{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T04:08:42Z","timestamp":1751342922227,"version":"3.41.0"},"publisher-location":"Cham","reference-count":34,"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_4","type":"book-chapter","created":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T12:57:08Z","timestamp":1751288228000},"page":"49-63","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Comparison of\u00a0Pipelines, Seq2seq Models, and\u00a0LLMs for\u00a0Rare Disease Information Extraction"],"prefix":"10.1007","author":[{"given":"Shashank","family":"Gupta","sequence":"first","affiliation":[]},{"given":"Xuguang","family":"Ai","sequence":"additional","affiliation":[]},{"given":"Yuhang","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Ramakanth","family":"Kavuluru","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,1]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Ai, X., Kavuluru, R.: End-to-end models for chemical\u2013protein interaction extraction: better tokenization and span-based pipeline strategies. In: 11th International Conference on Healthcare Informatics (ICHI), pp. 610\u2013618. IEEE (2023)","DOI":"10.1109\/ICHI57859.2023.00108"},{"key":"4_CR2","unstructured":"Bolton, E., et\u00a0al.: BiomedLM: a 2.7B parameter language model trained on biomedical text. arXiv preprint arXiv:2403.18421 (2024)"},{"key":"4_CR3","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4_CR4","unstructured":"Chung, H.W., et\u00a0al.: Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416 (2022)"},{"key":"4_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2105-10-S10-S7","volume":"10","author":"H Dietze","year":"2009","unstructured":"Dietze, H., Schroeder, M.: Goweb: a semantic search engine for the life science web. BMC Bioinf. 10, 1\u201313 (2009)","journal-title":"BMC Bioinf."},{"key":"4_CR6","unstructured":"Eberts, M., Ulges, A.: Span-based joint entity and relation extraction with transformer pre-training. In: ECAI 2020, pp. 2006\u20132013. IOS Press (2020)"},{"key":"4_CR7","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1016\/j.cmpb.2018.07.007","volume":"164","author":"H Fabregat","year":"2018","unstructured":"Fabregat, H., Araujo, L., Martinez-Romo, J.: Deep neural models for extracting entities and relationships in the new RDD corpus relating disabilities and rare diseases. Comput. Methods Programs Biomed. 164, 121\u2013129 (2018)","journal-title":"Comput. Methods Programs Biomed."},{"key":"4_CR8","unstructured":"Gao, L., et\u00a0al.: The pile: an 800 gb dataset of diverse text for language modeling. arXiv preprint arXiv:2101.00027 (2020)"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Giorgi, J., Bader, G., Wang, B.: A sequence-to-sequence approach for document-level relation extraction. In: Proceedings of BioNLP, pp. 10\u201325. ACL (2022)","DOI":"10.18653\/v1\/2022.bionlp-1.2"},{"key":"4_CR10","unstructured":"Global Genes: Facts. https:\/\/globalgenes.org\/learn\/rare-disease-facts\/"},{"key":"4_CR11","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.jbi.2017.08.011","volume":"74","author":"S Henry","year":"2017","unstructured":"Henry, S., McInnes, B.T.: Literature based discovery: models, methods, and trends. J. Biomed. Inf. 74, 20\u201332 (2017)","journal-title":"J. Biomed. Inf."},{"key":"4_CR12","unstructured":"Jurafsky, D., Martin, J.H.: Speech and Language Processing, 3rd edn. (2023). https:\/\/web.stanford.edu\/~jurafsky\/slp3\/"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Kavuluru, R., Rios, A., Tran, T.: Extracting drug-drug interactions with word and character-level recurrent neural networks. In: IEEE International Conference on Healthcare Informatics (ICHI), pp. 5\u201312. IEEE (2017)","DOI":"10.1109\/ICHI.2017.15"},{"key":"4_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12859-020-3517-7","volume":"21","author":"H Kilicoglu","year":"2020","unstructured":"Kilicoglu, H., Rosemblat, G., Fiszman, M., Shin, D.: Broad-coverage biomedical relation extraction with semrep. BMC Bioinf. 21, 1\u201328 (2020)","journal-title":"BMC Bioinf."},{"issue":"29","key":"4_CR15","doi-asserted-by":"publisher","first-page":"3153","DOI":"10.2174\/0929867324666170511111803","volume":"24","author":"B Klimova","year":"2017","unstructured":"Klimova, B., Storek, M., Valis, M., Kuca, K.: Global view on rare diseases: a mini review. Curr. Med. Chem. 24(29), 3153\u20133158 (2017)","journal-title":"Curr. Med. Chem."},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Li, F., Lin, Z., Zhang, M., Ji, D.: A span-based model for joint overlapped and discontinuous named entity recognition. In: Proceedings of the 59th Annual Meeting of the ACL and the 11th International Joint Conference on Natural Language Processing, vol. 1: Long Papers, pp. 4814\u20134828 (2021)","DOI":"10.18653\/v1\/2021.acl-long.372"},{"key":"4_CR17","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":"4_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2021.103961","volume":"125","author":"C Mart\u00ednez-deMiguel","year":"2022","unstructured":"Mart\u00ednez-deMiguel, C., Segura-Bedmar, I., Chac\u00f3n-Solano, E., Guerrero-Aspizua, S.: The raredis corpus: a corpus annotated with rare diseases, their signs and symptoms. J. Biomed. Inf. 125, 103961 (2022)","journal-title":"J. Biomed. Inf."},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Miwa, M., Bansal, M.: End-to-end relation extraction using lstms on sequences and tree structures. In: Proceedings of the 54th Annual Meeting of the ACL, vol. 1: Long Papers, pp. 1105\u20131116 (2016)","DOI":"10.18653\/v1\/P16-1105"},{"key":"4_CR20","unstructured":"National Organization for Rare Disorders (NORD): Rare Disease Database Frequently Asked Questions. https:\/\/rarediseases.org\/wp-content\/uploads\/2019\/01\/RDD-FAQ-2019.pdf (2019)"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Nayak, T., Ng, H.T.: Effective modeling of encoder-decoder architecture for joint entity and relation extraction. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 8528\u20138535 (2020)","DOI":"10.1609\/aaai.v34i05.6374"},{"key":"4_CR22","unstructured":"Open AI: Learning to reason with LLMs (2024). https:\/\/openai.com\/index\/learning-to-reason-with-llms\/"},{"key":"4_CR23","first-page":"101","volume":"5","author":"N Peng","year":"2017","unstructured":"Peng, N., Poon, H., Quirk, C., Toutanova, K., Yih, W.T.: Cross-sentence n-ary relation extraction with graph lstms. Trans. ACL 5, 101\u2013115 (2017)","journal-title":"Trans. ACL"},{"key":"4_CR24","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners (2019). https:\/\/insightcivic.s3.us-east-1.amazonaws.com\/language-models.pdf"},{"issue":"1","key":"4_CR25","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":"4_CR26","doi-asserted-by":"crossref","unstructured":"Tran, T., Kavuluru, R.: An end-to-end deep learning architecture for extracting protein\u2013protein interactions affected by genetic mutations. In: Database, pp. 1\u201313 (2018)","DOI":"10.1093\/database\/bay092"},{"key":"4_CR27","unstructured":"Tran, T., Kavuluru, R.: Neural metric learning for fast end-to-end relation extraction. arXiv preprint arXiv:1905.07458 (2019)"},{"key":"4_CR28","first-page":"24824","volume":"35","author":"J Wei","year":"2022","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. Adv. Neural. Inf. Process. Syst. 35, 24824\u201324837 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4_CR29","doi-asserted-by":"crossref","unstructured":"Yao, Y., et al.: DocRED: a large-scale document-level relation extraction dataset. In: Proceedings of the 57th Annual Meeting of the ACL, pp. 764\u2013777 (2019)","DOI":"10.18653\/v1\/P19-1074"},{"key":"4_CR30","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 of the 56th Annual Meeting of the ACL, vol. 1: Long Papers, pp. 506\u2013514 (2018)","DOI":"10.18653\/v1\/P18-1047"},{"key":"4_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, M., Zhang, Y., Fu, G.: End-to-end neural relation extraction with global optimization. In: Proceedings of EMNLP, pp. 1730\u20131740 (2017)","DOI":"10.18653\/v1\/D17-1182"},{"key":"4_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Lin, H., Yang, Z., Wang, J., Sun, Y.: Chemical\u2013protein interaction extraction via contextualized word representations and multihead attention. Database 2019, baz054 (2019)","DOI":"10.1093\/database\/baz054"},{"key":"4_CR33","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"},{"key":"4_CR34","doi-asserted-by":"crossref","unstructured":"Zhou, P., et al.: Attention-based bidirectional long short-term memory networks for relation classification. In: Proceedings of the 54th Annual Meeting of the ACL, pp. 207\u2013212 (2016)","DOI":"10.18653\/v1\/P16-2034"}],"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_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T12:57:12Z","timestamp":1751288232000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-97141-9_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,1]]},"ISBN":["9783031971402","9783031971419"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-97141-9_4","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"}}]}}