{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T22:56:00Z","timestamp":1743029760898,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031446924"},{"type":"electronic","value":"9783031446931"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-44693-1_29","type":"book-chapter","created":{"date-parts":[[2023,10,7]],"date-time":"2023-10-07T08:02:39Z","timestamp":1696665759000},"page":"361-372","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["An Adaptive Learning Method for\u00a0Solving the\u00a0Extreme Learning Rate Problem of\u00a0Transformer"],"prefix":"10.1007","author":[{"given":"Jianbang","family":"Ding","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuancheng","family":"Ren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruixuan","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,10,8]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Chen, M.X., et al.: The best of both worlds: Combining recent advances in neural machine translation. In: ACL (1), pp. 76\u201386. Association for Computational Linguistics (2018)","DOI":"10.18653\/v1\/P18-1008"},{"key":"29_CR2","doi-asserted-by":"crossref","unstructured":"Dai, Z., Yang, Z., Yang, Y., Carbonell, J.G., Le, Q.V., Salakhutdinov, R.: Transformer-xl: attentive language models beyond a fixed-length context. In: ACL (1), pp. 2978\u20132988. Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/P19-1285"},{"key":"29_CR3","unstructured":"Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12, 2121\u20132159 (2011)"},{"key":"29_CR4","doi-asserted-by":"crossref","unstructured":"Gehrmann, S., Deng, Y., Rush, A.M.: Bottom-up abstractive summarization. In: EMNLP, pp. 4098\u20134109. Association for Computational Linguistics (2018)","DOI":"10.18653\/v1\/D18-1443"},{"key":"29_CR5","unstructured":"Gotmare, A., Keskar, N.S., Xiong, C., Socher, R.: A closer look at deep learning heuristics: Learning rate restarts, warmup and distillation. In: ICLR (Poster). OpenReview.net (2019)"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Huang, H., Wang, C., Dong, B.: Nostalgic adam: weighting more of the past gradients when designing the adaptive learning rate. In: IJCAI, pp. 2556\u20132562. ijcai.org (2019)","DOI":"10.24963\/ijcai.2019\/355"},{"key":"29_CR7","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (Poster) (2015)"},{"key":"29_CR8","volume-title":"Learning multiple layers of features from tiny images","author":"A Krizhevsky","year":"2009","unstructured":"Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images. Tech. rep, Citeseer (2009)"},{"key":"29_CR9","unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches out, pp. 74\u201381 (2004)"},{"key":"29_CR10","unstructured":"Liu, L., Jiang, H., He, P., Chen, W., Liu, X., Gao, J., Han, J.: On the variance of the adaptive learning rate and beyond. arXiv preprint arXiv:1908.03265 (2019)"},{"key":"29_CR11","unstructured":"Loshchilov, I., Hutter, F.: Fixing weight decay regularization in adam. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"29_CR12","unstructured":"Luo, L., Xiong, Y., Liu, Y., Sun, X.: Adaptive gradient methods with dynamic bound of learning rate. In: ICLR (Poster). OpenReview.net (2019)"},{"issue":"2","key":"29_CR13","first-page":"313","volume":"19","author":"MP Marcus","year":"1993","unstructured":"Marcus, M.P., Santorini, B., Marcinkiewicz, M.A.: Building a large annotated corpus of English: the penn treebank. Comput. Linguist. 19(2), 313\u2013330 (1993)","journal-title":"Comput. Linguist."},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Ott, M., et al.: fairseq: a fast, extensible toolkit for sequence modeling. In: NAACL-HLT (Demonstrations), pp. 48\u201353. Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/N19-4009"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pp. 311\u2013318. Association for Computational Linguistics (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"29_CR16","doi-asserted-by":"publisher","first-page":"43","DOI":"10.2478\/pralin-2018-0002","volume":"110","author":"M Popel","year":"2018","unstructured":"Popel, M., Bojar, O.: Training tips for the transformer model. Prague Bull. Math. Linguistics 110, 43\u201370 (2018)","journal-title":"Prague Bull. Math. Linguistics"},{"key":"29_CR17","unstructured":"Reddi, S.J., Kale, S., Kumar, S.: On the convergence of adam and beyond. In: ICLR. OpenReview.net (2018)"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Robbins, H., Monro, S.: A stochastic approximation method. The annals of mathematical statistics, pp. 400\u2013407 (1951)","DOI":"10.1214\/aoms\/1177729586"},{"key":"29_CR19","unstructured":"Shazeer, N., Stern, M.: Adafactor: adaptive learning rates with sublinear memory cost. In: ICML. Proceedings of Machine Learning Research, vol. 80, pp. 4603\u20134611. PMLR (2018)"},{"key":"29_CR20","unstructured":"Tieleman, T., Hinton, G.: Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude. COURSERA: Neural Networks Mach. Learn. 4(2), 26\u201331 (2012)"},{"key":"29_CR21","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Wang, Q., Li, B., Xiao, T., Zhu, J., Li, C., Wong, D.F., Chao, L.S.: Learning deep transformer models for machine translation. In: ACL (1), pp. 1810\u20131822. Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/P19-1176"},{"key":"29_CR23","unstructured":"Wilson, A.C., Roelofs, R., Stern, M., Srebro, N., Recht, B.: The marginal value of adaptive gradient methods in machine learning. In: Advances in Neural Information Processing Systems, pp. 4148\u20134158 (2017)"},{"key":"29_CR24","unstructured":"Xiong, R., et al.: On layer normalization in the transformer architecture. CoRR abs\/2002.04745 (2020)"},{"key":"29_CR25","unstructured":"Zeiler, M.D.: Adadelta: an adaptive learning rate method. arXiv preprint arXiv:1212.5701 (2012)"},{"key":"29_CR26","unstructured":"Zhou, Z., Zhang, Q., Lu, G., Wang, H., Zhang, W., Yu, Y.: Adashift: decorrelation and convergence of adaptive learning rate methods. In: ICLR (Poster). OpenReview.net (2019)"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44693-1_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,9]],"date-time":"2023-10-09T08:22:32Z","timestamp":1696839752000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44693-1_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031446924","9783031446931"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44693-1_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"8 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Foshan","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2023\/index.php","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":"Softconf","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"478","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":"143","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":"30% - 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":"4","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}