{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T04:15:07Z","timestamp":1730434507218,"version":"3.28.0"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819794300","type":"print"},{"value":"9789819794317","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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":[[2025]]},"DOI":"10.1007\/978-981-97-9431-7_19","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T14:03:04Z","timestamp":1730383384000},"page":"245-257","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Model-Agnostic Knowledge Distillation Between Heterogeneous Models"],"prefix":"10.1007","author":[{"given":"Jiaxin","family":"Shen","sequence":"first","affiliation":[]},{"given":"Yanyao","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Yong","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Yufeng","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Wenjuan","family":"Han","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"19_CR1","unstructured":"Abnar, S., Dehghani, M., Zuidema, W.: Transferring inductive biases through knowledge distillation. arXiv preprint arXiv:2006.00555 (2020)"},{"key":"19_CR2","unstructured":"Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: FitNets: hints for thin deep nets. arXiv preprint. arXiv:1412.6550 (2014)"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Wu, Y., Rezagholizadeh, M., Ghaddar, A., Haidar, M.A., Ghodsi, A.: Universal-KD: attention-based output-grounded intermediate layer knowledge distillation. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 7649\u20137661. Association for Computational Linguistics, Punta Cana, Dominican Republic (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.603"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Liu, C., Tao, C., Feng, J., Zhao, D.: Multi-granularity structural knowledge distillation for language model compression. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1001\u20131011 (2022)","DOI":"10.18653\/v1\/2022.acl-long.71"},{"issue":"16","key":"19_CR5","first-page":"18056","volume":"38","author":"L Ge","year":"2024","unstructured":"Ge, L., Hu, C., Ma, G., Liu, J., Zhang, H.: Discrepancy and uncertainty aware denoising knowledge distillation for zero-shot cross-lingual named entity recognition. Proc. AAAI Conf. Artif. Intell. 38(16), 18056\u201318064 (2024)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"Tan, S., et al.: Are intermediate layers and labels really necessary? a general language model distillation method. In: Findings of the Association for Computational Linguistics: ACL 2023, pp. 9678\u20139696. Association for Computational Linguistics, Toronto, Canada (2023)","DOI":"10.18653\/v1\/2023.findings-acl.614"},{"key":"19_CR7","doi-asserted-by":"crossref","unstructured":"Awasthi, A., Sarawagi, S., Goyal, R., Ghosh, S., Piratla, V.: Parallel iterative edit models for local sequence transduction. 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), pp. 4260\u20134270 (2019)","DOI":"10.18653\/v1\/D19-1435"},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"Bryant, C., Felice, M., Andersen, \u00d8.E., Briscoe, T.: The BEA-2019 shared task on grammatical error correction. In: Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications, pp. 52\u201375 (2019)","DOI":"10.18653\/v1\/W19-4406"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"Buchholz, S., Marsi, E.: CoNLL-X shared task on multilingual dependency parsing. In: Proceedings of the CoNLL, pp. 149\u2013164 (2006)","DOI":"10.3115\/1596276.1596305"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Chen, D., Manning, C.D: A fast and accurate dependency parser using neural networks. In: Proceedings of the EMNLP, pp. 740\u2013750 (2014)","DOI":"10.3115\/v1\/D14-1082"},{"key":"19_CR11","unstructured":"Dahlmeier, D., Ng, H.T., Wu, S.M.: Building a large annotated corpus of learner English: the NUS corpus of learner English. In: Proceedings of the Eighth Workshop on Innovative Use of NLP for Building Educational Applications, pp. 22\u201331 (2013)"},{"key":"19_CR12","unstructured":"Denil, M., Shakibi, B., Dinh, L., Ranzato, M.A., de\u00a0Freitas, N.: Predicting parameters in deep learning. In: Advances in Neural Information Processing Systems (2013)"},{"key":"19_CR13","unstructured":"Dozat, T., Manning, C.D.: Deep biaffine attention for neural dependency parsing. In: Proceedings of the ICLR (2017)"},{"key":"19_CR14","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: NIPS Deep Learning Workshop (2015)"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Marcus, M., et al.: The penn treebank: annotating predicate argument structure. In: Proceedings of the Workshop on Human Language Technology, pp. 114\u2013119 (1994)","DOI":"10.3115\/1075812.1075835"},{"key":"19_CR16","unstructured":"Miyato, T., Dai, A.M., Goodfellow, I.: Adversarial training methods for semi-supervised text classification. In: Proceedings of the ICLR (2017"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"Han, W., Zhang, L., Jiang, Y., Tu, K.: Adversarial attack and defense of structured prediction models. In: Proceedings of the EMNLP, pp. 2327\u20132338 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.182"},{"key":"19_CR18","unstructured":"Mizumoto, T., Komachi, M., Nagata, M., Matsumoto, Y.: Mining revision log of language learning SNS for automated Japanese error correction of second language learners. In: Proceedings of the IJCNLP, pp. 147\u2013155 (2011)"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Omelianchuk, K., Atrasevych, V., Chernodub, A., Skurzhanskyi, O.: GECToR \u2013 grammatical error correction: tag, not rewrite. In: Proceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications, pp. 163\u2013170 (2020)","DOI":"10.18653\/v1\/2020.bea-1.16"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Papernot, N., McDaniel, P., Swami, A., Harang, R.: Crafting adversarial input sequences for recurrent neural networks. In: MILCOM 2016-2016 IEEE Military Communications Conference, pp. 49\u201354 (2016)","DOI":"10.1109\/MILCOM.2016.7795300"},{"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 EMNLP-IJCNLP, pp. 4314\u20134323 (2019)","DOI":"10.18653\/v1\/D19-1441"},{"key":"19_CR22","unstructured":"Zagoruyko, S., Komodakis, N.: Paying more attention to attention: improving the performance of convolutional neural networks via attention transfer. arXiv preprintarXiv:1612.03928 (2016)"},{"key":"19_CR23","doi-asserted-by":"crossref","unstructured":"Sun, X., Ge, T., Wei, F., Wang, H.: Instantaneous grammatical error correction with shallow aggressive decoding. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 5937\u20135947 (2021)","DOI":"10.18653\/v1\/2021.acl-long.462"},{"key":"19_CR24","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"19_CR25","doi-asserted-by":"crossref","unstructured":"Wang, Y., Huang, M., Zhu, X., Zhao, L.: Attention-based LSTM for aspect-level sentiment classification. In: Proceedings of the EMNLP, pp. 606\u2013615 (2016)","DOI":"10.18653\/v1\/D16-1058"},{"issue":"3\u20134","key":"19_CR26","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/BF00992696","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3\u20134), 229\u2013256 (1992)","journal-title":"Mach. Learn."},{"issue":"3","key":"19_CR27","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1080\/08957347.2018.1464447","volume":"31","author":"H Yannakoudakis","year":"2018","unstructured":"Yannakoudakis, H., Andersen, \u00d8.E., Geranpayeh, A., Briscoe, T., Nicholls, D.: Developing an automated writing placement system for ESL learners. Appl. Measur. Educ. 31(3), 251\u2013267 (2018)","journal-title":"Appl. Measur. Educ."},{"key":"19_CR28","unstructured":"Yannakoudakis, H., Briscoe, T., Medlock, B.: A new dataset and method for automatically grading ESOL texts. In: Proceedings of the ACL, pp. 180\u2013189 (2011)"},{"key":"19_CR29","unstructured":"Zhang, X., Zhao, J., LeCun, Y.: Character-level convolutional networks for text classification. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"}],"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\/978-981-97-9431-7_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T14:31:56Z","timestamp":1730385116000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-9431-7_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9789819794300","9789819794317"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-9431-7_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 2024","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":"Hangzhou","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2024\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}