{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,29]],"date-time":"2026-03-29T06:24:17Z","timestamp":1774765457358,"version":"3.50.1"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,2,15]],"date-time":"2024-02-15T00:00:00Z","timestamp":1707955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,2,15]],"date-time":"2024-02-15T00:00:00Z","timestamp":1707955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100005668","name":"Funda\u00e7\u00e3o de Apoio \u00e0 Pesquisa do Distrito Federal","doi-asserted-by":"publisher","award":["FAPDF\/CIC - KnEDLe"],"award-info":[{"award-number":["FAPDF\/CIC - KnEDLe"]}],"id":[{"id":"10.13039\/501100005668","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002322","name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002322","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Artif Intell Law"],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1007\/s10506-023-09388-1","type":"journal-article","created":{"date-parts":[[2024,2,15]],"date-time":"2024-02-15T06:03:12Z","timestamp":1707976992000},"page":"361-381","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Combining prompt-based language models and weak supervision for labeling named entity recognition on legal documents"],"prefix":"10.1007","volume":"33","author":[{"given":"Vitor","family":"Oliveira","sequence":"first","affiliation":[]},{"given":"Gabriel","family":"Nogueira","sequence":"additional","affiliation":[]},{"given":"Thiago","family":"Faleiros","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2309-3487","authenticated-orcid":false,"given":"Ricardo","family":"Marcacini","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,2,15]]},"reference":[{"key":"9388_CR1","doi-asserted-by":"publisher","unstructured":"Bach SH, Rodriguez D, Liu Y et\u00a0al (2019) Snorkel drybell: a case study in deploying weak supervision at industrial scale. In: Proceedings of the 2019 international conference on management of data, SIGMOD \u201919. Association for Computing Machinery, New York, NY, USA, pp 362\u2013375. https:\/\/doi.org\/10.1145\/3299869.3314036","DOI":"10.1145\/3299869.3314036"},{"key":"9388_CR2","unstructured":"Brown TB, Mann B, Ryder N et\u00a0al (2020) Language models are few-shot learners. arXiv:2005.14165"},{"key":"9388_CR3","doi-asserted-by":"crossref","unstructured":"Chowdhary K (2020) Natural language processing. In: Fundamentals of artificial intelligence. Springer, New Delhi, pp 603\u2013649","DOI":"10.1007\/978-81-322-3972-7_19"},{"key":"9388_CR4","doi-asserted-by":"crossref","unstructured":"Dai H, Song Y, Wang H (2021) Ultra-fine entity typing with weak supervision from a masked language model. arXiv:2106.04098","DOI":"10.18653\/v1\/2021.acl-long.141"},{"issue":"1","key":"9388_CR5","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1017\/S1351324920000601","volume":"27","author":"R Dale","year":"2021","unstructured":"Dale R (2021) Gpt-3: what\u2019s it good for? Nat Lang Eng 27(1):113\u2013118. https:\/\/doi.org\/10.1017\/S1351324920000601","journal-title":"Nat Lang Eng"},{"key":"9388_CR6","first-page":"1","volume":"7","author":"J Dem\u0161ar","year":"2006","unstructured":"Dem\u0161ar J (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7:1\u201330","journal-title":"J Mach Learn Res"},{"key":"9388_CR7","doi-asserted-by":"crossref","unstructured":"Dozier C, Kondadadi R, Light M et\u00a0al (2010) Named entity recognition and resolution in legal text. In: Semantic processing of legal texts. Springer, pp 27\u201343","DOI":"10.1007\/978-3-642-12837-0_2"},{"issue":"10","key":"9388_CR8","doi-asserted-by":"publisher","first-page":"1315","DOI":"10.1038\/nbt1004-1315","volume":"22","author":"SR Eddy","year":"2004","unstructured":"Eddy SR (2004) What is a hidden Markov model? Nat Biotechnol 22(10):1315\u20131316","journal-title":"Nat Biotechnol"},{"issue":"4","key":"9388_CR9","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1007\/s11023-020-09548-1","volume":"30","author":"L Floridi","year":"2020","unstructured":"Floridi L, Chiriatti M (2020) Gpt-3: its nature, scope, limits, and consequences. Mind Mach 30(4):681\u2013694","journal-title":"Mind Mach"},{"key":"9388_CR10","doi-asserted-by":"crossref","unstructured":"Fredriksson T, Mattos DI, Bosch J et\u00a0al (2020) Data labeling: an empirical investigation into industrial challenges and mitigation strategies. In: Product-focused software process improvement: 21st international conference, PROFES 2020, Proceedings 21, Turin, Italy, November 25\u201327, 2020. Springer, pp 202\u2013216","DOI":"10.1007\/978-3-030-64148-1_13"},{"key":"9388_CR11","doi-asserted-by":"crossref","unstructured":"Giri R, Porwal Y, Shukla V et\u00a0al (2017) Approaches for information retrieval in legal documents. In: 2017 tenth international conference on contemporary computing (IC3). IEEE, pp 1\u20136","DOI":"10.1109\/IC3.2017.8284324"},{"issue":"5","key":"9388_CR12","doi-asserted-by":"publisher","first-page":"602","DOI":"10.1016\/j.neunet.2005.06.042","volume":"18","author":"A Graves","year":"2005","unstructured":"Graves A, Schmidhuber J (2005) Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw 18(5):602\u2013610. https:\/\/doi.org\/10.1016\/j.neunet.2005.06.042","journal-title":"Neural Netw"},{"key":"9388_CR13","doi-asserted-by":"crossref","unstructured":"Karamanolakis G, Mukherjee S, Zheng G et\u00a0al (2021) Self-training with weak supervision. arXiv:2104.05514","DOI":"10.18653\/v1\/2021.naacl-main.66"},{"key":"9388_CR14","doi-asserted-by":"crossref","unstructured":"Lison P, Hubin A, Barnes J et\u00a0al (2020) Named entity recognition without labelled data: a weak supervision approach. arXiv:2004.14723","DOI":"10.18653\/v1\/2020.acl-main.139"},{"key":"9388_CR15","doi-asserted-by":"crossref","unstructured":"Lison P, Barnes J, Hubin A (2021) skweak: weak supervision made easy for NLP. arXiv preprint arXiv:2104.09683","DOI":"10.18653\/v1\/2021.acl-demo.40"},{"key":"9388_CR16","unstructured":"Liu Y, Ott M, Goyal N et\u00a0al (2019) Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692"},{"issue":"9","key":"9388_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3560815","volume":"55","author":"P Liu","year":"2023","unstructured":"Liu P, Yuan W, Fu J et al (2023) Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing. ACM Comput Surv 55(9):1\u201335. https:\/\/doi.org\/10.1145\/3560815","journal-title":"ACM Comput Surv"},{"key":"9388_CR18","doi-asserted-by":"crossref","unstructured":"Luz\u00a0de Araujo PH, de Campos TE, de\u00a0Oliveira RR et\u00a0al (2018) LeNER-Br: a dataset for named entity recognition in brazilian legal text. In: International conference on computational processing of the Portuguese language. Springer, pp 313\u2013323","DOI":"10.1007\/978-3-319-99722-3_32"},{"key":"9388_CR19","unstructured":"Maiya AS (2020) ktrain: a low-code library for augmented machine learning. arXiv preprint arXiv:2004.10703 [cs.LG]"},{"issue":"5","key":"9388_CR20","doi-asserted-by":"publisher","first-page":"482","DOI":"10.1016\/j.csi.2012.09.004","volume":"35","author":"M Marrero","year":"2013","unstructured":"Marrero M, Urbano J, S\u00e1nchez-Cuadrado S et al (2013) Named entity recognition: fallacies, challenges and opportunities. Comput Stand Interfaces 35(5):482\u2013489","journal-title":"Comput Stand Interfaces"},{"key":"9388_CR21","doi-asserted-by":"publisher","unstructured":"Meyer S, Elsweiler D, Ludwig B et\u00a0al (2022) Do we still need human assessors? prompt-based gpt-3 user simulation in conversational ai. In: Proceedings of the 4th conference on conversational user interfaces, CUI \u201922. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3543829.3544529,","DOI":"10.1145\/3543829.3544529"},{"issue":"1","key":"9388_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3445965","volume":"54","author":"Z Nasar","year":"2021","unstructured":"Nasar Z, Jaffry SW, Malik MK (2021) Named entity recognition and relation extraction: state-of-the-art. ACM Comput Surv 54(1):1\u201339","journal-title":"ACM Comput Surv"},{"issue":"2","key":"9388_CR23","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1007\/s00778-019-00552-1","volume":"29","author":"A Ratner","year":"2020","unstructured":"Ratner A, Bach SH, Ehrenberg H et al (2020) Snorkel: rapid training data creation with weak supervision. VLDB J 29(2):709\u2013730","journal-title":"VLDB J"},{"key":"9388_CR24","unstructured":"Ratner AJ, De\u00a0Sa CM, Wu S et\u00a0al (2016) Data programming: creating large training sets, quickly. Advances in neural information processing systems 29"},{"issue":"1","key":"9388_CR25","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/s10506-020-09263-3","volume":"29","author":"N Sakhaee","year":"2021","unstructured":"Sakhaee N, Wilson MC (2021) Information extraction framework to build legislation network. Artif Intell Law 29(1):35\u201358","journal-title":"Artif Intell Law"},{"key":"9388_CR26","unstructured":"Smith LN (2015) Cyclical learning rates for training neural networks. arXiv:1506.01186"},{"key":"9388_CR27","doi-asserted-by":"crossref","unstructured":"Souza F, Nogueira R, Lotufo R (2020) BERTimbau: pretrained BERT models for Brazilian Portuguese. In: Brazilian conference on intelligent systems. Springer, pp 403\u2013417","DOI":"10.1007\/978-3-030-61377-8_28"},{"key":"9388_CR28","doi-asserted-by":"crossref","unstructured":"Sun C, Qiu X, Xu Y et al (2019) How to fine-tune bert for text classification? In: China national conference on Chinese computational linguistics. Springer, Cham, pp 194\u2013206","DOI":"10.1007\/978-3-030-32381-3_16"},{"key":"9388_CR29","unstructured":"Torfi A, Shirvani RA, Keneshloo Y et\u00a0al (2020) Natural language processing advancements by deep learning: a survey. arXiv preprint arXiv:2003.01200"},{"key":"9388_CR30","doi-asserted-by":"crossref","unstructured":"Vardhan H, Surana N, Tripathy B (2021) Named-entity recognition for legal documents. In: International conference on advanced machine learning technologies and applications. Springer, pp 469\u2013479","DOI":"10.1007\/978-981-15-3383-9_43"},{"key":"9388_CR31","volume-title":"Natural Language processing with Python and SpaCy: a practical introduction","author":"Y Vasiliev","year":"2020","unstructured":"Vasiliev Y (2020) Natural Language processing with Python and SpaCy: a practical introduction. No Starch Press, San Francisco"},{"key":"9388_CR32","doi-asserted-by":"crossref","unstructured":"Wang S, Liu Y, Xu Y et\u00a0al (2021) Want to reduce labeling cost? GPT-3 can help. arXiv:2108.13487","DOI":"10.18653\/v1\/2021.findings-emnlp.354"},{"key":"9388_CR33","unstructured":"Wang S, Sun X, Li X et\u00a0al (2023) Gpt-ner: named entity recognition via large language models. arXiv:2304.10428"},{"key":"9388_CR34","unstructured":"Wei X, Cui X, Cheng N et\u00a0al (2023) Zero-shot information extraction via chatting with chatgpt. arXiv:2302.10205"},{"key":"9388_CR35","doi-asserted-by":"publisher","unstructured":"Zamani H, Croft WB (2018) On the theory of weak supervision for information retrieval. In: Proceedings of the 2018 ACM SIGIR international conference on theory of information retrieval, ICTIR \u201918. Association for Computing Machinery, New York, NY, USA, pp 147\u2013154. https:\/\/doi.org\/10.1145\/3234944.3234968","DOI":"10.1145\/3234944.3234968"},{"key":"9388_CR36","doi-asserted-by":"crossref","unstructured":"Zhang S, He L, Dragut E et\u00a0al (2019) How to invest my time: Lessons from human-in-the-loop entity extraction. In: Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, pp 2305\u20132313","DOI":"10.1145\/3292500.3330773"},{"issue":"1","key":"9388_CR37","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1093\/nsr\/nwx106","volume":"5","author":"ZH Zhou","year":"2018","unstructured":"Zhou ZH (2018) A brief introduction to weakly supervised learning. Natl Sci Rev 5(1):44\u201353","journal-title":"Natl Sci Rev"}],"container-title":["Artificial Intelligence and Law"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10506-023-09388-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10506-023-09388-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10506-023-09388-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T00:02:08Z","timestamp":1749081728000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10506-023-09388-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,15]]},"references-count":37,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["9388"],"URL":"https:\/\/doi.org\/10.1007\/s10506-023-09388-1","relation":{},"ISSN":["0924-8463","1572-8382"],"issn-type":[{"value":"0924-8463","type":"print"},{"value":"1572-8382","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,15]]},"assertion":[{"value":"20 December 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 February 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}