{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T19:13:39Z","timestamp":1742930019323,"version":"3.40.3"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031677502"},{"type":"electronic","value":"9783031677519"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-67751-9_5","type":"book-chapter","created":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T19:02:53Z","timestamp":1722538973000},"page":"52-65","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Stochastic Featurization for\u00a0Active Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1241-1881","authenticated-orcid":false,"given":"Linh","family":"Le","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minh-Tien","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Khai Phan","family":"Tran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Genghong","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhang","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guido","family":"Zuccon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gianluca","family":"Demartini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,1]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Abe, N., Zadrozny, B., Langford, J.: Outlier detection by active learning. In: SIGKDD (2006)","DOI":"10.1145\/1150402.1150459"},{"key":"5_CR2","unstructured":"Ash, J.T., Zhang, C., Krishnamurthy, A., Langford, J., Agarwal, A.: Deep batch active learning by diverse, uncertain gradient lower bounds. In: ICLR (2020)"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Beltagy, I., Lo, K., Cohan, A.: SciBERT: a pretrained language model for scientific text. In: EMNLP-IJCNLP (2019)","DOI":"10.18653\/v1\/D19-1371"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Beluch, W.H., Genewein, T., N\u00fcrnberger, A., K\u00f6hler, J.M.: The power of ensembles for active learning in image classification. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00976"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Benjamini, Y., Hochberg, Y.: Controlling the false discovery rate - a practical and powerful approach to multiple testing. J. Roy. Stat. Soc. B (1995)","DOI":"10.1111\/j.2517-6161.1995.tb02031.x"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Benjamini, Y., Yekutieli, D.: The control of the false discovery rate in multiple testing under dependency. Ann. Stat. (2001)","DOI":"10.1214\/aos\/1013699998"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Boros, E., et al.: Alleviating digitization errors in named entity recognition for historical documents. In: CoNLL (2020)","DOI":"10.18653\/v1\/2020.conll-1.35"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Culotta, A., McCallum, A.: Reducing labeling effort for structured prediction tasks. In: AAAI (2005)","DOI":"10.21236\/ADA440382"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Dagan, I., Engelson, S.P.: Committee-based sampling for training probabilistic classifiers. In: Machine Learning Proceedings (1995)","DOI":"10.1016\/B978-1-55860-377-6.50027-X"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Dernoncourt, F., Lee, J.Y.: PubMed 200k RCT: a dataset for sequential sentence classification in medical abstracts. In: IJCNLP (2017)","DOI":"10.18653\/v1\/E17-2110"},{"key":"5_CR11","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL (2019)"},{"key":"5_CR12","unstructured":"Gal, Y., Islam1, R., Ghahramani, Z.: Deep Bayesian active learning with image data. In: ICML (2017)"},{"key":"5_CR13","unstructured":"Gissin, D., Shalev-Shwartz, S.: Discriminative active learning. In: ICLR (2019)"},{"key":"5_CR14","unstructured":"Hu, P., Lipton, Z., Anandkumar, A., Ramanan, D.: Active learning with partial feedback. In: ICLR (2019)"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Kann, K., Cho, K., Bowman, S.R.: Towards realistic practices in low-resource natural language processing: the development set. In: EMNLP-IJCNLP (2019)","DOI":"10.18653\/v1\/D19-1329"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Kholghi, M., Vine, L.D., Sitbon, L., Zuccon, G., Nguyen, A.N.: Clinical information extraction using small data: an active learning approach based on sequence representations and word embeddings. JASIST (2017)","DOI":"10.1002\/asi.23936"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Linh, L., Nguyen, M.T., Zuccon, G., Demartini, G.: Loss-based active learning for named entity recognition. In: IJCNN (2021)","DOI":"10.1109\/IJCNN52387.2021.9533675"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Generative adversarial active learning for unsupervised outlier detection. In: TKDE (2019)","DOI":"10.1109\/TKDE.2019.2905606"},{"key":"5_CR19","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Mao, X., Koopman, B., Zuccon, G.: A reproducibility study of goldilocks: just-right tuning of BERT for TAR. In: ECIR, vol. 14611, pp. 132\u2013146 (2024)","DOI":"10.1007\/978-3-031-56066-8_13"},{"key":"5_CR21","doi-asserted-by":"crossref","unstructured":"Margatina, K., Vernikos, G., Barrault, L., Aletras, N.: Active learning by acquiring contrastive examples. In: EMNLP (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.51"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Michalopoulos, G., Wang, Y., Kaka, H., Chen, H., Wong, A.: UmlsBERT: clinical domain knowledge augmentation of contextual embeddings using the unified medical language system metathesaurus. In: NAACL (2021)","DOI":"10.18653\/v1\/2021.naacl-main.139"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Nguyen, D.H.M., Patrick, J.D.: Supervised machine learning and active learning in classification of radiology reports. JAMIA (2014)","DOI":"10.1136\/amiajnl-2013-002516"},{"key":"5_CR24","doi-asserted-by":"crossref","unstructured":"Nguyen, H.T., Smeulders, A.: Active learning using pre-clustering. In: ICML (2004)","DOI":"10.1145\/1015330.1015349"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Parvaneh, A., Abbasnejad, E., Teney, D., Haffari, R., van\u00a0den Hengel, A., Shi, J.Q.: Active learning by feature mixing. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01192"},{"key":"5_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2023.104576","volume":"149","author":"A Peluso","year":"2024","unstructured":"Peluso, A., et al.: Deep learning uncertainty quantification for clinical text classification. J. Biomed. Inf. 149, 104576 (2024)","journal-title":"J. Biomed. Inf."},{"key":"5_CR27","doi-asserted-by":"crossref","unstructured":"Prokhorov, V., Shareghi, E., Li, Y., Pilehvar, M.T., Collier, N.: On the importance of the Kullback-Leibler divergence term in variational autoencoders for text generation. In: EMNLP-IJCNLP (2019)","DOI":"10.18653\/v1\/D19-5612"},{"key":"5_CR28","unstructured":"Sang, E.F.T.K., Meulder, F.D.: Introduction to the CoNLL-2003 shared task: language-independent named entity recognition. In: NAACL (2003)"},{"key":"5_CR29","doi-asserted-by":"crossref","unstructured":"Seo, S., Kim, D., Ahn, Y., Lee, K.: Active learning on pre-trained language model with task-independent triplet loss. In: AAAI (2022)","DOI":"10.1609\/aaai.v36i10.21378"},{"key":"5_CR30","doi-asserted-by":"publisher","unstructured":"Settles, B.: Active Learning. Synthesis Lectures on Artificial Intelligence and Machine Learning (2012). https:\/\/doi.org\/10.1007\/978-3-031-01560-1","DOI":"10.1007\/978-3-031-01560-1"},{"key":"5_CR31","doi-asserted-by":"crossref","unstructured":"Sharma, M., Zhuang, D., Bilgic, M.: Active learning with rationales for text classification. In: Mihalcea, R., Chai, J.Y., Sarkar, A. (eds.) NAACL, pp. 441\u2013451 (2015)","DOI":"10.3115\/v1\/N15-1047"},{"key":"5_CR32","doi-asserted-by":"crossref","unstructured":"Shen, Y., Yun, H., Lipton, Z.C., Kronrod, Y., Anandkumar, A.: Deep active learning for named entity recognition. In: ICLR (2018)","DOI":"10.18653\/v1\/W17-2630"},{"key":"5_CR33","unstructured":"Socher, R., et al.: Active learning by acquiring contrastive examples. In: ACL (2021)"},{"key":"5_CR34","doi-asserted-by":"crossref","unstructured":"Srinivasan, A., Vajjala, S.: A multilingual evaluation of NER robustness to adversarial inputs. In: RepL4NLP@ACL (2023)","DOI":"10.18653\/v1\/2023.repl4nlp-1.4"},{"key":"5_CR35","doi-asserted-by":"crossref","unstructured":"Suominen, H., et al.: Overview of the ShaRe\/CLEF eHealth evaluation lab 2013. In: CLEF (2013)","DOI":"10.1007\/978-3-642-40802-1_24"},{"key":"5_CR36","doi-asserted-by":"crossref","unstructured":"Uzuner, \u00d6., South, B.R., Shen, S., DuVall, S.L.: 2010 i2b2\/VA challenge on concepts, assertions, and relations in clinical text. JAMIA (2011)","DOI":"10.1136\/amiajnl-2011-000203"},{"key":"5_CR37","unstructured":"Wolf, T., et al.: Transformers: state-of-the-art natural language processing. In: EMNLP (2020)"},{"key":"5_CR38","doi-asserted-by":"crossref","unstructured":"Yoo, D., Kweon, I.S.: Learning loss for active learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 93\u2013102 (2019)","DOI":"10.1109\/CVPR.2019.00018"},{"key":"5_CR39","doi-asserted-by":"crossref","unstructured":"Yu, Y., Kong, L., Zhang, J., Zhang, R., Zhang, C.: AcTune: uncertainty-based active self-training for active fine-tuning of pretrained language models. In: NAACL (2022)","DOI":"10.18653\/v1\/2022.naacl-main.102"},{"key":"5_CR40","doi-asserted-by":"crossref","unstructured":"Yuan, M., Lin, H.T., Boyd-Graber, J.: Cold-start active learning through self-supervised language modeling. In: EMNLP (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.637"},{"key":"5_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, M., Plank, B.: Cartography active learning. In: Findings of EMNLP (2021)","DOI":"10.18653\/v1\/2021.findings-emnlp.36"},{"key":"5_CR42","unstructured":"Zhang, X., Zhao, J.J., Lecun, Y.: Character-level convolutional networks for text classification. In: NIPS (2015)"},{"key":"5_CR43","doi-asserted-by":"crossref","unstructured":"Zhu, J., Wang, H., Yao, T., Tsou, B.K.: Active learning with sampling by uncertainty and density for word sense disambiguation and text classification. In: COLING (2008)","DOI":"10.3115\/1599081.1599224"}],"container-title":["Lecture Notes in Computer Science","Trustworthy Artificial Intelligence for Healthcare"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-67751-9_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T23:02:49Z","timestamp":1722726169000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-67751-9_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031677502","9783031677519"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-67751-9_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"1 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"TAI4H","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Trustworthy Artificial Intelligence for Healthcare","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Jeju","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","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":"4 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tml4h2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}