{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:42:30Z","timestamp":1778053350952,"version":"3.51.4"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031453915","type":"print"},{"value":"9783031453922","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\/978-3-031-45392-2_18","type":"book-chapter","created":{"date-parts":[[2023,10,11]],"date-time":"2023-10-11T20:17:29Z","timestamp":1697055449000},"page":"268-282","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["LegalBert-pt: A Pretrained Language Model for\u00a0the\u00a0Brazilian Portuguese Legal Domain"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7445-605X","authenticated-orcid":false,"given":"Raquel","family":"Silveira","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1643-9475","authenticated-orcid":false,"given":"Caio","family":"Ponte","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3606-2304","authenticated-orcid":false,"given":"Vitor","family":"Almeida","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9851-8304","authenticated-orcid":false,"given":"Vl\u00e1dia","family":"Pinheiro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8721-4308","authenticated-orcid":false,"given":"Vasco","family":"Furtado","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,10,12]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Aguiar, A., Silveira, R., Pinheiro, V., Furtado, V., Neto, J.A.: Text classification in legal documents extracted from lawsuits in Brazilian courts. In: Anais da X Brazilian Conference on Intelligent Systems, SBC, Porto Alegre, RS, Brasil (2021). https:\/\/sol.sbc.org.br\/index.php\/bracis\/article\/view\/19093","DOI":"10.1007\/978-3-030-91699-2_40"},{"key":"18_CR2","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1007\/978-3-030-98305-5_22","volume-title":"Computational Processing of the Portuguese Language","author":"A Aguiar","year":"2022","unstructured":"Aguiar, A., Silveira, R., Furtado, V., Pinheiro, V., Neto, J.A.M.: Using topic modeling in classification of Brazilian lawsuits. In: Pinheiro, V., et al. (eds.) PROPOR 2022. LNCS (LNAI), vol. 13208, pp. 233\u2013242. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-030-98305-5_22"},{"key":"18_CR3","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1007\/978-3-319-99722-3_32","volume-title":"Computational Processing of the Portuguese Language","author":"PH Luz de Araujo","year":"2018","unstructured":"Luz de Araujo, P.H., de Campos, T.E., de Oliveira, R.R.R., Stauffer, M., Couto, S., Bermejo, P.: LeNER-Br: a dataset for named entity recognition in Brazilian legal text. In: Villavicencio, A., et al. (eds.) PROPOR 2018. LNCS (LNAI), vol. 11122, pp. 313\u2013323. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-99722-3_32"},{"key":"18_CR4","unstructured":"Luz de Araujo, P.H., de Campos, T.E., Ataides Braz, F., Correia da Silva, N.: VICTOR: a dataset for Brazilian legal documents classification. In: Proceedings of the Twelfth Language Resources and Evaluation Conference, pp. 1449\u20131458. European Language Resources Association, Marseille (2020). https:\/\/aclanthology.org\/2020.lrec-1.181"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Beltagy, I., Lo, K., Cohan, A.: Scibert: a pretrained language model for scientific text. arXiv preprint arXiv:1903.10676 (2019)","DOI":"10.18653\/v1\/D19-1371"},{"key":"18_CR6","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., 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":"18_CR7","doi-asserted-by":"crossref","unstructured":"Chalkidis, I., Fergadiotis, M., Malakasiotis, P., Aletras, N., Androutsopoulos, I.: Legal-bert: the muppets straight out of law school. arXiv preprint arXiv:2010.02559 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.261"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Chalkidis, I., et al.: Lexglue: a benchmark dataset for legal language understanding in english (2022)","DOI":"10.2139\/ssrn.3936759"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Chinchor, N., Sundheim, B.M.: Muc-5 evaluation metrics. In: Fifth Message Understanding Conference (MUC-5): Proceedings of a Conference Held in Baltimore, Maryland, 25\u201327 August 1993 (1993)","DOI":"10.3115\/1072017.1072026"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Conneau, A., et al.: Unsupervised cross-lingual representation learning at scale. arXiv preprint arXiv:1911.02116 (2019)","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"18_CR11","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Feng, Z., et al.: Codebert: a pre-trained model for programming and natural languages. arXiv preprint arXiv:2002.08155 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"18_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2021.100388","volume":"40","author":"D Jain","year":"2021","unstructured":"Jain, D., Borah, M.D., Biswas, A.: Summarization of legal documents: where are we now and the way forward. Comput. Sci. Rev. 40, 100388 (2021)","journal-title":"Comput. Sci. Rev."},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Kalyan, K.S., Rajasekharan, A., Sangeetha, S.: Ammus: a survey of transformer-based pretrained models in natural language processing. arXiv preprint arXiv:2108.05542 (2021)","DOI":"10.1016\/j.jbi.2021.103982"},{"key":"18_CR15","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"},{"issue":"4","key":"18_CR16","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","volume":"36","author":"J Lee","year":"2020","unstructured":"Lee, J.: Biobert: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics 36(4), 1234\u20131240 (2020)","journal-title":"Bioinformatics"},{"key":"18_CR17","unstructured":"Legal-bertimbau-base. https:\/\/huggingface.co\/rufimelo\/Legal-BERTimbau-base"},{"key":"18_CR18","unstructured":"Licari, D., Comand\u00e8, G.: Italian-legal-bert: a pre-trained transformer language model for Italian law (2022)"},{"key":"18_CR19","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1016\/j.aiopen.2022.10.001","volume":"3","author":"T Lin","year":"2022","unstructured":"Lin, T., Wang, Y., Liu, X., Qiu, X.: A survey of transformers. AI Open 3, 111\u2013132 (2022). https:\/\/doi.org\/10.1016\/j.aiopen.2022.10.001","journal-title":"AI Open"},{"key":"18_CR20","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"18_CR21","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"18_CR22","unstructured":"Brito, M., et al.: Cdjur-br - a golden collection of legal document from Brazilian justice with fine-grained named entities. arXiv preprint arXiv:2023.49053 (2023)"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Meister, C., Cotterell, R.: Language model evaluation beyond perplexity. arXiv preprint arXiv:2106.00085 (2021)","DOI":"10.18653\/v1\/2021.acl-long.414"},{"key":"18_CR24","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1007\/s10506-018-9225-1","volume":"26","author":"TS Nguyen","year":"2018","unstructured":"Nguyen, T.S., Nguyen, L.M., Tojo, S., Satoh, K., Shimazu, A.: Recurrent neural network-based models for recognizing requisite and effectuation parts in legal texts. Artif. Intell. Law 26, 169\u2013199 (2018)","journal-title":"Artif. Intell. Law"},{"issue":"10","key":"18_CR25","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":"18_CR26","unstructured":"Paul, S., Mandal, A., Goyal, P., Ghosh, S.: Pre-training transformers on indian legal text. arXiv preprint arXiv:2209.06049 (2022)"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Peters, M.E., et al.: Deep contextualized word representations (2018)","DOI":"10.18653\/v1\/N18-1202"},{"key":"18_CR28","doi-asserted-by":"publisher","unstructured":"Polo, F., et al.: Legalnlp - natural language processing methods for the Brazilian legal language. In: Anais do XVIII Encontro Nacional de Intelig\u00eancia Artificial e Computacional, pp. 763\u2013774. SBC, Porto Alegre (2021). https:\/\/doi.org\/10.5753\/eniac.2021.18301. https:\/\/sol.sbc.org.br\/index.php\/eniac\/article\/view\/18301","DOI":"10.5753\/eniac.2021.18301"},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Sang, E.F., Veenstra, J.: Representing text chunks. arXiv preprint arXiv:cs\/9907006 (1999)","DOI":"10.3115\/977035.977059"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. arXiv preprint arXiv:1508.07909 (2015)","DOI":"10.18653\/v1\/P16-1162"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Shao, Y., et al.: Bert-pli: modeling paragraph-level interactions for legal case retrieval. In: IJCAI, pp. 3501\u20133507 (2020)","DOI":"10.24963\/ijcai.2020\/484"},{"key":"18_CR32","unstructured":"Sistema de gest\u00e3o de tabelas processuais unificadas. https:\/\/www.cnj.jus.br\/sgt\/consulta_publica_assuntos.php. Accessed 09 Aug 2022"},{"key":"18_CR33","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","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.) BRACIS 2020. LNCS (LNAI), vol. 12319, pp. 403\u2013417. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-61377-8_28"},{"key":"18_CR34","first-page":"1","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30, 1\u201311 (2017)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"18_CR35","unstructured":"Viegas, C.F.O.: Jurisbert: transformer-based model for embedding legal texts (2022)"},{"key":"18_CR36","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wang, P., Huang, L., Sun, X., Wang, H.: Incorporating hierarchy into text encoder: a contrastive learning approach for hierarchical text classification. arXiv preprint arXiv:2203.03825 (2022)","DOI":"10.18653\/v1\/2022.acl-long.491"},{"key":"18_CR37","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1016\/j.aiopen.2021.06.003","volume":"2","author":"C Xiao","year":"2021","unstructured":"Xiao, C., Hu, X., Liu, Z., Tu, C., Sun, M.: Lawformer: a pre-trained language model for Chinese legal long documents. AI Open 2, 79\u201384 (2021)","journal-title":"AI Open"},{"key":"18_CR38","unstructured":"Yang, Y., Uy, M.C.S., Huang, A.: Finbert: a pretrained language model for financial communications. arXiv preprint arXiv:2006.08097 (2020)"}],"container-title":["Lecture Notes in Computer Science","Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-45392-2_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T16:49:49Z","timestamp":1710348589000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-45392-2_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031453915","9783031453922"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-45392-2_18","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":"12 October 2023","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":"Belo Horizonte","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bracis2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.bracis.dcc.ufmg.br","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":"JEMS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"242","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":"90","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":"37% - 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":"5","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)"}}]}}