{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T16:25:17Z","timestamp":1781281517907,"version":"3.54.1"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030323806","type":"print"},{"value":"9783030323813","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-32381-3_16","type":"book-chapter","created":{"date-parts":[[2019,10,14]],"date-time":"2019-10-14T11:17:59Z","timestamp":1571051879000},"page":"194-206","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":981,"title":["How to Fine-Tune BERT for Text Classification?"],"prefix":"10.1007","author":[{"given":"Chi","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xipeng","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yige","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuanjing","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,10,13]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Caruana, R.: Multitask learning: a knowledge-based source of inductive bias. In: Proceedings of the Tenth International Conference on Machine Learning (1993)","DOI":"10.1016\/B978-1-55860-307-3.50012-5"},{"key":"16_CR2","unstructured":"Chen, Z., Badrinarayanan, V., Lee, C.Y., Rabinovich, A.: GradNorm: gradient normalization for adaptive loss balancing in deep multitask networks. arXiv preprint arXiv:1711.02257 (2017)"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Collobert, R., Weston, J.: A unified architecture for natural language processing: deep neural networks with multitask learning. In: Proceedings of the 25th International Conference on Machine Learning, pp. 160\u2013167. ACM (2008)","DOI":"10.1145\/1390156.1390177"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Conneau, A., Kiela, D., Schwenk, H., Barrault, L., Bordes, A.: Supervised learning of universal sentence representations from natural language inference data. arXiv preprint arXiv:1705.02364 (2017)","DOI":"10.18653\/v1\/D17-1070"},{"key":"16_CR5","unstructured":"Dai, A.M., Le, Q.V.: Semi-supervised sequence learning. In: Advances in Neural Information Processing Systems, pp. 3079\u20133087 (2015)"},{"key":"16_CR6","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Howard, J., Ruder, S.: Universal language model fine-tuning for text classification. arXiv preprint arXiv:1801.06146 (2018)","DOI":"10.18653\/v1\/P18-1031"},{"key":"16_CR8","unstructured":"Kiros, R., et al.: Skip-thought vectors. In: Advances in Neural Information Processing Systems, pp. 3294\u20133302 (2015)"},{"key":"16_CR9","unstructured":"Le, Q., Mikolov, T.: Distributed representations of sentences and documents. In: International Conference on Machine Learning, pp. 1188\u20131196 (2014)"},{"key":"16_CR10","unstructured":"Lin, Z., et al.: A structured self-attentive sentence embedding. arXiv preprint arXiv:1703.03130 (2017)"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Liu, L., et al.: Empower sequence labeling with task-aware neural language model. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12006"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Liu, X., Gao, J., He, X., Deng, L., Duh, K., Wang, Y.Y.: Representation learning using multi-task deep neural networks for semantic classification and information retrieval (2015)","DOI":"10.3115\/v1\/N15-1092"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Liu, X., He, P., Chen, W., Gao, J.: Multi-task deep neural networks for natural language understanding. arXiv preprint arXiv:1901.11504 (2019)","DOI":"10.18653\/v1\/P19-1441"},{"key":"16_CR14","unstructured":"Logeswaran, L., Lee, H.: An efficient framework for learning sentence representations. arXiv preprint arXiv:1803.02893 (2018)"},{"key":"16_CR15","unstructured":"Maas, A.L., Daly, R.E., Pham, P.T., Huang, D., Ng, A.Y., Potts, C.: Learning word vectors for sentiment analysis. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies-Volume 1, pp. 142\u2013150. Association for Computational Linguistics (2011)"},{"key":"16_CR16","unstructured":"McCann, B., Bradbury, J., Xiong, C., Socher, R.: Learned in translation: contextualized word vectors. In: Advances in Neural Information Processing Systems, pp. 6294\u20136305 (2017)"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"McCloskey, M., Cohen, N.J.: Catastrophic interference in connectionist networks: the sequential learning problem. In: Psychology of Learning and Motivation, vol. 24, pp. 109\u2013165. Elsevier (1989)","DOI":"10.1016\/S0079-7421(08)60536-8"},{"key":"16_CR18","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, pp. 3111\u20133119 (2013)"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.: Glove: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"16_CR20","unstructured":"Peters, M.E., et al.: Deep contextualized word representations. arXiv preprint arXiv:1802.05365 (2018)"},{"key":"16_CR21","unstructured":"Qiao, C., et al.: A new method of region embedding for text classification. In: International Conference on Learning Representations (2018)"},{"key":"16_CR22","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding by generative pre-training (2018). https:\/\/s3-us-west-2.amazonaws.com\/openai-assets\/research-covers\/languageunsupervised\/languageunderstandingpaper.pdf"},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Rei, M.: Semi-supervised multitask learning for sequence labeling. arXiv preprint arXiv:1704.07156 (2017)","DOI":"10.18653\/v1\/P17-1194"},{"key":"16_CR24","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Voorhees, E.M., Tice, D.M.: The TREC-8 question answering track evaluation. In: TREC, vol. 1999, p. 82. Citeseer (1999)","DOI":"10.6028\/NIST.SP.500-246.qa-overview"},{"key":"16_CR26","unstructured":"Wu, Y., et al.: Google\u2019s neural machine translation system: Bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144 (2016)"},{"key":"16_CR27","unstructured":"Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks? In: Advances in Neural Information Processing Systems, pp. 3320\u20133328 (2014)"},{"key":"16_CR28","unstructured":"Zhang, X., Zhao, J., LeCun, Y.: Character-level convolutional networks for text classification. In: Advances in Neural Information Processing Systems, pp. 649\u2013657 (2015)"}],"container-title":["Lecture Notes in Computer Science","Chinese Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-32381-3_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,25]],"date-time":"2024-07-25T00:00:37Z","timestamp":1721865637000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-32381-3_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030323806","9783030323813"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-32381-3_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"13 October 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CCL","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China National Conference on Chinese Computational Linguistics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kunming","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":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cncl2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.cips-cl.org\/static\/CCL2019\/en\/callfor.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}