{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T17:37:39Z","timestamp":1770053859455,"version":"3.49.0"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032113573","type":"print"},{"value":"9783032113580","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-3-032-11358-0_11","type":"book-chapter","created":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T07:04:11Z","timestamp":1770015851000},"page":"125-138","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Continual Pretraining of\u00a0a\u00a0Small Language Model on\u00a0Cuban Spanish Corpora"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1168-1767","authenticated-orcid":false,"given":"Ernesto Luis","family":"Estevanell-Valladares","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6707-1442","authenticated-orcid":false,"given":"Suilan","family":"Estevez-Velarde","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9522-3239","authenticated-orcid":false,"given":"Alejandro","family":"Piad-Morffis","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2345-1387","authenticated-orcid":false,"given":"Yudivian","family":"Almeida-Cruz","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8073-1033","authenticated-orcid":false,"given":"Alejandro","family":"Beltr\u00e1n Varela","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9303-0055","authenticated-orcid":false,"given":"Carla Sunami","family":"P\u00e9rez Valera","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4472-3967","authenticated-orcid":false,"given":"Daniel Alejandro","family":"Vald\u00e9s P\u00e9rez","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0042-3516","authenticated-orcid":false,"given":"Deborah Famadas","family":"Rodr\u00edguez","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1515-3111","authenticated-orcid":false,"given":"Elena","family":"Rodr\u00edguez Horta","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8692-2133","authenticated-orcid":false,"given":"Gabriel","family":"Hern\u00e1ndez Rodr\u00edguez","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0088-607X","authenticated-orcid":false,"given":"Niley","family":"Gonz\u00e1lez Ferrales","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5269-8281","authenticated-orcid":false,"given":"Roberto","family":"Garcia Rodriguez","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7671-4187","authenticated-orcid":false,"given":"Roberto Marti","family":"Cede\u00f1o","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2009-393X","authenticated-orcid":false,"given":"Juan Pablo","family":"Consuegra Ayala","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2784-2748","authenticated-orcid":false,"given":"Robiert","family":"Sep\u00falveda-Torres","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4052-7427","authenticated-orcid":false,"given":"Yoan","family":"Guti\u00e9rrez","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3076-0890","authenticated-orcid":false,"given":"Andr\u00e9s","family":"Montoyo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8127-9012","authenticated-orcid":false,"given":"Rafael","family":"Mu\u00f1oz Guillena","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1441-7865","authenticated-orcid":false,"given":"Manuel","family":"Palomar","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,2,3]]},"reference":[{"key":"11_CR1","unstructured":"Ahuja, K., et\u00a0al.: Belebele: a novel multilingual reading comprehension dataset for low-resource languages. In: arXiv preprint arXiv:2307.09641 (2023)"},{"key":"11_CR2","unstructured":"Artetxe, M., Ruder, S., Yogatama, D.: Xquad: a cross-lingual question answering dataset. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 8658\u20138663 (2020)"},{"key":"11_CR3","unstructured":"Gonzalez-Agirre, A., et\u00a0al.: Salamandra technical report. arXiv preprint arXiv:2502.08489 (2025)"},{"key":"11_CR4","unstructured":"Goodfellow, I. J., Mirza, M., Xiao, D., Courville, A., Bengio, Y.: An empirical investigation of catastrophic forgetting in gradient-based neural networks. arXiv preprint arXiv:1312.6211, (2013)"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Gururangan, S., et al.: Don\u2019t stop pretraining: adapt language models to domains and tasks. arXiv preprint arXiv:2004.10964 (2020)","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Hasan, T., et al.: Xl-sum: large-scale multilingual abstractive summarization for 44 languages. In: Findings of the Association for Computational Linguistics: EMNLP 2021, pp. 4693\u20134703 (2021)","DOI":"10.18653\/v1\/2021.findings-acl.413"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Hovy, D.: The social and the neural network: how to make natural language processing about people again. In: Proceedings of the Second Workshop on Computational Modeling of People\u2019s Opinions, Personality, and Emotions in Social Media, pp. 42\u201349 (2018)","DOI":"10.18653\/v1\/W18-1106"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Joshi, M., Choi, E., Weld, D., Zettlemoyer, L.: Triviaqa: a large scale distantly supervised challenge dataset for reading comprehension. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1601\u20131611 (2017)","DOI":"10.18653\/v1\/P17-1147"},{"key":"11_CR9","unstructured":"Lee, E.: The impact of model size on catastrophic forgetting in online continual learning. arXiv preprint arXiv:2407.00176 (2024)"},{"key":"11_CR10","unstructured":"Levesque, H., Davis, E., Morgenstern, L.: The winograd schema challenge. In: Proceedings of the Thirteenth International Conference on Principles of Knowledge Representation and Reasoning, pp. 552\u2013561 (2012)"},{"key":"11_CR11","first-page":"84799","volume":"37","author":"C Li","year":"2024","unstructured":"Li, C., Chen, M., Wang, J., Sitaram, S., Xie, X.: Culturellm: incorporating cultural differences into large language models. Adv. Neural. Inf. Process. Syst. 37, 84799\u201384838 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR12","unstructured":"Li, Y., Eldan, R.: Tinystories: how small can language models be and still speak coherent english (2023)"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Liu, Y., Held, W., Yang, D.: Dada: Dialect adaptation via dynamic aggregation of linguistic rules. arXiv preprint arXiv:2305.13406 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.850"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Mihaylov, T., Clark, P., Khot, T., Sabharwal, A.: Openbookqa: A new benchmark for open book question answering. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 2381\u20132391 (2018)","DOI":"10.18653\/v1\/D18-1260"},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"Nguyen, D., Rosseel, L., Grieve, J.: On learning and representing social meaning in NLP: a sociolinguistic perspective. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 603\u2013612 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.50"},{"key":"11_CR16","unstructured":"Patil, N., et al.: Regional tiny stories: using small models to compare language learning and tokenizer performance. arXiv preprint arXiv:2504.07989 (2025)"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Rust, P., Pfeiffer, J., Vuli\u0107, I., Gurevych, I., Ruder, S.: How good is your tokenizer? on the monolingual performance of multilingual language models. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics (ACL), pp. 3118\u20133135 (2021)","DOI":"10.18653\/v1\/2021.acl-long.243"},{"key":"11_CR18","unstructured":"liogeris, V., Daniu\u0161is, P., Nakvosas, A.: Full-parameter continual pretraining of gemma2: insights into fluency and domain knowledge. arXiv preprint arXiv:2505.05946 (2025)"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Tellez, E. S., Moctezuma, D., Miranda, S., Graff, M., Ruiz, G.: Regionalized models for spanish language variations based on twitter. Lang. Res. Eval. 57(4):1697\u20131727 (2023)","DOI":"10.1007\/s10579-023-09640-9"},{"key":"11_CR20","unstructured":"Y\u0131ld\u0131z, C., Ravichandran, NK., Sharma, N., Bethge, M., Ermis, B.: Investigating continual pretraining in large language models: insights and implications. arXiv preprint arXiv:2402.17400 (2024)"},{"key":"11_CR21","unstructured":"Zhang, B., Sennrich, R.: Root mean square layer normalization. Advances in Neural Information Processing Systems, 32 (2019)"}],"container-title":["Lecture Notes in Computer Science","Progress in Artificial Intelligence and Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-11358-0_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T07:04:25Z","timestamp":1770015865000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-11358-0_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032113573","9783032113580"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-11358-0_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"3 February 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IWAIPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Congress on Artificial Intelligence and Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Varadero","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cuba","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":"14 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iwaipr2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eventos.uci.cu\/en\/event\/ix-international-congress-on-artificial-intelligence-and-pattern-recognition-iwaipr-2025-2\/register","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}