{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T16:44:13Z","timestamp":1774716253484,"version":"3.50.1"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031790317","type":"print"},{"value":"9783031790324","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-79032-4_23","type":"book-chapter","created":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T22:15:18Z","timestamp":1738188918000},"page":"324-338","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["ptt5-v2: A Closer Look at\u00a0Continued Pretraining of\u00a0T5 Models for\u00a0the\u00a0Portuguese Language"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1490-3476","authenticated-orcid":false,"given":"Marcos","family":"Piau","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5652-0852","authenticated-orcid":false,"given":"Roberto","family":"Lotufo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2600-6035","authenticated-orcid":false,"given":"Rodrigo","family":"Nogueira","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,30]]},"reference":[{"key":"23_CR1","unstructured":"Bajaj, P., et\u00a0al.: MS MARCO: a human generated machine reading comprehension dataset (2018)"},{"key":"23_CR2","doi-asserted-by":"publisher","unstructured":"de\u00a0Barros, T.M., Pedrini, H., Dias, Z.: Leveraging emoji to improve sentiment classification of tweets. In: Proceedings of the 36th Annual ACM Symposium on Applied Computing, SAC 2021, pp. 845\u2013852. Association for Computing Machinery, New York, NY, USA (2021). https:\/\/doi.org\/10.1145\/3412841.3441960","DOI":"10.1145\/3412841.3441960"},{"key":"23_CR3","unstructured":"Bonifacio, L., et\u00a0al.: mMARCO: a multilingual version of the MS MARCO passage ranking dataset (2022)"},{"key":"23_CR4","unstructured":"Brum, H., Volpe\u00a0Nunes, M.d.G.: Building a sentiment corpus of tweets in Brazilian Portuguese. In: Calzolari, N., et al. (eds.) Proceedings of the Eleventh International Conference on Language Resources and Evaluation, LREC 2018, May 2018. European Language Resources Association (ELRA), Miyazaki, Japan (2018)"},{"key":"23_CR5","unstructured":"Campiotti, I., Rodrigues, M., Albuquerque, Y., Azevedo, R., Andrade, A.: DeBERTinha: a multistep approach to adapt DebertaV3 XSmall for Brazilian Portuguese natural language processing task (2023)"},{"key":"23_CR6","unstructured":"Carmo, D., Piau, M., Campiotti, I., Nogueira, R., Lotufo, R.: PTT5: pretraining and validating the T5 model on Brazilian Portuguese data (2020)"},{"key":"23_CR7","unstructured":"Chrabrowa, A., et\u00a0al.: Evaluation of transfer learning for Polish with a text-to-text model (2022)"},{"key":"23_CR8","unstructured":"Chung, H.W., et\u00a0al.: Scaling instruction-finetuned language models (2022)"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Conneau, A., et\u00a0al.: Unsupervised cross-lingual representation learning at scale (2020)","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"23_CR10","doi-asserted-by":"crossref","unstructured":"Costa, P.B., Pavan, M.C., Santos, W.R., Silva, S.C., Paraboni, I.: BERTabaporu: assessing a genre-specific language model for Portuguese NLP. In: Mitkov, R., Angelova, G. (eds.) Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing, September 2023, pp. 217\u2013223. INCOMA Ltd., Shoumen, Bulgaria, Varna, Bulgaria (2023)","DOI":"10.26615\/978-954-452-092-2_024"},{"key":"23_CR11","unstructured":"Cui, Y., Yang, Z., Yao, X.: Efficient and effective text encoding for Chinese LLaMA and Alpaca (2024)"},{"key":"23_CR12","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding (2019)"},{"key":"23_CR13","unstructured":"Finardi, P., Viegas, J.D., Ferreira, G.T., Mansano, A.F., Carid\u00e1, V.F.: Berta\u00fa: Ita\u00fa bert for digital customer service (2021)"},{"key":"23_CR14","unstructured":"Gadre, S.Y., et\u00a0al.: Language models scale reliably with over-training and on downstream tasks (2024)"},{"key":"23_CR15","unstructured":"Garcia, G.L., et\u00a0al.: Introducing bode: a fine-tuned large language model for Portuguese prompt-based task (2024)"},{"key":"23_CR16","unstructured":"Gomes, J.R.S., et\u00a0al.: Deep learning Brasil at ABSAPT 2022: Portuguese transformer ensemble approaches (2023)"},{"key":"23_CR17","unstructured":"Hermann, K.M., et\u00a0al.: Teaching machines to read and comprehend (2015)"},{"key":"23_CR18","unstructured":"Hoffmann, J., et\u00a0al.: Training compute-optimal large language models (2022)"},{"key":"23_CR19","doi-asserted-by":"publisher","unstructured":"Honnibal, M., Montani, I., Landeghem, S.V., Boyd, A.: spaCy: industrial-strength natural language processing in Python (2020, to appear). https:\/\/doi.org\/10.5281\/zenodo.1212303","DOI":"10.5281\/zenodo.1212303"},{"key":"23_CR20","unstructured":"Hu, J., Ruder, S., Siddhant, A., Neubig, G., Firat, O., Johnson, M.: XTREME: a massively multilingual multi-task benchmark for evaluating cross-lingual generalization (2020)"},{"key":"23_CR21","unstructured":"Jeronymo, V., Nascimento, M., Lotufo, R., Nogueira, R.: mRobust04: a multilingual version of the TREC robust 2004 benchmark (2022)"},{"key":"23_CR22","doi-asserted-by":"publisher","unstructured":"Jude\u00a0Ogundepo, O., Oladipo, A., Adeyemi, M., Ogueji, K., Lin, J.: AfriTeVA: extending \u201csmall data\u201d pretraining approaches to sequence-to-sequence models. In: Cherry, C., (eds.) Proceedings of the Third Workshop on Deep Learning for Low-Resource Natural Language Processing, July 2022, pp. 126\u2013135. Association for Computational Linguistics, Hybrid (2022). https:\/\/doi.org\/10.18653\/v1\/2022.deeplo-1.14","DOI":"10.18653\/v1\/2022.deeplo-1.14"},{"key":"23_CR23","unstructured":"Kaplan, J., McCandlish, S., et\u00a0al.: Scaling laws for neural language models (2020)"},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Kudo, T., Richardson, J.: SentencePiece: a simple and language independent subword tokenizer and detokenizer for neural text processing. arXiv preprint arXiv:1808.06226 (2018)","DOI":"10.18653\/v1\/D18-2012"},{"key":"23_CR25","unstructured":"Larcher, C., Piau, M., Finardi, P., Gengo, P., Esposito, P., Carid\u00e1, V.: Cabrita: closing the gap for foreign languages (2023)"},{"key":"23_CR26","doi-asserted-by":"crossref","unstructured":"Lin, J., Ma, X., Lin, S.C., Yang, J.H., Pradeep, R., Nogueira, R.: Pyserini: a Python toolkit for reproducible information retrieval research with sparse and dense representations. In: Proceedings of the 44th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2021, pp. 2356\u20132362 (2021)","DOI":"10.1145\/3404835.3463238"},{"key":"23_CR27","unstructured":"Lopes, R., Magalh\u00e3es, J., Semedo, D.: Gl\u00f3ria \u2013 a generative and open large language model for Portuguese (2024)"},{"key":"23_CR28","unstructured":"de\u00a0Morais, L.P., da\u00a0Silva\u00a0Soares, A., da\u00a0CM\u00a0Borges, V., da\u00a0Silva, N.F.F., Pereira, F.S.: Sub-language sentiment analysis in Whatsapp domain with deep learning approaches. Revista de Sistemas de Informa\u00e7ao da FSMA 1(31), 32\u201347 (2023)"},{"key":"23_CR29","doi-asserted-by":"crossref","unstructured":"Nagoudi, E.M.B., Elmadany, A., Abdul-Mageed, M.: AraT5: text-to-text transformers for Arabic language generation (2022)","DOI":"10.18653\/v1\/2022.acl-long.47"},{"key":"23_CR30","doi-asserted-by":"publisher","unstructured":"Nogueira, R., Jiang, Z., Pradeep, R., Lin, J.: Document ranking with a pretrained sequence-to-sequence model. In: Cohn, T., He, Y., Liu, Y. (eds.) Findings of the Association for Computational Linguistics, EMNLP 2020, Online, November 2020, pp. 708\u2013718. Association for Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.findings-emnlp.63","DOI":"10.18653\/v1\/2020.findings-emnlp.63"},{"key":"23_CR31","unstructured":"Oliveira, H.G., Real, L., Fonseca, E. (eds.): Proceedings of the ASSIN 2 Shared Task: Evaluating Semantic Textual Similarity and Textual Entailment in Portuguese, Extended Semantic Web Conference, No.\u00a02583 in CEUR Workshop Proceedings (2020)"},{"key":"23_CR32","doi-asserted-by":"publisher","unstructured":"Pires, R., Abonizio, H., Almeida, T.S., Nogueira, R.: Sabi\u00e1: Portuguese Large Language Models, pp. 226\u2013240. Springer, Heidelberg (2023). https:\/\/doi.org\/10.1007\/978-3-031-45392-2_15","DOI":"10.1007\/978-3-031-45392-2_15"},{"key":"23_CR33","unstructured":"Rae, J.W., et\u00a0al.: Scaling language models: methods, analysis & insights from training Gopher (2022)"},{"key":"23_CR34","unstructured":"Raffel, C., et\u00a0al.: Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv preprint arXiv:1910.10683 (2019)"},{"key":"23_CR35","doi-asserted-by":"crossref","unstructured":"Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P.: SQuAD: 100,000+ questions for machine comprehension of text (2016)","DOI":"10.18653\/v1\/D16-1264"},{"key":"23_CR36","unstructured":"Roberts, A., et\u00a0al.: Scaling up models and data with t5x and seqio (2022)"},{"key":"23_CR37","doi-asserted-by":"crossref","unstructured":"Rodrigues, J., et\u00a0al.: Advancing neural encoding of Portuguese with transformer Albertina PT-* (2023)","DOI":"10.1007\/978-3-031-49008-8_35"},{"key":"23_CR38","unstructured":"Rosa, G.M., Bonifacio, L.H., de\u00a0Souza, L.R., Lotufo, R., Nogueira, R.: A cost-benefit analysis of cross-lingual transfer methods (2021)"},{"key":"23_CR39","unstructured":"Santos, R., Silva, J., Gomes, L., Rodrigues, J., Branco, A.: Advancing generative AI for Portuguese with open decoder Gerv\u00e1sio PT* (2024)"},{"key":"23_CR40","unstructured":"Sarti, G., Nissim, M.: IT5: large-scale text-to-text pretraining for Italian language understanding and generation (2022)"},{"key":"23_CR41","unstructured":"Shazeer, N., Stern, M.: Adafactor: adaptive learning rates with sublinear memory cost (2018)"},{"key":"23_CR42","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1007\/978-3-030-61377-8_28","volume-title":"Intelligent Systems","author":"F Souza","year":"2020","unstructured":"Souza, F., Nogueira, R., Lotufo, R.: BERTimbau: pretrained BERT models for Brazilian Portuguese. In: Cerri, R., Prati, R.C. (eds.) LNCS, pp. 403\u2013417. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-61377-8_28"},{"key":"23_CR43","unstructured":"Srivastava, A., et\u00a0al.: Beyond the imitation game: quantifying and extrapolating the capabilities of language models (2023)"},{"key":"23_CR44","unstructured":"Wagner\u00a0Filho, J.A., Wilkens, R., Idiart, M., Villavicencio, A.: The brWaC corpus: a new open resource for Brazilian Portuguese. In: Proceedings of the Eleventh International Conference on Language Resources and Evaluation, LREC 2018 (2018)"},{"key":"23_CR45","unstructured":"Wang, A., et\u00a0al.: SuperGLUE: a stickier benchmark for general-purpose language understanding systems (2020)"},{"key":"23_CR46","doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.R.: GLUE: a multi-task benchmark and analysis platform for natural language understanding (2019)","DOI":"10.18653\/v1\/W18-5446"},{"key":"23_CR47","unstructured":"Wang, L., Yang, N., Huang, X., Yang, L., Majumder, R., Wei, F.: Multilingual E5 text embeddings: a technical report (2024)"},{"key":"23_CR48","doi-asserted-by":"crossref","unstructured":"Xue, L., et\u00a0al.: mT5: a massively multilingual pre-trained text-to-text transformer (2021)","DOI":"10.18653\/v1\/2021.naacl-main.41"}],"container-title":["Lecture Notes in Computer Science","Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-79032-4_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T22:15:31Z","timestamp":1738188931000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-79032-4_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031790317","9783031790324"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-79032-4_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"30 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"BRACIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brazilian Conference on Intelligent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bel\u00e9m do Par\u00e1","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brazil","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":"17 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"34","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bracis2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}