{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T22:41:47Z","timestamp":1743028907011,"version":"3.40.3"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031466601"},{"type":"electronic","value":"9783031466618"}],"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\/978-3-031-46661-8_13","type":"book-chapter","created":{"date-parts":[[2023,11,4]],"date-time":"2023-11-04T13:02:29Z","timestamp":1699102949000},"page":"185-199","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["FastNER: Speeding up\u00a0Inferences for\u00a0Named Entity Recognition Tasks"],"prefix":"10.1007","author":[{"given":"Yuming","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangxiang","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoling","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,5]]},"reference":[{"key":"13_CR1","unstructured":"Bolukbasi, T., Wang, J., Dekel, O., Saligrama, V.: Adaptive neural networks for efficient inference. In: ICML (2017)"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Cui, Y., Che, W., Liu, T., Qin, B., Wang, S., Hu, G.: Revisiting pre-trained models for Chinese natural language processing. arXiv:abs\/2004.13922 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.58"},{"key":"13_CR3","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":"13_CR4","doi-asserted-by":"crossref","unstructured":"Gao, X., Zhu, W., Gao, J., Yin, C.: F-PABEE: flexible-patience-based early exiting for single-label and multi-label text classification tasks. In: ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10095864"},{"key":"13_CR5","unstructured":"Hendrycks, D., Gimpel, K.: Bridging nonlinearities and stochastic regularizers with gaussian error linear units. arXiv:abs\/1606.08415 (2016)"},{"key":"13_CR6","unstructured":"Huang, G., Chen, D., Li, T., Wu, F., Maaten, L.V.D., Weinberger, K.Q.: Multi-scale dense convolutional networks for efficient prediction. arXiv:abs\/1703.09844 (2017)"},{"key":"13_CR7","unstructured":"Huang, Z., Xu, W., Yu, K.: Bidirectional LSTM-CRF models for sequence tagging. arXiv:abs\/1508.01991 (2015)"},{"key":"13_CR8","unstructured":"Kaya, Y., Hong, S., Dumitras, T.: Shallow-deep networks: understanding and mitigating network overthinking. In: ICML (2019)"},{"key":"13_CR9","doi-asserted-by":"publisher","unstructured":"Kim, J.D., Ohta, T., Tateisi, Y., Tsujii, J.: GENIA corpus-a semantically annotated corpus for bio-textmining. Bioinformatics (Oxford, England) 19(Suppl. 1), i180-2 (2003). https:\/\/doi.org\/10.1093\/bioinformatics\/btg1023","DOI":"10.1093\/bioinformatics\/btg1023"},{"key":"13_CR10","unstructured":"Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: ALBERT: a lite BERT for self-supervised learning of language representations. arXiv:abs\/1909.11942 (2020)"},{"key":"13_CR11","unstructured":"Levow, G.A.: The third international Chinese language processing bakeoff: word segmentation and named entity recognition. In: Proceedings of the Fifth SIGHAN Workshop on Chinese Language Processing, pp. 108\u2013117. Association for Computational Linguistics, Sydney, Australia, July 2006. https:\/\/aclanthology.org\/W06-0115"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Li, H., Zhang, H., Qi, X., Yang, R., Huang, G.: Improved techniques for training adaptive deep networks. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1891\u20131900 (2019)","DOI":"10.1109\/ICCV.2019.00198"},{"key":"13_CR13","doi-asserted-by":"publisher","unstructured":"Li, X., et al.: Pingan smart health and SJTU at COIN - shared task: utilizing pre-trained language models and common-sense knowledge in machine reading tasks. In: Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing, pp. 93\u201398. Association for Computational Linguistics, Hong Kong, China, November 2019. https:\/\/doi.org\/10.18653\/v1\/D19-6011, https:\/\/aclanthology.org\/D19-6011","DOI":"10.18653\/v1\/D19-6011"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Liu, W., Zhou, P., Zhao, Z., Wang, Z., Deng, H., Ju, Q.: FastBERT: a self-distilling BERT with adaptive inference time. arXiv:abs\/2004.02178 (2020)","DOI":"10.18653\/v1\/2020.acl-main.537"},{"issue":"8","key":"13_CR15","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)","journal-title":"OpenAI Blog"},{"key":"13_CR16","doi-asserted-by":"publisher","unstructured":"Schwartz, R., Stanovsky, G., Swayamdipta, S., Dodge, J., Smith, N.A.: The right tool for the job: matching model and instance complexities. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 6640\u20136651. Association for Computational Linguistics, Online, July 2020. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.593, https:\/\/aclanthology.org\/2020.acl-main.593","DOI":"10.18653\/v1\/2020.acl-main.593"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Sun, T., et al.: Learning sparse sharing architectures for multiple tasks. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i05.6424"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Teerapittayanon, S., McDanel, B., Kung, H.T.: BranchyNet: fast inference via early exiting from deep neural networks. In: 2016 23rd International Conference on Pattern Recognition (ICPR), pp. 2464\u20132469 (2016)","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Tjong Kim Sang, E.F., De Meulder, F.: Introduction to the CoNLL-2003 shared task: language-independent named entity recognition. In: Proceedings of the Seventh Conference on Natural Language Learning at HLT-NAACL 2003, pp. 142\u2013147 (2003). https:\/\/aclanthology.org\/W03-0419","DOI":"10.3115\/1119176.1119195"},{"key":"13_CR20","unstructured":"Vaswani, A., et al.: Attention is all you need. arXiv:abs\/1706.03762 (2017)"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.R.: GLUE: a multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461 (2018)","DOI":"10.18653\/v1\/W18-5446"},{"key":"13_CR22","unstructured":"Wolf, T., et al.: Transformers: state-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38\u201345. Association for Computational Linguistics, Online, October 2020. www.aclweb.org\/anthology\/2020.emnlp-demos.6"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Xin, J., Tang, R., Lee, J., Yu, Y., Lin, J.: DeeBERT: dynamic early exiting for accelerating BERT inference. arXiv preprint arXiv:2004.12993 (2020)","DOI":"10.18653\/v1\/2020.acl-main.204"},{"key":"13_CR24","doi-asserted-by":"crossref","unstructured":"Xin, J., Tang, R., Yu, Y., Lin, J.: BERxiT: early exiting for BERT with better fine-tuning and extension to regression. In: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pp. 91\u2013104 (2021)","DOI":"10.18653\/v1\/2021.eacl-main.8"},{"key":"13_CR25","unstructured":"Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R., Le, Q.V.: XLNet: generalized autoregressive pretraining for language understanding. In: NeurIPS (2019)"},{"key":"13_CR26","doi-asserted-by":"publisher","unstructured":"Yu, J., Bohnet, B., Poesio, M.: Named entity recognition as dependency parsing. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 6470\u20136476. Association for Computational Linguistics, Online, July 2020. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.577, https:\/\/aclanthology.org\/2020.acl-main.577","DOI":"10.18653\/v1\/2020.acl-main.577"},{"key":"13_CR27","doi-asserted-by":"publisher","unstructured":"Zhang, Z., Zhu, W., Zhang, J., Wang, P., Jin, R., Chung, T.S.: PCEE-BERT: accelerating BERT inference via patient and confident early exiting. In: Findings of the Association for Computational Linguistics: NAACL 2022, pp. 327\u2013338. Association for Computational Linguistics, Seattle, United States, July 2022. https:\/\/doi.org\/10.18653\/v1\/2022.findings-naacl.25, https:\/\/aclanthology.org\/2022.findings-naacl.25","DOI":"10.18653\/v1\/2022.findings-naacl.25"},{"key":"13_CR28","unstructured":"Zhou, W., Xu, C., Ge, T., McAuley, J., Xu, K., Wei, F.: BERT loses patience: fast and robust inference with early exit. arXiv:abs\/2006.04152 (2020)"},{"key":"13_CR29","doi-asserted-by":"crossref","unstructured":"Zhu, W., Wang, P., Ni, Y., Xie, G., Wang, X.: BADGE: speeding up BERT inference after deployment via block-wise bypasses and divergence-based early exiting. In: ACL Industry (2023)","DOI":"10.18653\/v1\/2023.acl-industry.48"},{"key":"13_CR30","doi-asserted-by":"crossref","unstructured":"Zhu, W., Wang, X., Ni, Y., Xie, G.: GAML-BERT: improving BERT early exiting by gradient aligned mutual learning. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 3033\u20133044. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic, November 2021. https:\/\/aclanthology.org\/2021.emnlp-main.242","DOI":"10.18653\/v1\/2021.emnlp-main.242"},{"key":"13_CR31","doi-asserted-by":"publisher","unstructured":"Zhu, W., et al.: PANLP at MEDIQA 2019: pre-trained language models, transfer learning and knowledge distillation. In: Proceedings of the 18th BioNLP Workshop and Shared Task, pp. 380\u2013388. Association for Computational Linguistics, Florence, Italy, August 2019. https:\/\/doi.org\/10.18653\/v1\/W19-5040, https:\/\/aclanthology.org\/W19-5040","DOI":"10.18653\/v1\/W19-5040"}],"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\/978-3-031-46661-8_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,4]],"date-time":"2023-11-04T13:03:39Z","timestamp":1699103019000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-46661-8_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031466601","9783031466618"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-46661-8_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"5 November 2023","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":"Shenyang","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"adma2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/adma2023.uqcloud.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes. Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"503","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":"216","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":"43% - 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":"2.97","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":"3.77","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}