{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T21:50:49Z","timestamp":1774129849655,"version":"3.50.1"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031735028","type":"print"},{"value":"9783031735035","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T00:00:00Z","timestamp":1731715200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T00:00:00Z","timestamp":1731715200000},"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\/978-3-031-73503-5_22","type":"book-chapter","created":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T03:59:55Z","timestamp":1731643195000},"page":"267-279","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Open Sentence Embeddings for\u00a0Portuguese with\u00a0the\u00a0Serafim PT* Encoders Family"],"prefix":"10.1007","author":[{"given":"Lu\u00eds","family":"Gomes","sequence":"first","affiliation":[]},{"given":"Ant\u00f3nio","family":"Branco","sequence":"additional","affiliation":[]},{"given":"Jo\u00e3o","family":"Silva","sequence":"additional","affiliation":[]},{"given":"Jo\u00e3o","family":"Rodrigues","sequence":"additional","affiliation":[]},{"given":"Rodrigo","family":"Santos","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,16]]},"reference":[{"key":"22_CR1","unstructured":"Bajaj, P., Campos, D., Craswell, N., et\u00a0al.: MS\u00a0MARCO: a human generated machine reading comprehension dataset. arXiv:1611.09268 (2018)"},{"key":"22_CR2","unstructured":"Bonifacio, L., Jeronymo, V., Queiroz\u00a0Abonizio, H., et\u00a0al.: mMARCO: a multilingual version of the MS\u00a0MARCO passage ranking dataset. arXiv:2108.13897 (2022)"},{"key":"22_CR3","unstructured":"Carlsson, F., Gogoulou, E., Yli\u00e4\u00e4, E., Cuba\u00a0Gyllensten, A., Sahlgren, M.: Semantic re-tuning with contrastive tension. In: ICLR (2021)"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Cer, D., Diab, M., et\u00a0al.: SemEval-2017 task 1: semantic textual similarity multilingual and crosslingual focused evaluation. In: Proceedings of the 11th SemEval (2017)","DOI":"10.18653\/v1\/S17-2001"},{"key":"22_CR5","unstructured":"EUbookshop. https:\/\/bookshop.europa.eu\/"},{"key":"22_CR6","unstructured":"Fonseca, E., Santos, L., Criscuolo, M., Alu\u00edsio, S.: ASSIN: avalia\u00e7\u00e3o de similaridade sem\u00eantica e infer\u00eancia textual. In: 12th PROPOR, pp. 13\u201315 (2016)"},{"key":"22_CR7","unstructured":"Gomes, J.R.S.: PLUE: Portuguese language understanding evaluation (2020). https:\/\/github.com\/ju-resplande\/PLUE"},{"key":"22_CR8","unstructured":"Henderson, M., et\u00a0al.: Efficient natural language response suggestion for smart reply (2017)"},{"key":"22_CR9","unstructured":"Koehn, P.: Europarl: a parallel corpus for statistical machine translation. In: Proceedings of Machine Translation Summit X: Papers, pp. 79\u201386 (2005)"},{"key":"22_CR10","unstructured":"Li, X., Li, J.: AnglE-optimized text embeddings. arXiv:2309.12871 (2023)"},{"key":"22_CR11","unstructured":"Li, Z., Zhang, X., Zhang, Y., Long, D., Xie, P., Zhang, M.: Towards general text embeddings with multi-stage contrastive learning. arXiv:2308.03281 (2023)"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Melo, R., Santos, P.A., Dias, J.: A semantic search system for the Supremo Tribunal de Justi\u00e7a. In: Progress in Artificial Intelligence, pp. 142\u2013154 (2023)","DOI":"10.1007\/978-3-031-49011-8_12"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Muennighoff, N., Tazi, N., Magne, L., Reimers, N.: MTEB: massive text embedding benchmark. arXiv:2210.07316 (2022)","DOI":"10.18653\/v1\/2023.eacl-main.148"},{"key":"22_CR14","unstructured":"Os\u00f3rio, T., et\u00a0al.: PORTULAN ExtraGLUE datasets and models: kick-starting a benchmark for the neural processing of Portuguese. In: BUCC Workshop (2024)"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Real, L., Fonseca, E., Gon\u00e7alo\u00a0Oliveira, H.: The ASSIN 2 shared task: a quick overview. In: Proceedings of the 14th PROPOR, pp. 406\u2013412 (2020)","DOI":"10.1007\/978-3-030-41505-1_39"},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks. In: Proceedings of EMNLP-IJCNLP, pp. 3982\u20133992 (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Making monolingual sentence embeddings multilingual using knowledge distillation. In: Proceedings of EMNLP, pp. 4512\u20134525 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.365"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Rodrigues, J., Gomes, L., Silva, J., et\u00a0al.: Advancing neural encoding of Portuguese with Transformer Albertina PT-*. In: Proceedings of EPIA (2023)","DOI":"10.1007\/978-3-031-49008-8_35"},{"key":"22_CR19","unstructured":"Santos, R., Rodrigues, J., Gomes, L., et\u00a0al.: Fostering the ecosystem of open neural encoders for Portuguese with Albertina PT* family. arXiv:2403.01897 (2024)"},{"key":"22_CR20","unstructured":"Santos, R., Silva, J., et\u00a0al.: Advancing generative AI for Portuguese with open decoder Gerv\u00e1sio PT*. In: SIGUL workshop (2024)"},{"key":"22_CR21","unstructured":"Solatorio, A.V.: GISTEmbed: guided in-sample selection of training negatives for text embedding fine-tuning. arXiv preprint arXiv:2402.16829 (2024)"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Souza, F., Nogueira, R., Lotufo, R.: BERTimbau: pretrained BERT models for Brazilian Portuguese. In: Intelligent Systems, pp. 403\u2013417 (2020)","DOI":"10.1007\/978-3-030-61377-8_28"},{"key":"22_CR23","unstructured":"STSb Multi MT. https:\/\/huggingface.co\/datasets\/PhilipMay\/stsb_multi_mt"},{"key":"22_CR24","unstructured":"Su, J.: CoSENT: a more effective sentence vector scheme than Sentence BERT. https:\/\/kexue.fm\/archives\/8847"},{"key":"22_CR25","unstructured":"Tatoeba. https:\/\/tatoeba.org\/"},{"key":"22_CR26","unstructured":"Tiedemann, J.: Parallel data, tools and interfaces in OPUS. In: Proceedings of LREC, pp. 2214\u20132218 (2012)"},{"key":"22_CR27","unstructured":"Vaswani, A., et al.: Attention is all you need. NeurIPS 30 (2017)"},{"key":"22_CR28","doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., Michael, J., et\u00a0al.: GLUE: a multi-task benchmark and analysis platform for natural language understanding. In: Proceedings of the EMNLP Workshop BlackboxNLP (2018)","DOI":"10.18653\/v1\/W18-5446"},{"key":"22_CR29","doi-asserted-by":"crossref","unstructured":"Wang, K., Reimers, N., Gurevych, I.: TSDAE: using transformer-based sequential denoising auto-encoder for unsupervised sentence embedding learning. In: Findings of the Association for Computational Linguistics: EMNLP, pp. 671\u2013688 (2021)","DOI":"10.18653\/v1\/2021.findings-emnlp.59"},{"key":"22_CR30","unstructured":"Zhong, Q., et\u00a0al.: Toward efficient language model pretraining and downstream adaptation via self-evolution: a case study on SuperGLUE. arXiv:2212.01853 (2022)"}],"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\/978-3-031-73503-5_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T05:16:48Z","timestamp":1731647808000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73503-5_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,16]]},"ISBN":["9783031735028","9783031735035"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73503-5_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,16]]},"assertion":[{"value":"16 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"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":"Viana do Castelo","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"epia2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/epia2024.pt","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}