{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T14:09:21Z","timestamp":1743084561101,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031388538"},{"type":"electronic","value":"9783031388545"}],"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\/978-3-031-38854-5_16","type":"book-chapter","created":{"date-parts":[[2023,7,22]],"date-time":"2023-07-22T21:01:44Z","timestamp":1690059704000},"page":"315-332","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["On the Impact of the Vocabulary for Domain-Adaptive Pretraining of Clinical Language Models"],"prefix":"10.1007","author":[{"given":"Anastasios","family":"Lamproudis","sequence":"first","affiliation":[]},{"given":"Aron","family":"Henriksson","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,7,23]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Beltagy, I., Lo, K., Cohan, A.: SciBERT: a pretrained language model for scientific text. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 3606\u20133611 (2019)","DOI":"10.18653\/v1\/D19-1371"},{"key":"16_CR2","unstructured":"Dalianis, H., Henriksson, A., Kvist, M., Velupillai, S., Weegar, R.: HEALTH BANK- a workbench for data science applications in healthcare. In: CEUR Workshop Proceedings Industry Track Workshop, pp. 1\u201318 (1 2015). http:\/\/ceur-ws.org\/Vol-1381\/paper1.pdf"},{"issue":"1","key":"16_CR3","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1186\/2041-1480-1-6","volume":"1","author":"H Dalianis","year":"2010","unstructured":"Dalianis, H., Velupillai, S.: De-identifying Swedish clinical text - refinement of a gold standard and experiments with conditional random fields. J. Biomed. Semant. 1(1), 6 (2010). https:\/\/doi.org\/10.1186\/2041-1480-1-6","journal-title":"J. Biomed. Semant."},{"key":"16_CR4","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4171\u20134186. Association for Computational Linguistics, Minneapolis, Minnesota (2019). https:\/\/doi.org\/10.18653\/v1\/N19-1423, https:\/\/aclanthology.org\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"16_CR5","unstructured":"El Boukkouri, H., Ferret, O., Lavergne, T., Zweigenbaum, P.: Re-train or train from scratch? Comparing pre-training strategies of BERT in the medical domain. In: LREC 2022, pp. 2626\u20132633 (2022)"},{"issue":"1","key":"16_CR6","first-page":"1","volume":"3","author":"Y Gu","year":"2021","unstructured":"Gu, Y., et al.: Domain-specific language model pretraining for biomedical natural language processing. ACM Trans. Comput. Healthc. (HEALTH) 3(1), 1\u201323 (2021)","journal-title":"ACM Trans. Comput. Healthc. (HEALTH)"},{"key":"16_CR7","doi-asserted-by":"publisher","unstructured":"Gururangan, S., et al.: Don\u2019t stop pretraining: adapt language models to domains and tasks. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 8342\u20138360. Association for Computational Linguistics, Online (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.740, https:\/\/aclanthology.org\/2020.acl-main.740","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Hong, J., Kim, T., Lim, H., Choo, J.: AVocaDO: strategy for adapting vocabulary to downstream domain. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 4692\u20134700 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.385"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Koto, F., Lau, J.H., Baldwin, T.: IndoBERTweet: a pretrained language model for indonesian twitter with effective domain-specific vocabulary initialization. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 10660\u201310668 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.833"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Kudo, T., Richardson, J.: SentencePiece: a simple and language independent subword tokenizer and detokenizer for neural text processing. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 66\u201371 (2018)","DOI":"10.18653\/v1\/D18-2012"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Lamproudis, A., Henriksson, A., Dalianis, H.: Developing a clinical language model for Swedish: continued pretraining of generic BERT with In-Domain data. In: Proceedings of RANLP 2021: Recent Advances in Natural Language Processing, 1\u20133 September 2021, Varna, Bulgaria, pp. 790\u2013797 (2021)","DOI":"10.26615\/978-954-452-072-4_090"},{"key":"16_CR12","unstructured":"Lamproudis, A., Henriksson, A., Dalianis, H.: Evaluating pretraining strategies for clinical BERT models. In: Proceedings of the Language Resources and Evaluation Conference, pp. 410\u2013416. European Language Resources Association, Marseille, France (2022). https:\/\/aclanthology.org\/2022.lrec-1.43"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Lamproudis, A., Henriksson, A., Dalianis, H.: Vocabulary modifications for domain-adaptive pretraining of clinical language models. In: HEALTHINF 2022, pp. 180\u2013188. SciTePress (2022)","DOI":"10.5220\/0010893800003123"},{"issue":"4","key":"16_CR14","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","volume":"36","author":"J Lee","year":"2020","unstructured":"Lee, J., et al.: BioBERT: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics 36(4), 1234\u20131240 (2020)","journal-title":"Bioinformatics"},{"key":"16_CR15","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"16_CR16","unstructured":"Malmsten, M., B\u00f6rjeson, L., Haffenden, C.: Playing with words at the national library of Sweden-making a Swedish BERT. arXiv preprint arXiv:2007.01658 (2020)"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Remmer, S., Lamproudis, A., Dalianis, H.: Multi-label diagnosis classification of Swedish discharge summaries - ICD-10 code assignment using KB-BERT. In: Proceedings of RANLP 2021: Recent Advances in Natural Language Processing, RANLP 2021, 1\u20133 September 2021, Varna, Bulgaria, pp. 1158\u20131166 (2021)","DOI":"10.26615\/978-954-452-072-4_130"},{"key":"16_CR18","doi-asserted-by":"publisher","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1715\u20131725. Association for Computational Linguistics, Berlin, Germany (2016). https:\/\/doi.org\/10.18653\/v1\/P16-1162, https:\/\/aclanthology.org\/P16-1162","DOI":"10.18653\/v1\/P16-1162"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Shin, H.C., et al.: BioMegatron: larger biomedical domain language model. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 4700\u20134706 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.379"},{"key":"16_CR20","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1016\/j.jbi.2014.01.012","volume":"49","author":"M Skeppstedt","year":"2014","unstructured":"Skeppstedt, M., Kvist, M., Nilsson, G.H., Dalianis, H.: Automatic recognition of disorders, findings, pharmaceuticals and body structures from clinical text: an annotation and machine learning study. J. Biomed. Inform. 49, 148\u2013158 (2014)","journal-title":"J. Biomed. Inform."},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Tai, W., Kung, H., Dong, X.L., Comiter, M., Kuo, C.F.: exBERT: extending pre-trained models with domain-specific vocabulary under constrained training resources. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings, pp. 1433\u20131439 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.129"},{"key":"16_CR22","unstructured":"Velupillai, S.: Automatic classification of factuality levels: a case study on Swedish diagnoses and the impact of local context. In: Fourth International Symposium on Languages in Biology and Medicine, LBM 2011 (2011)"},{"key":"16_CR23","unstructured":"Velupillai, S., Dalianis, H., Kvist, M.: Factuality levels of diagnoses in Swedish clinical text. In: User Centred Networked Health Care, pp. 559\u2013563. IOS Press (2011)"},{"key":"16_CR24","first-page":"141","volume":"11","author":"S Verkijk","year":"2021","unstructured":"Verkijk, S., Vossen, P.: MedRoBERTa.nl: a language model for Dutch electronic health records. Comput. Linguist. Neth. J. 11, 141\u2013159 (2021)","journal-title":"Comput. Linguist. Neth. J."},{"key":"16_CR25","unstructured":"Winter, B., Figueroa, A., L\u00f6ser, A., Gers, F.A., Siu, A.: KIMERA: injecting domain knowledge into vacant transformer heads, pp. 363\u2013373 (2022)"},{"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)"}],"container-title":["Communications in Computer and Information Science","Biomedical Engineering Systems and Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-38854-5_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,22]],"date-time":"2023-07-22T21:05:49Z","timestamp":1690059949000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-38854-5_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031388538","9783031388545"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-38854-5_16","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"23 July 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"BIOSTEC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Joint Conference on Biomedical Engineering Systems and Technologies","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 February 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 February 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"biostec2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/biostec.scitevents.org\/?y=2022","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":"PRIMORIS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"262","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":"21","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":"8% - 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":"3","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":"4","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)"}}]}}