{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T05:05:36Z","timestamp":1749531936299,"version":"3.40.5"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031777912"},{"type":"electronic","value":"9783031777929"}],"license":[{"start":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T00:00:00Z","timestamp":1732060800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T00:00:00Z","timestamp":1732060800000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-77792-9_6","type":"book-chapter","created":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T11:52:24Z","timestamp":1732276344000},"page":"86-101","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Empowering CamemBERT Legal Entity Extraction With LLM Boostrapping"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8285-0399","authenticated-orcid":false,"given":"Julien","family":"Breton","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4428-4298","authenticated-orcid":false,"given":"Mokhtar Boumedyen","family":"Billami","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5402-6255","authenticated-orcid":false,"given":"Max","family":"Chevalier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2840-005X","authenticated-orcid":false,"given":"Cassia","family":"Trojahn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,20]]},"reference":[{"key":"6_CR1","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1007\/978-3-031-17604-3_11","volume-title":"Enterprise Design, Operations, and Computing: 26th International Conference, EDOC 2022, Bozen-Bolzano, Italy, October 3\u20137, 2022, Proceedings","author":"P Bellan","year":"2022","unstructured":"Bellan, P., Dragoni, M., Ghidini, C.: Extracting business process entities and\u00a0relations from\u00a0text using pre-trained language models and\u00a0in-context learning. In: Almeida, J.P.A., Karastoyanova, D., Guizzardi, G., Montali, M., Maggi, F.M., Fonseca, C.M. (eds.) Enterprise Design, Operations, and Computing: 26th International Conference, EDOC 2022, Bozen-Bolzano, Italy, October 3\u20137, 2022, Proceedings, pp. 182\u2013199. Springer International Publishing, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-17604-3_11"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Biesner, D., et al.: Anonymization of German financial documents using neural network-based language models with contextual word representations. Int. J. Data Sci. Anal., 151\u2013161 (2022)","DOI":"10.1007\/s41060-021-00285-x"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Breton, J., Billami, M.B., Chevalier, M., Cassia, T.: Leveraging semantic model and LLM for bootstrapping a legal entity extraction: an industrial use case. In: 20th International Conference on Semantic Systems (SEMANTICS 2024) (2024)","DOI":"10.3233\/SSW240004"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Castano, S., Ferrara, A., Furiosi, E., Montanelli, S., Picascia, S., Riva, D., Stefanetti, C.: Enforcing legal information extraction through context-aware techniques: the ASKE approach. Comput. Law & Secur. Rev. 52, 105903 (2024)","DOI":"10.1016\/j.clsr.2023.105903"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y., Xiao, B., Lin, Z., Dai, C., Li, Z., Yan, L.: Multi-label text classification with deep neural networks. In: 2018 International Conference on Network Infrastructure and Digital Content (IC-NIDC), pp. 409\u2013413. IEEE (2018)","DOI":"10.1109\/ICNIDC.2018.8525817"},{"issue":"1","key":"6_CR6","doi-asserted-by":"publisher","first-page":"1418","DOI":"10.1038\/s41467-024-45563-x","volume":"15","author":"J Dagdelen","year":"2024","unstructured":"Dagdelen, J., et al.: Structured information extraction from scientific text with large language models. Nat. Commun. 15(1), 1418 (2024)","journal-title":"Nat. Commun."},{"key":"6_CR7","unstructured":"Dragoni, M., Villata, S., Rizzi, W., Governatori, G.: Combining NLP approaches for rule extraction from legal documents. In: 1st Workshop on MIning and REasoning with Legal texts (MIREL 2016)"},{"key":"6_CR8","unstructured":"Dunn, A., et al.: Structured information extraction from complex scientific text with fine-tuned large language models. ArXiv (2022)"},{"key":"6_CR9","unstructured":"Gu, Y., Dong, L., Wei, F., Huang, M.: MiniLLM: knowledge distillation of large language models (2024)"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Hsieh, C.Y., et al.: Distilling step-by-step! outperforming larger language models with less training data and smaller model sizes. ArXiv (2023)","DOI":"10.18653\/v1\/2023.findings-acl.507"},{"key":"6_CR11","unstructured":"Lafferty, J., McCallum, A., Pereira, F., et\u00a0al.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: ICML, vol.\u00a01, p.\u00a03. Williamstown, MA (2001)"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Louis, A., van Dijck, G., Spanakis, G.: Finding the law: enhancing statutory article retrieval via graph neural networks. In: Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pp. 2753\u20132768. Association for Computational Linguistics, Dubrovnik, Croatia (2023)","DOI":"10.18653\/v1\/2023.eacl-main.203"},{"issue":"64\u201367","key":"6_CR13","first-page":"2","volume":"5","author":"LR Medsker","year":"2001","unstructured":"Medsker, L.R., Jain, L., et al.: Recurrent neural networks. Design Appl. 5(64\u201367), 2 (2001)","journal-title":"Design Appl."},{"key":"6_CR14","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1007\/978-3-642-45358-8_7","volume-title":"Natural Language Processing of Semitic Languages","author":"B Mohit","year":"2014","unstructured":"Mohit, B.: Named entity recognition. In: Zitouni, I. (ed.) Natural Language Processing of Semitic Languages, pp. 221\u2013245. Springer, Berlin, Heidelberg (2014). https:\/\/doi.org\/10.1007\/978-3-642-45358-8_7"},{"key":"6_CR15","doi-asserted-by":"publisher","unstructured":"Oliveira, V., Nogueira, G., Faleiros, T., Marcacini, R.: Combining prompt-based language models and weak supervision for labeling named entity recognition on legal documents. Artif. Intell. Law (2024). https:\/\/doi.org\/10.1007\/s10506-023-09388-1","DOI":"10.1007\/s10506-023-09388-1"},{"key":"6_CR16","unstructured":"Pakhale, K.: Comprehensive overview of named entity recognition: models, domain-specific applications and challenges. arXiv preprint arXiv:2309.14084 (2023)"},{"key":"6_CR17","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1007\/978-3-031-47546-7_13","volume-title":"AIxIA 2023 \u2013 Advances in Artificial Intelligence: XXIInd International Conference of the Italian Association for Artificial Intelligence, AIxIA 2023, Rome, Italy, November 6\u20139, 2023, Proceedings","author":"R Pozzi","year":"2023","unstructured":"Pozzi, R., Rubini, R., Bernasconi, C., Palmonari, M.: Named entity recognition and linking for entity extraction from Italian civil judgements. In: Basili, R., Lembo, D., Limongelli, C., Orlandini, A. (eds.) AIxIA 2023 \u2013 Advances in Artificial Intelligence: XXIInd International Conference of the Italian Association for Artificial Intelligence, AIxIA 2023, Rome, Italy, November 6\u20139, 2023, Proceedings, pp. 187\u2013201. Springer Nature Switzerland, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-47546-7_13"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Prasanna, P.L., Rao, D.R.: Text classification using artificial neural networks. Int. J. Eng. Technol. 7(1.1), 603\u2013606 (2018)","DOI":"10.14419\/ijet.v7i1.1.10785"},{"key":"6_CR19","unstructured":"Sassier, P., Lansoy, D.: Ubu Loi. Arth\u00e8me Fayard, France (2008)"},{"key":"6_CR20","unstructured":"Sherstinsky, A.: Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. ArXiv (2018)"},{"key":"6_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10664-020-09933-5","volume":"26","author":"A Sleimi","year":"2021","unstructured":"Sleimi, A., Sannier, N., Sabetzadeh, M., Briand, L., Ceci, M., Dann, J.: An automated framework for the extraction of semantic legal metadata from legal texts. Empir. Softw. Eng. 26, 1\u201350 (2021)","journal-title":"Empir. Softw. Eng."},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Sleimi, A., Sannier, N., Sabetzadeh, M., Briand, L., Dann, J.: Automated extraction of semantic legal metadata using natural language processing. In: 2018 IEEE 26th International Requirements Engineering Conference (RE), pp. 124\u2013135 (2018)","DOI":"10.1109\/RE.2018.00022"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Solihin, F., Budi, I., Aji, R.F., Makarim, E.: Advancement of information extraction use in legal documents. Int. Rev. Law, Comput. Technol. 35(3), 322\u2013351 (2021)","DOI":"10.1080\/13600869.2021.1964225"},{"issue":"2","key":"6_CR24","first-page":"268","volume":"73","author":"O Suissa","year":"2022","unstructured":"Suissa, O., Elmalech, A., Zhitomirsky-Geffet, M.: Text analysis using deep neural networks in digital humanities and information science. J. Am. Soc. Inf. Sci. 73(2), 268\u2013287 (2022)","journal-title":"J. Am. Soc. Inf. Sci."},{"key":"6_CR25","unstructured":"Tang, R., Han, X., Jiang, X., Hu, X.: Does synthetic data generation of LLMs help clinical text mining? Arxiv (2023). arXiv preprint arXiv:2303.04360 (2023)"},{"key":"6_CR26","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"6_CR27","volume":"1550","author":"Z Wang","year":"2020","unstructured":"Wang, Z., Wu, Y., Lei, P., Peng, C.: Named entity recognition method of Brazilian legal text based on pre-training model. J. Phys: Conf. Ser. 1550, 032149 (2020)","journal-title":"J. Phys: Conf. Ser."},{"key":"6_CR28","unstructured":"Wei, X., et\u00a0al.: Zero-shot information extraction via chatting with ChatGPT. arXiv preprint arXiv:2302.10205 (2023)"},{"key":"6_CR29","doi-asserted-by":"crossref","unstructured":"Zaratiana, U., Tomeh, N., Holat, P., Charnois, T.: GLiNER: generalist model for named entity recognition using bidirectional transformer (2023)","DOI":"10.18653\/v1\/2022.umios-1.2"},{"key":"6_CR30","unstructured":"Zhao, W.X., et\u00a0al.: A survey of large language models. arXiv preprint arXiv:2303.18223 (2023)"},{"key":"6_CR31","unstructured":"Zhou, W., Zhang, S., Gu, Y., Chen, M., Poon, H.: UniversalNER: targeted distillation from large language models for open named entity recognition (2023)"}],"container-title":["Lecture Notes in Computer Science","Knowledge Engineering and Knowledge Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-77792-9_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T12:03:04Z","timestamp":1732276984000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-77792-9_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,20]]},"ISBN":["9783031777912","9783031777929"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-77792-9_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,20]]},"assertion":[{"value":"20 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"EKAW","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Knowledge Engineering and Knowledge Management","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","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":"25 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ekaw2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/event.cwi.nl\/ekaw2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}