{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T09:01:52Z","timestamp":1743066112827,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031702419"},{"type":"electronic","value":"9783031702426"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-70242-6_31","type":"book-chapter","created":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T10:03:06Z","timestamp":1726740186000},"page":"327-340","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Adaptation of\u00a0Large Language Models for\u00a0the\u00a0Public Sector: A Clustering Use Case"],"prefix":"10.1007","author":[{"given":"Emilien","family":"Caudron","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nathan","family":"Ghesqui\u00e8re","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wouter","family":"Travers","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexandra","family":"Balahur","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,20]]},"reference":[{"key":"31_CR1","doi-asserted-by":"crossref","unstructured":"Alsentzer, E., et al.: Publicly available clinical BERT embeddings (2019)","DOI":"10.18653\/v1\/W19-1909"},{"issue":"4","key":"31_CR2","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1007\/s10791-008-9066-8","volume":"12","author":"E Amig\u00f3","year":"2009","unstructured":"Amig\u00f3, E., Gonzalo, J., Artiles, J., Verdejo, F.: A comparison of extrinsic clustering evaluation metrics based on formal constraints. Inf. Retr. Boston. 12(4), 461\u2013486 (2009)","journal-title":"Inf. Retr. Boston."},{"key":"31_CR3","unstructured":"Araci, D.: Finbert: Financial sentiment analysis with pre-trained language models (2019)"},{"key":"31_CR4","doi-asserted-by":"publisher","unstructured":"Arefeva, V., Egger, R.: When BERT started traveling: TourBERT-a natural language processing model for the travel industry. Digital 2(4), 546\u2013559 (2022). https:\/\/doi.org\/10.3390\/digital2040030, https:\/\/www.mdpi.com\/2673-6470\/2\/4\/30","DOI":"10.3390\/digital2040030"},{"key":"31_CR5","doi-asserted-by":"crossref","unstructured":"Beltagy, I., Lo, K., Cohan, A.: SciBERT: a pretrained language model for scientific text (2019)","DOI":"10.18653\/v1\/D19-1371"},{"key":"31_CR6","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: Burstein, J., Doran, C., Solorio, T. (eds.) 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":"31_CR7","series-title":"Studies in Classification, Data Analysis, and Knowledge Organization","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/978-3-030-52348-0_2","volume-title":"Classification and Data Analysis","author":"A Dudek","year":"2020","unstructured":"Dudek, A.: Silhouette index as clustering evaluation tool. In: Jajuga, K., Bat\u00f3g, J., Walesiak, M. (eds.) SKAD 2019. SCDAKO, pp. 19\u201333. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-52348-0_2"},{"key":"31_CR8","doi-asserted-by":"publisher","unstructured":"Edwards, A., Camacho-Collados, J., De\u00a0Ribaupierre, H., Preece, A.: Go simple and pre-train on domain-specific corpora: on the role of training data for text classification. In: Scott, D., Bel, N., Zong, C. (eds.) Proceedings of the 28th International Conference on Computational Linguistics, pp. 5522\u20135529. International Committee on Computational Linguistics, Barcelona, Spain (Online) (2020). https:\/\/doi.org\/10.18653\/v1\/2020.coling-main.481, https:\/\/aclanthology.org\/2020.coling-main.481","DOI":"10.18653\/v1\/2020.coling-main.481"},{"key":"31_CR9","unstructured":"European Commission: first transition pathway co-created with industry and civil society for a resilient, green and digital tourism ecosystem. https:\/\/ec.europa.eu\/commission\/presscorner\/detail\/en\/ip_22_850"},{"key":"31_CR10","unstructured":"European Commission: shaping Europe\u2019s digital future. https:\/\/digital-strategy.ec.europa.eu\/en\/activities\/digital-programme"},{"key":"31_CR11","unstructured":"European Commission: communication from the commission: artificial intelligence for Europe, com(2018) 237 final (2018). https:\/\/eur-lex.europa.eu\/legal-content\/EN\/TXT\/?uri=COM:2018:237:FIN#document1"},{"key":"31_CR12","unstructured":"European Commission: transition pathway for tourism (2022). https:\/\/op.europa.eu\/s\/y7Ht"},{"key":"31_CR13","doi-asserted-by":"publisher","unstructured":"Gururangan, S., et al.: Don\u2019t stop pretraining: adapt language models to domains and tasks. In: Jurafsky, D., Chai, J., Schluter, N., Tetreault, J. (eds.) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 8342\u20138360. Association for Computational Linguistics (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":"31_CR14","unstructured":"Hadi, M.U., et al.: Large language models: a comprehensive survey of its applications, challenges, limitations, and future prospects. https:\/\/api.semanticscholar.org\/CorpusID:266378240"},{"key":"31_CR15","doi-asserted-by":"publisher","unstructured":"Howard, J., Ruder, S.: Universal language model fine-tuning for text classification. In: Gurevych, I., Miyao, Y. (eds.) Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 328\u2013339. Association for Computational Linguistics, Melbourne, Australia (2018). https:\/\/doi.org\/10.18653\/v1\/P18-1031, https:\/\/aclanthology.org\/P18-1031","DOI":"10.18653\/v1\/P18-1031"},{"key":"31_CR16","unstructured":"Huang, K., Altosaar, J., Ranganath, R.: Clinicalbert: Modeling clinical notes and predicting hospital readmission (2020)"},{"key":"31_CR17","unstructured":"Kumar, P.S., Reddy, P.V.: Document clustering using RoBERTa and convolution neural network model. Int. J. Intell. Syst. Appl. Eng. 12(8s), 221\u2013230 (2023). https:\/\/www.ijisae.org\/index.php\/IJISAE\/article\/view\/4112"},{"key":"31_CR18","doi-asserted-by":"publisher","unstructured":"Tangi, L., Combetto, M., MARTIN, B.J., RODRIGUEZ, M.P.,: Artificial intelligence for interoperability in the European public sector (KJ-NA-31-675-EN-N (online)) (2023). https:\/\/doi.org\/10.2760\/633646","DOI":"10.2760\/633646"},{"key":"31_CR19","doi-asserted-by":"crossref","unstructured":"Lee, J.S., Hsiang, J.: PatentBERT: patent classification with fine-tuning a pre-trained BERT model (2019)","DOI":"10.1016\/j.wpi.2020.101965"},{"key":"31_CR20","doi-asserted-by":"publisher","unstructured":"Lee, J., et al.: BioBERT: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics 36(4), 1234\u20131240 (2019). https:\/\/doi.org\/10.1093\/bioinformatics\/btz682","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"31_CR21","unstructured":"Ling, C., et al.: Domain specialization as the key to make large language models disruptive: a comprehensive survey (2023)"},{"key":"31_CR22","unstructured":"Naveed, H., et al.: A comprehensive overview of large language models (2024)"},{"key":"31_CR23","unstructured":"OpenAI: Language models are few-shot learners. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol.\u00a033, pp. 1877\u20131901. Curran Associates, Inc. (2020). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf"},{"key":"31_CR24","unstructured":"OpenAI: Gpt-4 technical report (2023)"},{"key":"31_CR25","doi-asserted-by":"publisher","unstructured":"Pasta, A., et al.: Clustering users based on hearing aid use: an exploratory analysis of real-world data. Front. Digit.l Health 3 (2021). https:\/\/doi.org\/10.3389\/fdgth.2021.725130","DOI":"10.3389\/fdgth.2021.725130"},{"key":"31_CR26","unstructured":"Semantic Interoperability Community: text mining on grow tourism pledges - documentation (2023). https:\/\/github.com\/SEMICeu\/semic_pledges"},{"key":"31_CR27","doi-asserted-by":"publisher","unstructured":"Subakti, A., Murfi, H., Hariadi, N.: The performance of BERT as data representation of text clustering. J. Big Data 9(1), 15 (2022). https:\/\/doi.org\/10.1186\/s40537-022-00564-9,","DOI":"10.1186\/s40537-022-00564-9,"},{"key":"31_CR28","doi-asserted-by":"publisher","unstructured":"Wang, H., Li, J., Wu, H., Hovy, E., Sun, Y.: Pre-trained language models and their applications. Engineering 25, 51\u201365 (2023). https:\/\/doi.org\/10.1016\/j.eng.2022.04.024,https:\/\/www.sciencedirect.com\/science\/article\/pii\/S2095809922006324","DOI":"10.1016\/j.eng.2022.04.024,"},{"key":"31_CR29","unstructured":"Wei, J., et al.: Emergent abilities of large language models (2022)"},{"key":"31_CR30","unstructured":"Yang, Y., UY, M.C.S., Huang, A.: FinBERT: a pretrained language model for financial communications (2020)"}],"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\/978-3-031-70242-6_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T12:18:34Z","timestamp":1740399514000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70242-6_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031702419","9783031702426"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70242-6_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"20 September 2024","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":"Turin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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 June 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 June 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nldb2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/nldb2024.di.unito.it\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}