{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T06:11:32Z","timestamp":1757311892436,"version":"3.37.3"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,6,17]],"date-time":"2023-06-17T00:00:00Z","timestamp":1686960000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,6,17]],"date-time":"2023-06-17T00:00:00Z","timestamp":1686960000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100003593","name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004901","name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de Minas Gerais","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004901","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Lang Resources & Evaluation"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1007\/s10579-023-09665-0","type":"journal-article","created":{"date-parts":[[2023,6,17]],"date-time":"2023-06-17T05:01:45Z","timestamp":1686978105000},"page":"1315-1333","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["CachacaNER: a dataset for named entity recognition in texts about the cacha\u00e7a beverage"],"prefix":"10.1007","volume":"58","author":[{"given":"Priscilla","family":"Silva","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arthur","family":"Franco","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thiago","family":"Santos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mozar","family":"Brito","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Denilson","family":"Pereira","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,6,17]]},"reference":[{"key":"9665_CR1","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1109\/DAS.2016.15","volume-title":"Proceedings of the 12th IAPR workshop on document analysis systems","author":"C Adak","year":"2016","unstructured":"Adak, C., Chaudhuri, B. B., & Blumenstein, M. (2016). Named entity recognition from unstructured handwritten document images. Proceedings of the 12th IAPR workshop on document analysis systems (pp. 375\u2013380). https:\/\/doi.org\/10.1109\/DAS.2016.15"},{"key":"9665_CR2","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-98305-5","volume-title":"Proceedings of the 11th International conference on computational processing of the portuguese language (propor)","author":"HO Albuquerque","year":"2022","unstructured":"Albuquerque, H. O., Costa, R., Silvestre, G., Souza, E., da Silva, N. F. F., Vit\u00f3rio, D., Moriyama, G., Martins, L., Soezima, L., Nunes, A., Siqueira, F., Tarrega, J. P., Beinotti, J. V., Dias, M., Silva, M., Gardini, M., Silva, V., de Carvalho, A. C. P. L. F., & Oliveira, A. L. I. (2022). UlyssesNER-Br: a corpus of brazilian legislative documents for named entity recognition. Proceedings of the 11th International conference on computational processing of the portuguese language (propor) (pp. 3\u201314). Springer-Verlag. https:\/\/doi.org\/10.1007\/978-3-030-98305-5"},{"key":"9665_CR3","volume-title":"Influ\u00eancia da madeira na qualidade qu\u00edmica e sensorial da aguardente de cana envelhecida (Unpublished doctoral dissertation)","author":"AM Bortoletto","year":"2016","unstructured":"Bortoletto, A. M. (2016). Influ\u00eancia da madeira na qualidade qu\u00edmica e sensorial da aguardente de cana envelhecida (Unpublished doctoral dissertation). Escola Superior de Agricultura."},{"key":"9665_CR4","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1007\/978-3-319-99722-3_32","volume-title":"Proceedings of the 13th international conference on computational processing of the portuguese language (propor)","author":"PHL de Araujo","year":"2018","unstructured":"de Araujo, P. H. L., de Campos, T., Oliveria, R., Stauffer, M., Couto, S., & de Souza Bermejo, P. (2018). LeNER-Br: A dataset for named entity recognition in brazilian legal text. Proceedings of the 13th international conference on computational processing of the portuguese language (propor) (pp. 313\u2013323). Springer. https:\/\/doi.org\/10.1007\/978-3-319-99722-3_32"},{"key":"9665_CR5","doi-asserted-by":"publisher","first-page":"4171","DOI":"10.18653\/v1\/N19-1423","volume-title":"Proceedings of the 2019 conference of the north American chapter of the association for computational linguistics","author":"J Devlin","year":"2019","unstructured":"Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 conference of the north American chapter of the association for computational linguistics (pp. 4171\u20134186). Minnesota Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/N19-1423"},{"key":"9665_CR6","unstructured":"ExpoCacha\u00e7a (2022). N\u00fameros da cacha\u00e7a: A import\u00e2ncia do mercado da cacha\u00e7a no brasil e no mundo. Retrieved September, 2022 from https:\/\/www.expocachaca.com.br\/numeros-da-cachaca"},{"key":"9665_CR7","doi-asserted-by":"publisher","DOI":"10.1037\/h0031619","author":"JL Fleiss","year":"1971","unstructured":"Fleiss, J. L. (1971). Measuring nominal scale agreement among many raters. Psychological Bulletin. https:\/\/doi.org\/10.1037\/h0031619","journal-title":"Psychological Bulletin"},{"key":"9665_CR8","volume-title":"Proceedings of the seventh international conference on language resources and evaluation","author":"C Freitas","year":"2010","unstructured":"Freitas, C., Mota, C., Santos, D., Oliveira, H. G., & Carvalho, P. (2010). Second HAREM: Advancing the state of the art of named entity recognition in Portuguese. Proceedings of the seventh international conference on language resources and evaluation. European Language Resources Association."},{"key":"9665_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2018.06.001","author":"A Goyal","year":"2018","unstructured":"Goyal, A., Gupta, V., & Kumar, M. (2018). Recent named entity recognition and classification techniques: A systematic review. Computer Science Review. https:\/\/doi.org\/10.1016\/j.cosrev.2018.06.001","journal-title":"Computer Science Review"},{"key":"9665_CR10","unstructured":"Instituto Brasileiro da Cacha\u00e7a (2022). IBRAC. Retrieved September, 2022, from https:\/\/ibrac.net\/"},{"key":"9665_CR11","doi-asserted-by":"publisher","DOI":"10.1017\/jwe.2022.2","author":"D Katumullage","year":"2022","unstructured":"Katumullage, D., Yang, C., Barth, J., & Cao, J. (2022). Using neural network models for wine review classification. Journal of Wine Economics. https:\/\/doi.org\/10.1017\/jwe.2022.2","journal-title":"Journal of Wine Economics"},{"key":"9665_CR12","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btg1023","author":"JD Kim","year":"2003","unstructured":"Kim, J. D., Ohta, T., Tateisi, Y., & Tsujii, J. (2003). GENIA corpus\u2014a semantically annotated corpus for bio-textmining. Bioinformatics. https:\/\/doi.org\/10.1093\/bioinformatics\/btg1023","journal-title":"Bioinformatics"},{"key":"9665_CR13","doi-asserted-by":"publisher","first-page":"159","DOI":"10.2307\/2529310","volume":"331","author":"JR Landis","year":"1977","unstructured":"Landis, J. R., & Koch, G. G. (1977). The measurement of observer agreement for categorical data. Biometrics, 331, 159\u2013174.","journal-title":"Biometrics"},{"key":"9665_CR14","unstructured":"Lefever, E. , Hendrickx, I. , Croijmans, I. , van\u00a0den Bosch, A., Majid, A. (2018). Discovering the language of wine reviews: A text mining account.\u00a0 Proceedings of the eleventh international conference on language resources and evaluation (LREC). European Language Resources Association (ELRA)"},{"key":"9665_CR15","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/TKDE.2020.2981314","volume":"341","author":"J Li","year":"2022","unstructured":"Li, J., Sun, A., Han, J., & Li, C. (2022). A survey on deep learning for named entity recognition. IEEE Transactions on Knowledge and Data Engineering, 341, 50\u201370. https:\/\/doi.org\/10.1109\/TKDE.2020.2981314","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"9665_CR16","first-page":"121","volume":"1171","author":"C Malarkodi","year":"2016","unstructured":"Malarkodi, C., Lex, E., & Devi, S. L. (2016). Named entity recognition for the agricultural domain. Research in Computing Science, 1171, 121\u2013132.","journal-title":"Research in Computing Science"},{"key":"9665_CR17","unstructured":"Mendon\u00e7a, C. A. E. Jr., Barbosa, L. A., Macedo, H. T., S\u00e3o Crist\u00f3v\u00e3o, S. (2015). Paramopama: a Brazilian-Portuguese corpus for named entity recognition. XII encontro nacional de intelig\u00eancia artificial e computacional (ENIAC): SBC."},{"key":"9665_CR18","doi-asserted-by":"crossref","unstructured":"Menezes, D. S. , Savarese, P., Milidi\u00fa, R. L. (2019). Building a massive corpus for named entity recognition using free open data sources. Preprint retrieved from\u00a0https:\/\/arvix.org\/abs\/1908.05758v1","DOI":"10.1109\/BRACIS.2019.00011"},{"key":"9665_CR19","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1075\/li.30.1.03nad","volume":"30","author":"D Nadeau","year":"2007","unstructured":"Nadeau, D., & Sekine, S. (2007). A survey of named entity recognition and classification. Lingvistic\u00e6 Investigationes, 30, 13\u201326. https:\/\/doi.org\/10.1075\/li.30.1.03nad","journal-title":"Lingvistic\u00e6 Investigationes"},{"key":"9665_CR20","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1016\/j.artint.2012.03.006","volume":"194","author":"J Nothman","year":"2013","unstructured":"Nothman, J., Ringland, N., Radford, W., Murphy, T., & Curran, J. R. (2013). Learning multilingual named entity recognition from wikipedia. Artificial Intelligence, 194, 151\u2013175. https:\/\/doi.org\/10.1016\/j.artint.2012.03.006","journal-title":"Artificial Intelligence"},{"key":"9665_CR21","doi-asserted-by":"publisher","DOI":"10.3390\/fermentation4040084","author":"J Palmer","year":"2018","unstructured":"Palmer, J., & Chen, B. (2018). Wineinformatics: Regression on the grade and price of wines through their sensory attributes. Fermentation. https:\/\/doi.org\/10.3390\/fermentation4040084","journal-title":"Fermentation"},{"key":"9665_CR22","doi-asserted-by":"publisher","first-page":"1946","DOI":"10.18653\/v1\/P17-1178","volume-title":"Proceedings of the 55th annual meeting of the association for computational linguistics","author":"X Pan","year":"2017","unstructured":"Pan, X., Zhang, B., May, J., Nothman, J., Knight, K., & Ji, H. (2017). Cross-lingual name tagging and linking for 282 languages. Proceedings of the 55th annual meeting of the association for computational linguistics (pp. 1946\u20131958). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/P17-1178"},{"key":"9665_CR23","doi-asserted-by":"publisher","DOI":"10.1145\/3148011.3154478","volume-title":"Proceedings of the knowledge capture conference","author":"R Peres","year":"2017","unstructured":"Peres, R., Esteves, D., & Maheshwari, G. (2017). Bidirectional LSTM with a context input window for named entity recognition in tweets. Proceedings of the knowledge capture conference. Association for Computing Machinery. https:\/\/doi.org\/10.1145\/3148011.3154478"},{"key":"9665_CR24","volume-title":"Avalia\u00e7\u00e3o sensorial das bebidas aguardente de cana industrial e cacha\u00e7a de alambique (Unpublished doctoral dissertation)","author":"SHDM Pinheiro","year":"2010","unstructured":"Pinheiro, S. H. D. M. (2010). Avalia\u00e7\u00e3o sensorial das bebidas aguardente de cana industrial e cacha\u00e7a de alambique (Unpublished doctoral dissertation). Universidade Federal de Vi\u00e7osa."},{"key":"9665_CR25","volume-title":"Proceedings of the third workshop on very large corpora","author":"L Ramshaw","year":"1995","unstructured":"Ramshaw, L., & Marcus, M. (1995). Text chunking using transformation-based learning. Proceedings of the third workshop on very large corpora. Association for Computational Linguistics."},{"key":"9665_CR26","volume-title":"Proceedings of the 6th conference on natural language learning","author":"EFTK Sang","year":"2002","unstructured":"Sang, E. F. T. K. (2002). Introduction to the CoNLL-2002 shared task: Language-independent named entity recognition. Proceedings of the 6th conference on natural language learning. Association for Computational Linguistics."},{"key":"9665_CR27","first-page":"142","volume-title":"Proceedings of the 7th conference on natural language learning","author":"EFTK Sang","year":"2003","unstructured":"Sang, E. F. T. K., & de Meulder, F. (2003). Introduction to the CoNLL-2003 shared task: Language-independent named entity recognition. Proceedings of the 7th conference on natural language learning (pp. 142\u2013147). Association for Computational Linguistics."},{"key":"9665_CR28","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/11751984_8","volume-title":"International workshop on computational processing of the portuguese language","author":"D Santos","year":"2006","unstructured":"Santos, D., & Cardoso, N. (2006). A golden resource for named entity recognition in portuguese. International workshop on computational processing of the portuguese language (pp. 69\u201379). Springer."},{"key":"9665_CR29","doi-asserted-by":"publisher","first-page":"473","DOI":"10.5220\/0010443204730483","volume-title":"Proceedings of the 23rd international conference on enterprise information systems","author":"D Santos","year":"2021","unstructured":"Santos, D., Dutra, F., Parreiras, F., & Brand\u00e3o, W. (2021). Assessing the effectiveness of multilingual transformer-based text embeddings for named entity recognition in portuguese. Proceedings of the 23rd international conference on enterprise information systems (pp. 473\u2013483). SciTePress. https:\/\/doi.org\/10.5220\/0010443204730483"},{"key":"9665_CR30","volume-title":"Proceedings of the fifth international conference on language resources and evaluation","author":"D Santos","year":"2006","unstructured":"Santos, D., Seco, N., Cardoso, N., & Vilela, R. (2006). HAREM: An advanced NER evaluation contest for Portuguese. Proceedings of the fifth international conference on language resources and evaluation. European Language Resources Association."},{"key":"9665_CR31","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1007\/s11036-020-01644-x","volume":"26","author":"RDA Silva","year":"2021","unstructured":"Silva, R. D. A., Silva, L. D., Dutra, M. L., & Araujo, G. M. D. (2021). An improved ner methodology to the portuguese language. Mobile Networks and Applications, 26, 319\u2013325. https:\/\/doi.org\/10.1007\/s11036-020-01644-x","journal-title":"Mobile Networks and Applications"},{"key":"9665_CR32","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. (2020). Bertimbau: Pretrained bert models for brazilian portuguese. In R. Cerri & R. C. Prati (Eds.), Intelligent systems (pp. 403\u2013417). ChamSpringer International Publishing."},{"key":"9665_CR33","unstructured":"Yadav, V., Bethard, S. (2019). A survey on recent advances in named entity recognition from deep learning models. Preprint retrieved from\u00a0\u00a0https:\/\/arxiv.org\/1910.11470v1"},{"key":"9665_CR34","first-page":"1361","volume-title":"Proceedings of the International conference on computational linguistics","author":"MA Yosef","year":"2012","unstructured":"Yosef, M. A., Bauer, S., Hoffart, J., Spaniol, M., & Weikum, G. (2012). HYENA: Hierarchical type classification for entity names. Proceedings of the International conference on computational linguistics (pp. 1361\u20131370). ACL."}],"container-title":["Language Resources and Evaluation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-023-09665-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10579-023-09665-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-023-09665-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T10:07:57Z","timestamp":1730542077000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10579-023-09665-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,17]]},"references-count":34,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["9665"],"URL":"https:\/\/doi.org\/10.1007\/s10579-023-09665-0","relation":{},"ISSN":["1574-020X","1574-0218"],"issn-type":[{"type":"print","value":"1574-020X"},{"type":"electronic","value":"1574-0218"}],"subject":[],"published":{"date-parts":[[2023,6,17]]},"assertion":[{"value":"3 May 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 June 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}