{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T16:23:39Z","timestamp":1742919819595,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030926373"},{"type":"electronic","value":"9783030926380"}],"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\/978-3-030-92638-0_19","type":"book-chapter","created":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T13:02:45Z","timestamp":1641042165000},"page":"316-334","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MS-BERT: A\u00a0Multi-layer Self-distillation Approach for\u00a0BERT Compression Based on\u00a0Earth Mover\u2019s Distance"],"prefix":"10.1007","author":[{"given":"Jiahui","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaxing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,1,1]]},"reference":[{"key":"19_CR1","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), Minneapolis, Minnesota, pp. 4171\u20134186. Association for Computational Linguistics, June 2019"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Gordon, M., Duh, K., Andrews, N.: Compressing BERT: studying the effects of weight pruning on transfer learning. In: Proceedings of the 5th Workshop on Representation Learning for NLP, pp. 143\u2013155. Association for Computational Linguistics, July 2020","DOI":"10.18653\/v1\/2020.repl4nlp-1.18"},{"key":"19_CR3","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","volume":"129","author":"J Gou","year":"2021","unstructured":"Gou, J., Yu, B., Maybank, S.J., Tao, D.: Knowledge distillation: a survey. Int. J. Comput. Vis. 129, 1789\u20131819 (2021)","journal-title":"Int. J. Comput. Vis."},{"key":"19_CR4","unstructured":"Graves, A.: Adaptive computation time for recurrent neural networks. arXiv preprint arXiv:1603.08983 (2016)"},{"key":"19_CR5","unstructured":"Han, S., Pool, J., Tran, J., Dally, W.J.: Learning both weights and connections for efficient neural networks. CoRR arXiv:1506.02626 (2015)"},{"key":"19_CR6","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"19_CR7","doi-asserted-by":"crossref","unstructured":"Jawahar, G., Sagot, B., Seddah, D.: What does BERT learn about the structure of language? In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy, pp. 3651\u20133657. Association for Computational Linguistics, July 2019","DOI":"10.18653\/v1\/P19-1356"},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"Jiao, X., et al.: TinyBERT: distilling BERT for natural language understanding. In: Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 4163\u20134174. Association for Computational Linguistics, November 2020","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"Kovaleva, O., Romanov, A., Rogers, A., Rumshisky, A.: Revealing the dark secrets of BERT. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China, pp. 4365\u20134374. Association for Computational Linguistics, November 2019","DOI":"10.18653\/v1\/D19-1445"},{"key":"19_CR10","unstructured":"Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: ALBERT: a lite BERT for self-supervised learning of language representations. CoRR arXiv:1909.11942 (2019)"},{"key":"19_CR11","doi-asserted-by":"crossref","unstructured":"Li, J., Liu, X., Zhao, H., Xu, R., Yang, M., Jin, Y.: BERT-EMD: many-to-many layer mapping for bert compression with earth mover\u2019s distance. arXiv preprint arXiv:2010.06133 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.242"},{"key":"19_CR12","doi-asserted-by":"crossref","unstructured":"Liu, W., Zhou, P., Wang, Z., Zhao, Z., Deng, H., Ju, Q.: FastBERT: a self-distilling BERT with adaptive inference time. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 6035\u20136044. Association for Computational Linguistics, July 2020","DOI":"10.18653\/v1\/2020.acl-main.537"},{"key":"19_CR13","unstructured":"Liu, X., et al.: LCQMC: a large-scale Chinese question matching corpus. In: Proceedings of the 27th International Conference on Computational Linguistics, Santa Fe, New Mexico, USA, pp. 1952\u20131962. Association for Computational Linguistics, August 2018"},{"key":"19_CR14","unstructured":"McCarley, J., Chakravarti, R., Sil, A.: Structured pruning of a BERT-based question answering model. CoRR arXiv:1910.06360 (2019)"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Mirzadeh, S.I., Farajtabar, M., Li, A., Levine, N., Matsukawa, A., Ghasemzadeh, H.: Improved knowledge distillation via teacher assistant. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 5191\u20135198 (2020)","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Pele, O., Werman, M.: Fast and robust earth mover\u2019s distances. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 460\u2013467. IEEE, September 2009","DOI":"10.1109\/ICCV.2009.5459199"},{"key":"19_CR17","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)"},{"key":"19_CR18","unstructured":"Sanh, V., Debut, L., Chaumond, J., Wolf, T.: DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. CoRR arXiv:1910.01108 (2019)"},{"key":"19_CR19","volume-title":"Introduction to Information Retrieval","author":"H Sch\u00fctze","year":"2008","unstructured":"Sch\u00fctze, H., Manning, C.D., Raghavan, P.: Introduction to Information Retrieval, vol. 39. Cambridge University Press, Cambridge (2008)"},{"issue":"12","key":"19_CR20","doi-asserted-by":"publisher","first-page":"713","DOI":"10.1109\/EE.1938.6431064","volume":"57","author":"CE Shannon","year":"1938","unstructured":"Shannon, C.E.: A symbolic analysis of relay and switching circuits. Electr. Eng. 57(12), 713\u2013723 (1938). https:\/\/doi.org\/10.1109\/EE.1938.6431064","journal-title":"Electr. Eng."},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"Sun, S., Cheng, Y., Gan, Z., Liu, J.: Patient knowledge distillation for BERT model compression. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China, pp. 4323\u20134332. Association for Computational Linguistics, November 2019","DOI":"10.18653\/v1\/D19-1441"},{"key":"19_CR22","unstructured":"Torregrossa, F., Claveau, V., Kooli, N., Gravier, G., Allesiardo, R.: On the correlation of word embedding evaluation metrics. In: Proceedings of the 12th Language Resources and Evaluation Conference, Marseille, France, pp. 4789\u20134797. European Language Resources Association, May 2020. https:\/\/www.aclweb.org\/anthology\/2020.lrec-1.589"},{"key":"19_CR23","doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.: GLUE: a multi-task benchmark and analysis platform for natural language understanding. In: Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, Brussels, Belgium, pp. 353\u2013355. Association for Computational Linguistics, November 2018","DOI":"10.18653\/v1\/W18-5446"},{"issue":"10","key":"19_CR24","doi-asserted-by":"publisher","first-page":"2495","DOI":"10.1109\/TPAMI.2018.2857824","volume":"41","author":"Y Wang","year":"2018","unstructured":"Wang, Y., Xu, C., Xu, C., Tao, D.: Packing convolutional neural networks in the frequency domain. IEEE Trans. Pattern Analy. Mach. Intell. 41(10), 2495\u20132510 (2018)","journal-title":"IEEE Trans. Pattern Analy. Mach. Intell."},{"key":"19_CR25","unstructured":"Xu, Y., Qiu, X., Zhou, L., Huang, X.: Improving BERT fine-tuning via self-ensemble and self-distillation. arXiv preprint arXiv:2002.10345 (2020)"},{"key":"19_CR26","doi-asserted-by":"crossref","unstructured":"Yang, Z., Shou, L., Gong, M., Lin, W., Jiang, D.: Model compression with multi-task knowledge distillation for web-scale question answering system. arXiv preprint arXiv:1904.09636 (2019)","DOI":"10.1145\/3336191.3371792"},{"key":"19_CR27","unstructured":"Yang, Z., Dai, Z., Yang, Y., Carbonell, J.G., Salakhutdinov, R., Le, Q.V.: XLNet: generalized autoregressive pretraining for language understanding. CoRR arXiv:1906.08237 (2019)"},{"key":"19_CR28","unstructured":"Zhao, S., Gupta, R., Song, Y., Zhou, D.: Extreme language model compression with optimal subwords and shared projections. CoRR arXiv:1909.11687 (2019)"}],"container-title":["Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","Collaborative Computing: Networking, Applications and Worksharing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-92638-0_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T13:10:46Z","timestamp":1641042646000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-92638-0_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030926373","9783030926380"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-92638-0_19","relation":{},"ISSN":["1867-8211","1867-822X"],"issn-type":[{"type":"print","value":"1867-8211"},{"type":"electronic","value":"1867-822X"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"1 January 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CollaborateCom","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Collaborative Computing: Networking, Applications and Worksharing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 October 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"colcom2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/collaboratecom.eai-conferences.org\/2021\/","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":"Confy +","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"206","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":"62","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":"7","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":"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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}