19-4013","DOI":"10.18653\/v1\/n19-4013"},{"key":"31_CR27","unstructured":"Yang, Z., Dai, Z., Yang, Y., Carbonell, J.G., Salakhutdinov, R., Le, Q.V.: XLnet: generalized autoregressive pretraining for language understanding. In: Wallach, H.M., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9-Buc, F., Fox, E.B., Garnett, R. (eds.) Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, 8\u201314 December, 2019, Vancouver, BC, Canada, pp. 5754\u20135764 (2019). https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/dc6a7e655d7e5840e66733e9ee67cc69-Abstract.html"},{"key":"31_CR28","doi-asserted-by":"publisher","unstructured":"Yang, Z., et al.: Hotpotqa: a dataset for diverse, explainable multi-hop question answering. In: Riloff, E., Chiang, D., Hockenmaier, J., Tsujii, J. (eds.) Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, 31 October \u2013 4 November, 2018, pp. 2369\u20132380. Association for Computational Linguistics (2018). https:\/\/doi.org\/10.18653\/v1\/d18-1259","DOI":"10.18653\/v1\/d18-1259"}],"container-title":["Lecture Notes in Computer Science","Chinese Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-84186-7_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,7]],"date-time":"2021-08-07T10:13:07Z","timestamp":1628331187000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-84186-7_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030841850","9783030841867"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-84186-7_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"8 August 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CCL","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China National Conference on Chinese Computational Linguistics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hohhot","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 August 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 August 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cncl2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.cips-cl.org\/static\/CCL2021\/en\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"www.softconf.com","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"90","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"31","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"34% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}