{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T12:21:16Z","timestamp":1742991676008,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031216886"},{"type":"electronic","value":"9783031216893"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-21689-3_29","type":"book-chapter","created":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T10:03:56Z","timestamp":1668765836000},"page":"402-416","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Impact of\u00a0Morphological Segmentation on\u00a0Pre-trained Language Models"],"prefix":"10.1007","author":[{"given":"Matheus","family":"Westhelle","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4329-9228","authenticated-orcid":false,"given":"Luciana","family":"Bencke","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4400-054X","authenticated-orcid":false,"given":"Viviane P.","family":"Moreira","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,19]]},"reference":[{"key":"29_CR1","unstructured":"Al-Rfou, R.: Polyglot (2020). https:\/\/github.com\/aboSamoor\/polyglot"},{"key":"29_CR2","doi-asserted-by":"publisher","unstructured":"Bisong, E.: Google Colaboratory, pp. 59\u201364. Apress, Berkeley (2019). https:\/\/doi.org\/10.1007\/978-1-4842-4470-8_7","DOI":"10.1007\/978-1-4842-4470-8_7"},{"key":"29_CR3","doi-asserted-by":"crossref","unstructured":"Bostrom, K., Durrett, G.: Byte pair encoding is suboptimal for language model pretraining. In: Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 4617\u20134624. Online, November 2020","DOI":"10.18653\/v1\/2020.findings-emnlp.414"},{"key":"29_CR4","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 1877\u20131901. Curran Associates, Inc. (2020)"},{"key":"29_CR5","unstructured":"Chen, B., et al.: Probing BERT in hyperbolic spaces. In: International Conference on Learning Representations (2021)"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Creutz, M., Lagus, K.: Unsupervised discovery of morphemes. In: Proceedings of the ACL-02 Workshop on Morphological and Phonological Learning, pp. 21\u201330. Association for Computational Linguistics, July 2002","DOI":"10.3115\/1118647.1118650"},{"key":"29_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: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4171\u20134186, June 2019"},{"key":"29_CR8","unstructured":"Fonseca, E., Santos, L., Criscuolo, M., Aluisio, S.: Assin: Avaliacao de similaridade semantica e inferencia textual. In: Computational Processing of the Portuguese Language-12th International Conference, Tomar, Portugal, pp. 13\u201315 (2016)"},{"key":"29_CR9","unstructured":"GOMES, J.R.S.: Plue: Portuguese language understanding evaluation (2020). https:\/\/github.com\/jubs12\/PLUE"},{"key":"29_CR10","unstructured":"Hewitt, J., Manning, C.D.: A structural probe for finding syntax in word representations. In: NAACL (2019)"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Hofmann, V., Pierrehumbert, J.B., Sch\u00fctze, H.: Superbizarre is not superb: derivational morphology improves BERT\u2019s interpretation of complex words. In: ACL\/IJCNLP (2021)","DOI":"10.18653\/v1\/2021.acl-long.279"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Klein, S., Tsarfaty, R.: Getting the ##life out of living: how adequate are word-pieces for modelling complex morphology? In: Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, pp. 204\u2013209. Association for Computational Linguistics, Online, July 2020","DOI":"10.18653\/v1\/2020.sigmorphon-1.24"},{"key":"29_CR13","unstructured":"Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: AlBERT: a lite BERT for self-supervised learning of language representations. In: International Conference on Learning Representations (2020)"},{"key":"29_CR14","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv abs\/1907.11692 (2019)"},{"key":"29_CR15","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2019)"},{"key":"29_CR16","unstructured":"Micikevicius, P., et al.: Mixed precision training. In: International Conference on Learning Representations (2018)"},{"key":"29_CR17","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"324","DOI":"10.1007\/978-3-319-99722-3_33","volume-title":"Computational Processing of the Portuguese Language","author":"RA Monteiro","year":"2018","unstructured":"Monteiro, R.A., Santos, R.L.S., Pardo, T.A.S., de Almeida, T.A., Ruiz, E.E.S., Vale, O.A.: Contributions to the study of fake news in Portuguese: new corpus and automatic detection results. In: Villavicencio, A., et al. (eds.) PROPOR 2018. LNCS (LNAI), vol. 11122, pp. 324\u2013334. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-99722-3_33"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Nzeyimana, A., Rubungo, A.N.: KinyaBERT: a morphology-aware Kinyarwanda language model. In: ACL (2022)","DOI":"10.18653\/v1\/2022.acl-long.367"},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Park, H.H., Zhang, K.J., Haley, C., Steimel, K., Liu, H., Schwartz, L.: Morphology matters: a multilingual language modeling analysis. Trans. Assoc. Comput. Linguist. 9, 261\u2013276 (2021)","DOI":"10.1162\/tacl_a_00365"},{"key":"29_CR20","volume-title":"The Book of Why: The New Science of Cause and Effect","author":"J Pearl","year":"2018","unstructured":"Pearl, J., Mackenzie, D.: The Book of Why: The New Science of Cause and Effect, 1st edn. Basic Books Inc., New York (2018)","edition":"1"},{"key":"29_CR21","unstructured":"Santana, M.: News of the site Folha de S\u00e3o Paulo (Brazilian Newspaper), Version 2. https:\/\/www.kaggle.com\/datasets\/marlesson\/news-of-the-site-folhauol (2019). [Online; acessado em 24 de Novembro de 2021]"},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. In: ACL, pp. 1715\u20131725, August 2016","DOI":"10.18653\/v1\/P16-1162"},{"key":"29_CR23","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":"29_CR24","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. NIPS 2017, pp. 6000\u20136010. Curran Associates Inc., Red Hook (2017)"},{"key":"29_CR25","unstructured":"Virpioja, S., Smit, P., Gr\u00f6nroos, S.A., Kurimo, M.: Morfessor 2.0: Python implementation and extensions for Morfessor baseline (2013)"},{"key":"29_CR26","doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.: GLUE: a multi-task benchmark and analysis platform for natural language understanding. In: EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pp. 353\u2013355, November 2018","DOI":"10.18653\/v1\/W18-5446"},{"key":"29_CR27","unstructured":"Wu, Y., et al.: Google\u2019s neural machine translation system: bridging the gap between human and machine translation. arXiv abs\/1609.08144 (2016)"}],"container-title":["Lecture Notes in Computer Science","Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-21689-3_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,21]],"date-time":"2022-11-21T00:15:31Z","timestamp":1668989731000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-21689-3_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031216886","9783031216893"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-21689-3_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"19 November 2022","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":"Campinas","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bracis2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www2.sbc.org.br\/bracis2022\/","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":"225","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":"89","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":"40% - 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":"3","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":"4","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}