{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T08:35:38Z","timestamp":1743064538630,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819608461"},{"type":"electronic","value":"9789819608478"}],"license":[{"start":{"date-parts":[[2024,12,14]],"date-time":"2024-12-14T00:00:00Z","timestamp":1734134400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,14]],"date-time":"2024-12-14T00:00:00Z","timestamp":1734134400000},"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\/978-981-96-0847-8_11","type":"book-chapter","created":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T04:26:37Z","timestamp":1734063997000},"page":"155-169","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Balanced Knowledge Distillation with\u00a0Open-Domain Unlabeled Data for\u00a0Named Entity Recognition"],"prefix":"10.1007","author":[{"given":"Chenxiao","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjie","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiajun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjun","family":"Ke","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,14]]},"reference":[{"key":"11_CR1","unstructured":"Devlin, J., Chang, M.W., Lee, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"11_CR2","unstructured":"Michel, P., Levy, O., Neubig, G.: Are sixteen heads really better than one? Adv. Neural Inform. Process. Syst. 32 (2019)"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Srinivas, S., Babu, R.V.: Data-free parameter pruning for deep neural networks. arXiv preprint arXiv:1507.06149 (2015)","DOI":"10.5244\/C.29.31"},{"key":"11_CR4","unstructured":"Gong, Y., Liu, L., Yang, M.: Compressing deep convolutional networks using vector quantization. arXiv preprint arXiv:1412.6115 (2014)"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Strubell, E., Verga, P., Belanger, D.: Fast and accurate entity recognition with iterated dilated convolutions. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. Copenhagen, Denmark (2017)","DOI":"10.18653\/v1\/D17-1283"},{"key":"11_CR6","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"11_CR7","unstructured":"Tang, R., Lu, Y., Liu, L.: Distilling task-specific knowledge from bert into simple neural networks. arXiv preprint arXiv:1903.12136 (2019)"},{"key":"11_CR8","unstructured":"Tang, J., Shivanna, R., Zhao, Z.: Understanding and improving knowledge distillation. arXiv preprint arXiv:2002.03532 (2020)"},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"Marcheggiani, D., Arti\u2018eres, T.: An experimental comparison of active learning strategies for partially labeled sequences. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. Doha, Qatar (2014)","DOI":"10.3115\/v1\/D14-1097"},{"issue":"6","key":"11_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3457607","volume":"54","author":"N Mehrabi","year":"2021","unstructured":"Mehrabi, N., Morstatter, F., Saxena, N.: A survey on bias and fairness in machine learning. ACM Comput. Surv. 54(6), 1\u201335 (2021)","journal-title":"ACM Comput. Surv."},{"issue":"2","key":"11_CR11","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1137\/16M1080173","volume":"60","author":"L Bottou","year":"2018","unstructured":"Bottou, L., Curtis, F.E., Nocedal, J.: Optimization methods for large-scale machine learning. SIAM Rev. 60(2), 223\u2013311 (2018)","journal-title":"SIAM Rev."},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"11_CR13","unstructured":"Goyal, P., Doll\u00e1r, P., Girshick, R.: Accurate, large minibatch sgd: Training imagenet in 1 hour. arXiv preprint arXiv:1706.02677 (2017)"},{"key":"11_CR14","unstructured":"Huang, Z., Xu, W., Yu, K.: Bidirectional lstm-crf models for sequence tagging. arXiv preprint arXiv:1508.01991 (2015)"},{"key":"11_CR15","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1162\/tacl_a_00104","volume":"4","author":"JP Chiu","year":"2016","unstructured":"Chiu, J.P., Nichols, E.: Named entity recognition with bidirectional LSTM- CNNs. Trans. Assoc. Comput. Linguist. 4, 357\u2013370 (2016)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Ye, Z., Ling, Z.H.: Hybrid semi-Markov CRF for neural sequence labeling. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. Melbourne, Australia (2018)","DOI":"10.18653\/v1\/P18-2038"},{"key":"11_CR17","unstructured":"Ghaddar, A., Langlais, P.: Robust lexical features for improved neural network named-entity recognition. In: Proceedings of the 27th International Conference on Computational Linguistics. Santa Fe, New Mexico, USA (2018)"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Liu, T., Yao, J.G., Lin, C.Y.: Towards improving neural named entity recognition with gazetteers. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Florence, Italy (2019)","DOI":"10.18653\/v1\/P19-1524"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Zhou, X., Zhang, X., Tao, C.: Multi-grained knowledge distillation for named entity recognition. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Online (2021)","DOI":"10.18653\/v1\/2021.naacl-main.454"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Mukherjee, S., Hassan Awadallah, A.: XtremeDistil: Multi-stage distillation for massive multilingual models. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Online (2020)","DOI":"10.18653\/v1\/2020.acl-main.202"},{"key":"11_CR21","unstructured":"Merity, S., Xiong, C., Bradbury, J.: Pointer sentinel mixture models. arXiv preprint arXiv:1609.07843 (2016)"},{"key":"11_CR22","doi-asserted-by":"crossref","unstructured":"Conneau, A., Khandelwal, K., Goyal, N.: Unsupervised cross-lingual representation learning at scale. arXiv preprint arXiv:1911.02116 (2019)","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"Gururangan, S., Marasovi\u0107, A., Swayamdipta, S.: Don\u2019t stop pretraining: Adapt language models to domains and tasks. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Online (2020)","DOI":"10.18653\/v1\/2020.acl-main.740"},{"issue":"2","key":"11_CR24","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1023\/A:1009950525500","volume":"2","author":"M Mitra","year":"2000","unstructured":"Mitra, M., Chaudhuri, B.: Information retrieval from documents: A survey. Inf. Retrieval 2(2), 141\u2013163 (2000)","journal-title":"Inf. Retrieval"},{"issue":"10","key":"11_CR25","doi-asserted-by":"publisher","first-page":"1429","DOI":"10.1016\/S0893-6080(03)00138-2","volume":"16","author":"DR Wilson","year":"2003","unstructured":"Wilson, D.R., Martinez, T.R.: The general inefficiency of batch training for gradient descent learning. Neural Netw. 16(10), 1429\u20131451 (2003)","journal-title":"Neural Netw."},{"key":"11_CR26","unstructured":"Muhammad, I., Yan, Z.: Supervised machine learning approaches: A survey. J. Soft Comput. 5(3) (2015)"},{"key":"11_CR27","unstructured":"Liu, L., Jiang, H., He, P.: On the variance of the adaptive learning rate and beyond. arXiv preprint arXiv:1908.03265 (2019)"},{"key":"11_CR28","unstructured":"Sang, E.F., De Meulder, F.: Introduction to the conll-2003 shared task: Language-independent named entity recognition. arXiv preprint cs\/0306050 (2003)"},{"key":"11_CR29","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084 (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"11_CR30","unstructured":"Paszke, A., Gross, S., Massa, F.: Pytorch: An imperative style, high-performance deep learning library. Adv. Neural Inform. Process. Syst., 32 (2019)"},{"key":"11_CR31","unstructured":"Akbik, A., Bergmann, T., Blythe, D.: FLAIR: An easy-to-use framework for state-of-the-art NLP. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics. Minneapolis, Minnesota (2019)"},{"key":"11_CR32","unstructured":"Schweter, S., Akbik, A.: Flert: Document-level features for named entity recognition. arXiv preprint arXiv:2011.06993 (2020)"},{"key":"11_CR33","unstructured":"Mikolov, T., Grave, E., Bojanowski, P.: Advances in pre-training distributed word representations. arXiv preprint arXiv:1712.09405 (2017)"}],"container-title":["Lecture Notes in Computer Science","Advanced Data Mining and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0847-8_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T05:03:29Z","timestamp":1734066209000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0847-8_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,14]]},"ISBN":["9789819608461","9789819608478"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0847-8_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,14]]},"assertion":[{"value":"14 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ADMA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Advanced Data Mining and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sydney, NSW","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","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":"3 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"adma2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/adma2024.github.io\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}