{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T23:47:58Z","timestamp":1774309678157,"version":"3.50.1"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031490071","type":"print"},{"value":"9783031490088","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-49008-8_35","type":"book-chapter","created":{"date-parts":[[2023,12,14]],"date-time":"2023-12-14T13:04:15Z","timestamp":1702559055000},"page":"441-453","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["Advancing Neural Encoding of Portuguese with Transformer Albertina PT-*"],"prefix":"10.1007","author":[{"given":"Jo\u00e3o","family":"Rodrigues","sequence":"first","affiliation":[]},{"given":"Lu\u00eds","family":"Gomes","sequence":"additional","affiliation":[]},{"given":"Jo\u00e3o","family":"Silva","sequence":"additional","affiliation":[]},{"given":"Ant\u00f3nio","family":"Branco","sequence":"additional","affiliation":[]},{"given":"Rodrigo","family":"Santos","sequence":"additional","affiliation":[]},{"given":"Henrique Lopes","family":"Cardoso","sequence":"additional","affiliation":[]},{"given":"Tom\u00e1s","family":"Os\u00f3rio","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,12,15]]},"reference":[{"key":"35_CR1","unstructured":"Abadji, J., Ortiz Suarez, P., Romary, L., Sagot, B.: Towards a cleaner document-oriented multilingual crawled corpus. In: Proceedings of the Thirteenth Language Resources and Evaluation Conference (LREC), pp. 4344\u20134355 (2022)"},{"key":"35_CR2","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: 3rd International Conference on Learning Representations (ICLR) (2015)"},{"key":"35_CR3","unstructured":"Bengio, Y., Ducharme, R., Vincent, P.: A neural probabilistic language model. Adv. Neural Inf. Process. Syst. 13 (2000)"},{"key":"35_CR4","unstructured":"Bommasani, R., Hudson, D.A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M.S., Bohg, J., Bosselut, A., Brunskill, E., et al.: On the opportunities and risks of foundation models (2021). arXiv:2108.07258"},{"key":"35_CR5","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., 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":"35_CR6","unstructured":"De Vries, W., van Cranenburgh, A., Bisazza, A., Caselli, T., van Noord, G., Nissim, M.: BERTje: A Dutch BERT model (2019). arXiv:1912.09582"},{"key":"35_CR7","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics, pp. 4171\u20134186 (2019)"},{"key":"35_CR8","unstructured":"Gomes, J.R.S.: PLUE: Portuguese language understanding evaluation. github.com\/ju-resplande\/PLUE (2020)"},{"key":"35_CR9","unstructured":"Gugger, S., Debut, L., Wolf, T., Schmid, P., Mueller, Z., Mangrulkar, S.: Accelerate: Training and inference at scale made simple, efficient and adaptable (2022). github.com\/huggingface\/accelerate"},{"key":"35_CR10","unstructured":"Guti\u00e9rrez-Fandi\u00f1o, A., Armengol-Estap\u00e9, J., P\u00e1mies, M., Llop-Palao, J., Silveira-Ocampo, J., Carrino, C.P., Armentano-Oller, C., Rodriguez-Penagos, C., Gonzalez-Agirre, A., Villegas, M.: MarIA: Spanish language models. Procesamiento del Lenguaje Natural, pp. 39\u201360 (2022)"},{"key":"35_CR11","unstructured":"Hajlaoui, N., Kolovratnik, D., V\u00e4yrynen, J., Steinberger, R., Varga, D.: DCEP -digital corpus of the European parliament. In: Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC) (2014)"},{"key":"35_CR12","unstructured":"He, P., Liu, X., Gao, J., Chen, W.: DeBERTa: Decoding-enhanced BERT with disentangled attention. In: International Conference on Learning Representations (2021)"},{"key":"35_CR13","unstructured":"Hugging Face. huggingface.co\/Accessed Apr. 2023"},{"key":"35_CR14","unstructured":"Koehn, P.: Europarl: A parallel corpus for statistical machine translation. In: Proceedings of Machine Translation Summit X: Papers, pp. 79\u201386 (2005)"},{"key":"35_CR15","doi-asserted-by":"crossref","unstructured":"Kudo, T., Richardson, J.: SentencePiece: A simple and language independent subword tokenizer and detokenizer for neural text processing. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 66\u201371 (2018)","DOI":"10.18653\/v1\/D18-2012"},{"key":"35_CR16","unstructured":"Lauren\u00e7on, H., Saulnier, L., Wang, T., Akiki, C., del Moral, A.V., Scao, T.L., Werra, L.V., Mou, C., Ponferrada, E.G., Nguyen, H., et al.: The BigScience ROOTS corpus: A 1.6TB composite multilingual dataset. In: Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (2022)"},{"issue":"7553","key":"35_CR17","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436\u2013444 (2015)","journal-title":"Nature"},{"key":"35_CR18","doi-asserted-by":"crossref","unstructured":"Martin, L., Muller, B., Ortiz Su\u00e1rez, P.J., Dupont, Y., Romary, L., de la Clergerie, \u00c9., Seddah, D., Sagot, B.: CamemBERT: a tasty French language model. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 7203\u20137219 (2020)","DOI":"10.18653\/v1\/2020.acl-main.645"},{"key":"35_CR19","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space (2013). arXiv:1301.3781"},{"key":"35_CR20","doi-asserted-by":"crossref","unstructured":"Miquelina, N., Quaresma, P., Nogueira, V.B.: Generating a European Portuguese BERT based model using content from Arquivo.pt archive. In: Proceedings of the Intelligent Data Engineering and Automated Learning 23rd International Conference (IDEAL), pp. 280\u2013288 (2022)","DOI":"10.1007\/978-3-031-21753-1_28"},{"issue":"10","key":"35_CR21","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"SJ Pan","year":"2010","unstructured":"Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345\u20131359 (2010)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"35_CR22","doi-asserted-by":"crossref","unstructured":"Peters, M.E., Ruder, S., Smith, N.A.: To tune or not to tune? adapting pretrained representations to diverse tasks. In: Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP), pp. 7\u201314 (2019)","DOI":"10.18653\/v1\/W19-4302"},{"key":"35_CR23","doi-asserted-by":"crossref","unstructured":"Real, L., Fonseca, E., Gon\u00e7alo Oliveira, H.: The ASSIN 2 shared task: a quick overview. In: 14th International Conference on the Computational Processing of the Portuguese Language (PROPOR), pp. 406\u2013412. Springer (2020)","DOI":"10.1007\/978-3-030-41505-1_39"},{"key":"35_CR24","doi-asserted-by":"crossref","unstructured":"Schneider, E.T.R., de Souza, J.V.A., Knafou, J., Oliveira, L.E.S., et al.: BioBERTpt\u2013a Portuguese neural language model for clinical named entity recognition. In: Proceedings of the 3rd Clinical Natural Language Processing Workshop, pp. 65\u201372. Association for Computational Linguistics (2020)","DOI":"10.18653\/v1\/2020.clinicalnlp-1.7"},{"key":"35_CR25","doi-asserted-by":"crossref","unstructured":"Souza, F., Nogueira, R., Lotufo, R.: BERTimbau: pretrained BERT models for Brazilian Portuguese. In: Intelligent Systems: 9th Brazilian Conference (BRACIS), pp. 403\u2013417. Springer (2020)","DOI":"10.1007\/978-3-030-61377-8_28"},{"key":"35_CR26","unstructured":"Sun, Y., Wang, S., Feng, S., Ding, S., Pang, C., Shang, J., Liu, J., Chen, X., Zhao, Y., Lu, Y., et al.: Ernie 3.0: Large-scale knowledge enhanced pre-training for language understanding and generation (2021). arXiv:2107.02137"},{"key":"35_CR27","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. Adv. Neural Inf. Process. Syst. 27 (2014)"},{"key":"35_CR28","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"35_CR29","unstructured":"Wagner Filho, J.A., Wilkens, R., Idiart, M., Villavicencio, A.: The brWaC corpus: a new open resource for Brazilian Portuguese. In: Proceedings of the 11th International Conference on Language Resources and Evaluation (LREC) (2018)"},{"key":"35_CR30","unstructured":"Wang, A., Pruksachatkun, Y., Nangia, N., Singh, A., Michael, J., Hill, F., et al.: Superglue: A stickier benchmark for general-purpose language understanding systems. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"35_CR31","doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., Michael, J., et al.: GLUE: A multi-task benchmark and analysis platform for natural language understanding. In: Proceedings of the EMNLP Workshop BlackboxNLP, pp. 353\u2013355 (2018)","DOI":"10.18653\/v1\/W18-5446"},{"key":"35_CR32","unstructured":"Wolf, T. et al.: Transformers: State-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38\u201345 (2020)"}],"container-title":["Lecture Notes in Computer Science","Progress in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-49008-8_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,14]],"date-time":"2023-12-14T13:18:55Z","timestamp":1702559935000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-49008-8_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031490071","9783031490088"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-49008-8_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"15 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"EPIA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"EPIA Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Faial Island","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"epia2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/epia2023.inesctec.pt\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easy Chair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"163","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"85","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"52% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}