{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T22:53:22Z","timestamp":1774047202848,"version":"3.50.1"},"publisher-location":"Cham","reference-count":56,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031971402","type":"print"},{"value":"9783031971419","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"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":[[2026]]},"DOI":"10.1007\/978-3-031-97141-9_6","type":"book-chapter","created":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T12:55:59Z","timestamp":1751288159000},"page":"80-94","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["How Important is Domain-Specific Language Model Pretraining and\u00a0Instruction Finetuning for\u00a0Biomedical Relation Extraction?"],"prefix":"10.1007","author":[{"given":"Aviv","family":"Brokman","sequence":"first","affiliation":[]},{"given":"Ramakanth","family":"Kavuluru","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,1]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Alsentzer, E., Murphy, J., Boag, W., Weng, W.H., Jindi, D., Naumann, T., McDermott, M.: Publicly available clinical BERT embeddings. In: Proceedings of the 2nd Clinical Natural Language Processing Workshop, pp. 72\u201378 (2019)","DOI":"10.18653\/v1\/W19-1909"},{"key":"6_CR2","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1016\/j.jbi.2018.05.003","volume":"82","author":"G Bakal","year":"2018","unstructured":"Bakal, G., Talari, P., Kakani, E.V., Kavuluru, R.: Exploiting semantic patterns over biomedical knowledge graphs for predicting treatment and causative relations. J. Biomed. Inf. 82, 189\u2013199 (2018)","journal-title":"J. Biomed. Inf."},{"key":"6_CR3","doi-asserted-by":"publisher","unstructured":"Black, S., Gao, L., Wang, P., Leahy, C., Biderman, S.: GPT-neo: large scale autoregressive language modeling with mesh-tensorflow (2021). https:\/\/doi.org\/10.5281\/zenodo.5297715","DOI":"10.5281\/zenodo.5297715"},{"key":"6_CR4","unstructured":"Bolton, E., et\u00a0al.: BioMedLM: a 2.7 b parameter language model trained on biomedical text. arXiv preprint arXiv:2403.18421 (2024)"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Botsis, T., Buttolph, T., Nguyen, M.D., Winiecki, S., Woo, E.J., Ball, R.: Vaccine adverse event text mining system for extracting features from vaccine safety reports. J. Am. Med. Inf. Assoc. 19(6), 1011\u20131018 (2012)","DOI":"10.1136\/amiajnl-2012-000881"},{"key":"6_CR6","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems, vol.\u00a033, pp. 1877\u20131901 (2020)"},{"key":"6_CR7","unstructured":"Christiano, P.F., Leike, J., Brown, T., Martic, M., Legg, S., Amodei, D.: Deep reinforcement learning from human preferences. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"6_CR8","unstructured":"Chung, H.W., et\u00a0al.: Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416 (2022)"},{"key":"6_CR9","unstructured":"Clark, K., Luong, M., Le, Q.V., Manning, C.D.: ELECTRA: pre-training text encoders as discriminators rather than generators. In: 8th International Conference on Learning Representations (2020)"},{"key":"6_CR10","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings\u00a0of NAACL:HLT, pp. 4171\u20134186 (2019)"},{"key":"6_CR11","unstructured":"Dirkson, A., Verberne, S., Kraaij, W.: FuzzyBIO: a proposal for fuzzy representation of discontinuous entities. In: Proceedings\u00a0of the 12th Workshop on Health Text Mining and Information Analysis, pp. 77\u201382 (2021)"},{"key":"6_CR12","unstructured":"Eberts, M., Ulges, A.: Span-based joint entity and relation extraction with transformer pre-training. In: Proceedings\u00a0of the EACL, pp. 2006\u20132013 (2020)"},{"key":"6_CR13","unstructured":"Fries, J.A., et\u00a0al.: BigBIO: a framework for data-centric biomedical natural language processing. arXiv preprint arXiv:2206.15076 (2022)"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Giorgi, J., Bader, G., Wang, B.: A sequence-to-sequence approach for document-level relation extraction. In: Proceedings\u00a0of the 21st Workshop on Biomedical Language Processing, pp. 10\u201325 (2022)","DOI":"10.18653\/v1\/2022.bionlp-1.2"},{"key":"6_CR15","unstructured":"Gu, Y., et al.: Domain-specific language model pretraining for biomedical natural language processing (2020)"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Gururangan, S., Marasovi\u0107, A., Swayamdipta, S., Lo, K., Beltagy, I., Downey, D., Smith, N.A.: Don\u2019t stop pretraining: adapt language models to domains and tasks. In: Proceedings\u00a0of the ACL, pp. 8342\u20138360 (2020)","DOI":"10.18653\/v1\/2020.acl-main.740"},{"issue":"5","key":"6_CR17","doi-asserted-by":"publisher","first-page":"914","DOI":"10.1016\/j.jbi.2013.07.011","volume":"46","author":"M Herrero-Zazo","year":"2013","unstructured":"Herrero-Zazo, M., Segura-Bedmar, I., Mart\u00ednez, P., Declerck, T.: The ddi corpus: an annotated corpus with pharmacological substances and drug-drug interactions. J. Biomed. Inf. 46(5), 914\u2013920 (2013)","journal-title":"J. Biomed. Inf."},{"key":"6_CR18","unstructured":"Hou, Y., et al.: Discovering drug-target interaction knowledge from biomedical literature (2021)"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Hou, Y., et al.: Discovering drug\u2013target interaction knowledge from biomedical literature. Bioinformatics 38(22), 5100\u20135107 (2022)","DOI":"10.1093\/bioinformatics\/btac648"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Huguet\u00a0Cabot, P.L., Navigli, R.: REBEL: relation extraction by end-to-end language generation. In: Findings of the ACL: EMNLP 2021, pp. 2370\u20132381 (2021)","DOI":"10.18653\/v1\/2021.findings-emnlp.204"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Kavuluru, R.: End-to-end n-ary relation extraction for combination drug therapies. In: IEEE 11th International Conference\u00a0on Healthcare Informatics, pp. 72\u201380 (2023)","DOI":"10.1109\/ICHI57859.2023.00021"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Johnson, A.E., et al.: Mimic-iii, a freely accessible critical care database. Sci. Data 3(1), 1\u20139 (2016)","DOI":"10.1038\/sdata.2016.35"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Kanakarajan, K.r., Kundumani, B., Sankarasubbu, M.: BioELECTRA: pretrained biomedical text encoder using discriminators. In: Proceedings\u00a0of the 20th Workshop on BioNLP, pp. 143\u2013154 (2021)","DOI":"10.18653\/v1\/2021.bionlp-1.16"},{"key":"6_CR24","unstructured":"Krallinger, M., et\u00a0al.: Overview of the biocreative vi chemical-protein interaction track. In: Proceedings\u00a0of the Sixth BioCreative Challenge Evaluation Workshop, vol.\u00a01, pp. 141\u2013146 (2017)"},{"issue":"4","key":"6_CR25","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","volume":"36","author":"J Lee","year":"2019","unstructured":"Lee, J., et al.: BioBERT: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics 36(4), 1234\u20131240 (2019)","journal-title":"Bioinformatics"},{"issue":"4","key":"6_CR26","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1093\/bioinformatics\/btx613","volume":"34","author":"J Lever","year":"2018","unstructured":"Lever, J., et al.: A collaborative filtering-based approach to biomedical knowledge discovery. Bioinformatics 34(4), 652\u2013659 (2018)","journal-title":"Bioinformatics"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Proceedings\u00a0of the ACL, pp. 7871\u20137880 (2020)","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"6_CR28","doi-asserted-by":"crossref","unstructured":"Lewis, P., Ott, M., Du, J., Stoyanov, V.: Pretrained language models for biomedical and clinical tasks: understanding and extending the state-of-the-art. In: Proceedings of the 3rd Clinical Natural Language Processing Workshop, pp. 146\u2013157 (2020)","DOI":"10.18653\/v1\/2020.clinicalnlp-1.17"},{"key":"6_CR29","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: Biocreative V CDR task corpus: a resource for chemical disease relation extraction. Database J. Biol. Databases Curat. (2016)","DOI":"10.1093\/database\/baw068"},{"issue":"1","key":"6_CR30","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1007\/s40264-018-0766-8","volume":"42","author":"F Liu","year":"2019","unstructured":"Liu, F., Jagannatha, A., Yu, H.: Towards drug safety surveillance and pharmacovigilance: current progress in detecting medication and adverse drug events from electronic health records. Drug Saf. 42(1), 95\u201397 (2019)","journal-title":"Drug Saf."},{"key":"6_CR31","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Stoyanov, V.: Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"6_CR32","doi-asserted-by":"crossref","unstructured":"Lo, K., Wang, L.L., Neumann, M., Kinney, R., Weld, D.: S2ORC: the semantic scholar open research corpus. In: Proceedings\u00a0of the ACL, pp. 4969\u20134983 (2020)","DOI":"10.18653\/v1\/2020.acl-main.447"},{"key":"6_CR33","doi-asserted-by":"crossref","unstructured":"Luo, R., et al.: BioGPT: generative pre-trained transformer for biomedical text generation and mining. Brief. Bioinf. 23(6) (2022)","DOI":"10.1093\/bib\/bbac409"},{"key":"6_CR34","doi-asserted-by":"crossref","unstructured":"Miwa, M., Sasaki, Y.: Modeling joint entity and relation extraction with table representation. In: Proceedings of EMNLP, pp. 1858\u20131869 (2014)","DOI":"10.3115\/v1\/D14-1200"},{"key":"6_CR35","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR36","doi-asserted-by":"crossref","unstructured":"Parmar, M., Mishra, S., Purohit, M., Luo, M., Mohammad, M., Baral, C.: In-BoXBART: get instructions into biomedical multi-task learning. In: Findings of the ACL: NAACL 2022, pp. 112\u2013128 (2022)","DOI":"10.18653\/v1\/2022.findings-naacl.10"},{"key":"6_CR37","doi-asserted-by":"crossref","unstructured":"Peng, Y., Yan, S., Lu, Z.: Transfer learning in biomedical natural language processing: an evaluation of bert and elmo on ten benchmarking datasets. In: Proceedings\u00a0of the Workshop on BioNLP, pp. 58\u201365 (2019)","DOI":"10.18653\/v1\/W19-5006"},{"key":"6_CR38","unstructured":"Phan, L.N., et al.: Scifive: a text-to-text transformer model for biomedical literature. arXiv preprint arXiv:2106.03598 (2021)"},{"issue":"8","key":"6_CR39","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"},{"issue":"1","key":"6_CR40","first-page":"5485","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(1), 5485\u20135551 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"6_CR41","unstructured":"Sanh, V., Webson, A., Raffel, C., Bach, S.H., Sutawika, L., Alyafeai, Z.: Multitask prompted training enables zero-shot task generalization. In: International Conference on Learning Representations (2022)"},{"key":"6_CR42","doi-asserted-by":"crossref","unstructured":"Schick, T., Sch\u00fctze, H.: Exploiting cloze-questions for few-shot text classification and natural language inference. In: Proceedings\u00a0of the 16th EACL, pp. 255\u2013269 (2021)","DOI":"10.18653\/v1\/2021.eacl-main.20"},{"key":"6_CR43","doi-asserted-by":"crossref","unstructured":"Shin, H.C., et al.: BioMegatron: larger biomedical domain language model. In: Proceedings of EMNLP, pp. 4700\u20134706 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.379"},{"key":"6_CR44","unstructured":"Shoeybi, M., Patwary, M., Puri, R., LeGresley, P., Casper, J., Catanzaro, B.: Megatron-lm: training multi-billion parameter language models using model parallelism. arXiv preprint arXiv:1909.08053 (2019)"},{"key":"6_CR45","unstructured":"Stiennon, N., et al.: Learning to summarize with human feedback. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol.\u00a033, pp. 3008\u20133021 (2020)"},{"key":"6_CR46","doi-asserted-by":"crossref","unstructured":"Tiktinsky, A., et al.: a dataset for n-ary relation extraction of drug combinations. In: Proceedings of NAACL: HLT, pp. 3190\u20133203 (2022)","DOI":"10.18653\/v1\/2022.naacl-main.233"},{"key":"6_CR47","unstructured":"Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Scialom, T.: Llama 2: open foundation and fine-tuned chat models (2023)"},{"key":"6_CR48","doi-asserted-by":"crossref","unstructured":"Wadhwa, S., Amir, S., Wallace, B.C.: Revisiting relation extraction in the era of large language models. In: Proceedings\u00a0of the ACL (2023)","DOI":"10.18653\/v1\/2023.acl-long.868"},{"key":"6_CR49","doi-asserted-by":"crossref","unstructured":"Wang, H., Xu, C., McAuley, J.: Automatic multi-label prompting: Simple and interpretable few-shot classification. In: Proceedings of NAACL: HLT, pp. 5483\u20135492 (2022)","DOI":"10.18653\/v1\/2022.naacl-main.401"},{"key":"6_CR50","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Self-instruct: aligning language models with self-generated instructions. In: Proceedings\u00a0of the ACL, pp. 13484\u201313508 (2023)","DOI":"10.18653\/v1\/2023.acl-long.754"},{"key":"6_CR51","doi-asserted-by":"crossref","unstructured":"Wang, Y., Yu, B., Zhu, H., Liu, T., Yu, N., Sun, L.: Discontinuous named entity recognition as maximal clique discovery. In: Proceedings\u00a0of the ACL, pp. 764\u2013774 (2021)","DOI":"10.18653\/v1\/2021.acl-long.63"},{"key":"6_CR52","unstructured":"Wei, J., et al.: Finetuned language models are zero-shot learners. In: International Conference on Learning Representations (2022)"},{"key":"6_CR53","doi-asserted-by":"crossref","unstructured":"Yuan, H., Yuan, Z., Gan, R., Zhang, J., Xie, Y., Yu, S.: BioBART: pretraining and evaluation of a biomedical generative language model. In: Proceedings\u00a0of the 21st Workshop on Biomedical Language Processing, pp. 97\u2013109 (2022)","DOI":"10.18653\/v1\/2022.bionlp-1.9"},{"key":"6_CR54","doi-asserted-by":"crossref","unstructured":"Zeng, D., Zhang, H., Liu, Q.: Copymtl: copy mechanism for joint extraction of entities and relations with multi-task learning. In: Proceedings\u00a0of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 9507\u20139514 (2020)","DOI":"10.1609\/aaai.v34i05.6495"},{"key":"6_CR55","doi-asserted-by":"crossref","unstructured":"Zeng, X., Zeng, D., He, S., Liu, K., Zhao, J.: Extracting relational facts by an end-to-end neural model with copy mechanism. In: Proceedings\u00a0of the ACL, pp. 506\u2013514 (2018)","DOI":"10.18653\/v1\/P18-1047"},{"key":"6_CR56","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Chen, D.: A frustratingly easy approach for entity and relation extraction. In: Proceedings of NAACL: HLT, pp. 50\u201361 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.5"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-97141-9_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T12:56:18Z","timestamp":1751288178000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-97141-9_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,1]]},"ISBN":["9783031971402","9783031971419"],"references-count":56,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-97141-9_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,1]]},"assertion":[{"value":"1 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLDB","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Applications of Natural Language to Information Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kanazawa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nldb2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/nldb2025.github.io\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}