{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:14:48Z","timestamp":1750220088188,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,3,18]],"date-time":"2022-03-18T00:00:00Z","timestamp":1647561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,3,18]]},"DOI":"10.1145\/3532213.3532240","type":"proceedings-article","created":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T13:29:18Z","timestamp":1657718958000},"page":"181-186","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Distil Knowledge from Natural Language"],"prefix":"10.1145","author":[{"given":"Yixun","family":"Liu","sequence":"first","affiliation":[{"name":"Physics, Sichuan University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuyi","family":"Zou","sequence":"additional","affiliation":[{"name":"Computer Science and Technology, Nanchang Hangkong University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Physics, Sichuan University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Advances in Neural Information Processing Systems","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky , Ilya Sutskever , and Geoffrey E Hinton . Imagenet classification with deep convolutional neural networks . In Advances in Neural Information Processing Systems , 2012 . Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems, 2012."},{"key":"e_1_3_2_1_2_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman . Very deep convolutional networks for large-scale image recognition. arXiv , 2015 . Karen Simonyan and Andrew Zisserman. Very deep convolutional networks for large-scale image recognition. arXiv, 2015."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/3172077.3172193"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_33"},{"key":"e_1_3_2_1_9_1","volume-title":"Wide residual networks. arXiv e-print","author":"Zagoruyko Sergey","year":"2016","unstructured":"Sergey Zagoruyko and Nikos Komodakis . Wide residual networks. arXiv e-print , 2016 . Sergey Zagoruyko and Nikos Komodakis. Wide residual networks. arXiv e-print, 2016."},{"key":"e_1_3_2_1_10_1","volume-title":"Distilling the knowledge in a neural network,\" arXiv preprint arXiv:1503.02531","author":"Hinton G.","year":"2015","unstructured":"G. Hinton , O. Vinyals , and J. Dean , \" Distilling the knowledge in a neural network,\" arXiv preprint arXiv:1503.02531 , 2015 . G. Hinton, O. Vinyals, and J. Dean, \"Distilling the knowledge in a neural network,\" arXiv preprint arXiv:1503.02531, 2015."},{"key":"e_1_3_2_1_11_1","volume-title":"Fitnets: Hints for thin deep nets. arXiv preprint arXiv:1412.6550","author":"Romero A.","year":"2014","unstructured":"A. Romero , N. Ballas , S. E. Kahou , A. Chassang , C. Gatta , and Y. Bengio . Fitnets: Hints for thin deep nets. arXiv preprint arXiv:1412.6550 , 2014 . A. Romero, N. Ballas, S. E. Kahou, A. Chassang, C. Gatta, and Y. Bengio. Fitnets: Hints for thin deep nets. arXiv preprint arXiv:1412.6550, 2014."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.754"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.121"},{"key":"e_1_3_2_1_14_1","volume-title":"Born again neural networks. arXiv preprint arXiv:1805.04770","author":"Furlanello T.","year":"2018","unstructured":"T. Furlanello , Z. C. Lipton , M. Tschannen , L. Itti , and A. Anandkumar . Born again neural networks. arXiv preprint arXiv:1805.04770 , 2018 . T. Furlanello, Z. C. Lipton, M. Tschannen, L. Itti, and A. Anandkumar. Born again neural networks. arXiv preprint arXiv:1805.04770, 2018."},{"key":"e_1_3_2_1_15_1","volume-title":"Large scale distributed neural network training through online distillation. arXiv preprint arXiv:1804.03235","author":"Anil R.","year":"2018","unstructured":"R. Anil , G. Pereyra , A. Passos , R. Ormandi , G. E. Dahl , and G. E. Hinton . Large scale distributed neural network training through online distillation. arXiv preprint arXiv:1804.03235 , 2018 . R. Anil, G. Pereyra, A. Passos, R. Ormandi, G. E. Dahl, and G. E. Hinton. Large scale distributed neural network training through online distillation. arXiv preprint arXiv:1804.03235, 2018."},{"key":"e_1_3_2_1_16_1","volume-title":"Improved knowledge distillation via teacher assistant: Bridging the gap between student and teacher. arXiv preprint arXiv:1902.03393","author":"Mirzadeh S.-I.","year":"2019","unstructured":"S.-I. Mirzadeh , M. Farajtabar , A. Li , and H. Ghasemzadeh . Improved knowledge distillation via teacher assistant: Bridging the gap between student and teacher. arXiv preprint arXiv:1902.03393 , 2019 . S.-I. Mirzadeh, M. Farajtabar, A. Li, and H. Ghasemzadeh. Improved knowledge distillation via teacher assistant: Bridging the gap between student and teacher. arXiv preprint arXiv:1902.03393, 2019."},{"key":"e_1_3_2_1_17_1","volume-title":"Efficient estimation of word representations in vector space,\" arXiv preprint arXiv:1301.3781","author":"Mikolov T.","year":"2013","unstructured":"T. Mikolov , K. Chen , G. Corrado , and J. Dean , \" Efficient estimation of word representations in vector space,\" arXiv preprint arXiv:1301.3781 , 2013 . T. Mikolov, K. Chen, G. Corrado, and J. Dean, \"Efficient estimation of word representations in vector space,\" arXiv preprint arXiv:1301.3781, 2013."},{"key":"e_1_3_2_1_18_1","first-page":"3111","volume-title":"Distributed representations of words and phrases and their compositionality,\" Advances in Neural Information Processing Systems","author":"Mikolov T.","unstructured":"T. Mikolov , I. Sutskever , K. Chen , G.S. Corrado , and J. Dean , \" Distributed representations of words and phrases and their compositionality,\" Advances in Neural Information Processing Systems pp. 3111 - 3119 . T. Mikolov, I. Sutskever, K. Chen, G.S. Corrado, and J. Dean, \"Distributed representations of words and phrases and their compositionality,\" Advances in Neural Information Processing Systems pp. 3111-3119."},{"key":"e_1_3_2_1_19_1","first-page":"746","volume-title":"Linguistic regularities in continuous space word representations,\" 2013 Conference of the North American","author":"Mikolov T.","unstructured":"T. Mikolov , W.-t. Yih , and G. Zweig , \" Linguistic regularities in continuous space word representations,\" 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics , pp. 746 - 751 . T. Mikolov, W.-t. Yih, and G. Zweig, \"Linguistic regularities in continuous space word representations,\" 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics, pp. 746-751."},{"key":"e_1_3_2_1_20_1","unstructured":"Jacob Devlin Ming-Wei Chang Kenton Lee and Kristina Toutanova. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv:1810.04805.  Jacob Devlin Ming-Wei Chang Kenton Lee and Kristina Toutanova. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv:1810.04805."},{"key":"e_1_3_2_1_21_1","unstructured":"Piotr Bojanowski Edouard Grave Armand Joulin and Tomas Mikolov. Enriching Word Vectors with Subword Information. arXiv:1607.04606.  Piotr Bojanowski Edouard Grave Armand Joulin and Tomas Mikolov. Enriching Word Vectors with Subword Information. arXiv:1607.04606."},{"key":"e_1_3_2_1_22_1","first-page":"W19","year":"2019","unstructured":"Jean Charbonnier and Christian Wartena. Predicting Word Concreteness and Imagery. W19 - 0415 , 2019 . Jean Charbonnier and Christian Wartena. Predicting Word Concreteness and Imagery. W19-0415, 2019.","journal-title":"Jean Charbonnier and Christian Wartena. Predicting Word Concreteness and Imagery."},{"key":"e_1_3_2_1_23_1","first-page":"535","volume-title":"ACM","author":"Bucilua C.","unstructured":"C. Bucilua , R. Caruana , and A. Niculescu-Mizil , \" Model compression,\" Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining , ACM , pp. 535 - 541 . C. Bucilua, R. Caruana, and A. Niculescu-Mizil, \"Model compression,\" Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining, ACM, pp. 535-541."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Rabinovich. E B. Sznajder A. Spector I. Shnayderman R. Aharonov D. Konopnicki and N. Slonim (2018 September). Learning Concept Abstractness Using Weak Supervision. ArXiv e-prints.  Rabinovich. E B. Sznajder A. Spector I. Shnayderman R. Aharonov D. Konopnicki and N. Slonim (2018 September). Learning Concept Abstractness Using Weak Supervision. ArXiv e-prints.","DOI":"10.18653\/v1\/D18-1522"},{"key":"e_1_3_2_1_25_1","first-page":"777","volume-title":"Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Ebert S., S.","year":"2016","unstructured":"Rothe, S., S. Ebert , and H. Sch\u00fctze ( 2016 ). Ultradense word embeddings by orthogonal transformation . In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies , pp. 767\u2013 777 . Rothe, S., S. Ebert, and H. Sch\u00fctze (2016). Ultradense word embeddings by orthogonal transformation. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 767\u2013777."},{"key":"e_1_3_2_1_26_1","volume-title":"Learning multiple layers of features from tiny images,\" University of Toronto","author":"Krizhevsky A.","year":"2009","unstructured":"A. Krizhevsky and G. Hinton , \" Learning multiple layers of features from tiny images,\" University of Toronto , Toronto, Technical Report TR- 2009 2009. A. Krizhevsky and G. Hinton, \"Learning multiple layers of features from tiny images,\" University of Toronto, Toronto, Technical Report TR-2009 2009."},{"key":"e_1_3_2_1_27_1","unstructured":"Princeton University. WordNet [DB\/OL] https:\/\/wordnet.princeton.edu\/.  Princeton University. WordNet [DB\/OL] https:\/\/wordnet.princeton.edu\/."},{"key":"e_1_3_2_1_28_1","volume-title":"International Conference on Natural Language Processing and Knowledge Engineering","author":"Dong Zhendong","year":"2003","unstructured":"Zhendong Dong and Qiang Dong . HowNet - a hybrid language and knowledge resource . International Conference on Natural Language Processing and Knowledge Engineering , 2003 . Zhendong Dong and Qiang Dong. HowNet - a hybrid language and knowledge resource. International Conference on Natural Language Processing and Knowledge Engineering, 2003."},{"key":"e_1_3_2_1_29_1","unstructured":"Extended Edition of Synonym Cilin by Social Computing and Information Retrieval Research Center of Harbin Institute of Technology [EB\/OL] ( 2015-09-13). http:\/\/www.datatang.com\/data\/42306\/.  Extended Edition of Synonym Cilin by Social Computing and Information Retrieval Research Center of Harbin Institute of Technology [EB\/OL] ( 2015-09-13). http:\/\/www.datatang.com\/data\/42306\/."},{"key":"e_1_3_2_1_30_1","volume-title":"Proc of the 10th International Conference on Research in Computational Linguistics","author":"Jiang","year":"1997","unstructured":"Jiang J and Conrath D. W . Semantic similarity based on corpus statistics and lexical taxonomy . Proc of the 10th International Conference on Research in Computational Linguistics , 1997 . Jiang J and Conrath D. W. Semantic similarity based on corpus statistics and lexical taxonomy. Proc of the 10th International Conference on Research in Computational Linguistics, 1997."},{"volume-title":"Proc of International Joint Conference on Artificial Intelligence","author":"P.","key":"e_1_3_2_1_31_1","unstructured":"Resnik. P. Using information content to evaluate semantic similarity in a Taxonomy . Proc of International Joint Conference on Artificial Intelligence , 1995: 448-453. Resnik. P. Using information content to evaluate semantic similarity in a Taxonomy. Proc of International Joint Conference on Artificial Intelligence, 1995: 448-453."},{"key":"e_1_3_2_1_32_1","unstructured":"Jianping Gou Baosheng Yu Stephen John Maybank Dacheng Tao. Knowledge Distillation: A Survey. arXiv:2006.05525.  Jianping Gou Baosheng Yu Stephen John Maybank Dacheng Tao. Knowledge Distillation: A Survey. arXiv:2006.05525."},{"volume-title":"Proc of International Joint Conference on Artificial Intelligence","author":"P.","key":"e_1_3_2_1_33_1","unstructured":"Resnik. P. Using information content to evaluate semantic similarity in a Taxonomy . Proc of International Joint Conference on Artificial Intelligence , 1995: 448-453. Resnik. P. Using information content to evaluate semantic similarity in a Taxonomy. Proc of International Joint Conference on Artificial Intelligence, 1995: 448-453."},{"key":"e_1_3_2_1_34_1","first-page":"1492","volume-title":"Aggregated residual transformations for deep neural networks,\" Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Xie S.","unstructured":"S. Xie , R. Girshick , P. Doll\u00e1r , Z. Tu , and K. He , \" Aggregated residual transformations for deep neural networks,\" Proceedings of the IEEE conference on computer vision and pattern recognition pp. 1492 - 1500 . S. Xie, R. Girshick, P. Doll\u00e1r, Z. Tu, and K. He, \"Aggregated residual transformations for deep neural networks,\" Proceedings of the IEEE conference on computer vision and pattern recognition pp. 1492-1500."},{"key":"e_1_3_2_1_35_1","first-page":"646","volume-title":"Deep networks with stochastic depth,\" European conference on computer vision","author":"Huang G.","unstructured":"G. Huang , Y. Sun , Z. Liu , D. Sedra , and K.Q. Weinberger , \" Deep networks with stochastic depth,\" European conference on computer vision , Springer , pp. 646 - 661 . G. Huang, Y. Sun, Z. Liu, D. Sedra, and K.Q. Weinberger, \"Deep networks with stochastic depth,\" European conference on computer vision, Springer, pp. 646-661."},{"key":"e_1_3_2_1_36_1","volume-title":"Deep mutual learning,\" arXiv e-print","author":"Zhang Y.","year":"2017","unstructured":"Y. Zhang , T. Xiang , T.M. Hospedales , and H. Lu , \" Deep mutual learning,\" arXiv e-print , 2017 . Y. Zhang, T. Xiang, T.M. Hospedales, and H. Lu, \"Deep mutual learning,\" arXiv e-print, 2017."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"}],"event":{"name":"ICCAI '22: 2022 8th International Conference on Computing and Artificial Intelligence","acronym":"ICCAI '22","location":"Tianjin China"},"container-title":["Proceedings of the 8th International Conference on Computing and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3532213.3532240","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3532213.3532240","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:09:43Z","timestamp":1750183783000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3532213.3532240"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,18]]},"references-count":37,"alternative-id":["10.1145\/3532213.3532240","10.1145\/3532213"],"URL":"https:\/\/doi.org\/10.1145\/3532213.3532240","relation":{},"subject":[],"published":{"date-parts":[[2022,3,18]]},"assertion":[{"value":"2022-07-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}