{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T18:55:39Z","timestamp":1742928939020,"version":"3.40.3"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031424298"},{"type":"electronic","value":"9783031424304"}],"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\/978-3-031-42430-4_31","type":"book-chapter","created":{"date-parts":[[2023,9,28]],"date-time":"2023-09-28T15:03:54Z","timestamp":1695913434000},"page":"376-386","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Mitigating Catastrophic Forgetting in\u00a0Neural Machine Translation Through Teacher-Student Distillation with\u00a0Attention Mechanism"],"prefix":"10.1007","author":[{"given":"Quynh-Trang Pham","family":"Thi","sequence":"first","affiliation":[]},{"given":"Ngoc-Huyen","family":"Ngo","sequence":"additional","affiliation":[]},{"given":"Anh-Duc","family":"Nguyen","sequence":"additional","affiliation":[]},{"given":"Duc-Trong","family":"Le","sequence":"additional","affiliation":[]},{"given":"Tri-Thanh","family":"Nguyen","sequence":"additional","affiliation":[]},{"given":"Quang-Thuy","family":"Ha","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,9,29]]},"reference":[{"key":"31_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/3-540-49430-8_2","volume-title":"Neural Networks: Tricks of the Trade","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Orr, G.B., M\u00fcller, K.-R.: Efficient BackProp. In: Orr, G.B., M\u00fcller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 1524, pp. 9\u201350. Springer, Heidelberg (1998). https:\/\/doi.org\/10.1007\/3-540-49430-8_2"},{"key":"31_CR2","unstructured":"Anil, R., Pereyra, G., Passos, A., Ormandi, R., Dahl, G.E., Hinton, G.E.: Large scale distributed neural network training through online distillation. In: 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings. OpenReview.net (2018)"},{"key":"31_CR3","unstructured":"Xu, L., Zhu, X., Gong, S.: Knowledge distillation by on the-fly native ensemble. In: Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R., (eds.) Advances in Neural Information Processing Systems, vol. 31. Curran Associates Inc (2018)"},{"key":"31_CR4","doi-asserted-by":"crossref","unstructured":"Shao, C., Feng, Y.: Overcoming catastrophic forgetting beyond continual learning: balanced training for neural machine translation. In: Muresan, S., Nakov, P., Villavicencio, A. (eds.) Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2023\u20132036. ACL 2022, Dublin, Ireland, 22\u201327 May 2022. Association for Computational Linguistics (2022)","DOI":"10.18653\/v1\/2022.acl-long.143"},{"key":"31_CR5","unstructured":"Song, G., Chai, W.: Collaborative learning for deep neural networks. In: Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 31. Curran Associates Inc (2018)"},{"key":"31_CR6","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. CoRR abs\/1503.02531 (2015)"},{"issue":"6","key":"31_CR7","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. Vision 129(6), 1789\u20131819 (2021). https:\/\/doi.org\/10.1007\/s11263-021-01453-z","journal-title":"Int. J. Comput. Vision"},{"key":"31_CR8","unstructured":"Gupta, M., Agrawal, P.: Compression of deep learning models for text: a survey. CoRR abs\/2008.05221 (2020)"},{"key":"31_CR9","doi-asserted-by":"crossref","unstructured":"Kim, Y., Rush, A.M.: Sequence-level knowledge distillation. CoRR abs\/1606.07947 (2016)","DOI":"10.18653\/v1\/D16-1139"},{"key":"31_CR10","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Xiang, T., Hospedales, T.M., Lu, H.: Deep mutual learning. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4320\u20134328 (2018)","DOI":"10.1109\/CVPR.2018.00454"},{"key":"31_CR11","unstructured":"Chen, D., Mei, J.P., Wang, C., Feng, Y., Chen, C.: Online knowledge distillation with diverse peers. CoRR abs\/1912.00350 (2019)"},{"key":"31_CR12","doi-asserted-by":"crossref","unstructured":"Wu, G., Gong, S.: Peer collaborative learning for online knowledge distillation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 12, pp. 10302\u201310310 (2021)","DOI":"10.1609\/aaai.v35i12.17234"},{"key":"31_CR13","unstructured":"Furlanello, T., Lipton, Z., Tschannen, M., Itti, L., Anandkumar, A.: Born again neural networks. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning, vol. 80, pp. 1607\u20131616. Proceedings of Machine Learning Research. PMLR (2018)"},{"key":"31_CR14","doi-asserted-by":"crossref","unstructured":"Wei, H R., Huang, S., Wang, R., Dai, X., Chen, J.: Online distilling from checkpoints for neural machine translation. 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), pp. 1932\u20131941. Minneapolis, Minnesota: Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/N19-1192"},{"key":"31_CR15","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: Bengio, Y., LeCun, Y. (ed.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7\u20139 May 2015, Conference Track Proceedings (2015)"},{"key":"31_CR16","unstructured":"Luong, M.-T., Manning, C.: Stanford neural machine translation systems for spoken language domains. In: Proceedings of the 12th International Workshop on Spoken Language Translation: Evaluation Campaign. Da Nang, Vietnam (2015)"},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Post, M.: A call for clarity in reporting BLEU scores. In: Proceedings of the Third Conference on Machine Translation: Research Papers. Brussels, Belgium: Association for Computational Linguistics, pp. 186\u2013191 (2018)","DOI":"10.18653\/v1\/W18-6319"},{"key":"31_CR18","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (ed.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7\u20139 May 2015, Conference Track Proceedings (2015)"},{"key":"31_CR19","unstructured":"Vaswani, A, et al.: Attention is all you need. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30. Curran Associates Inc (2017)"},{"key":"31_CR20","doi-asserted-by":"crossref","unstructured":"Chuang, Y.-S., Su, S.-Y., Chen, Y.-N.: Lifelong language knowledge distillation. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics, pp. 2914\u20132924 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.233"}],"container-title":["Communications in Computer and Information Science","Recent Challenges in Intelligent Information and Database Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-42430-4_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T13:34:42Z","timestamp":1730208882000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-42430-4_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031424298","9783031424304"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-42430-4_31","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"29 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACIIDS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Intelligent Information and Database Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Phuket","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thailand","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":"24 July 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aciids2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aciids.pwr.edu.pl\/2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"224","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":"50","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":"22% - 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":"3,87","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":"2,82","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)"}}]}}