{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:06:06Z","timestamp":1750309566549,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T00:00:00Z","timestamp":1734307200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Endowments for the Humanities","award":["HAA-287903-22"],"award-info":[{"award-number":["HAA-287903-22"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,16]]},"DOI":"10.1145\/3677389.3702578","type":"proceedings-article","created":{"date-parts":[[2025,3,13]],"date-time":"2025-03-13T16:53:52Z","timestamp":1741884832000},"page":"1-5","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Seventeenth-Century Spanish American Notary Records for Fine-Tuning Spanish Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1513-7521","authenticated-orcid":false,"given":"Shraboni","family":"Sarker","sequence":"first","affiliation":[{"name":"University of Missouri, Columbia, MO, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2483-1626","authenticated-orcid":false,"given":"Ahmad Tamim","family":"Hamad","sequence":"additional","affiliation":[{"name":"The University of Missouri, Columbia, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8012-3501","authenticated-orcid":false,"given":"Hulayyil","family":"Alshammari","sequence":"additional","affiliation":[{"name":"The University of Missouri, Columbia, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6350-6995","authenticated-orcid":false,"given":"Viviana","family":"Grieco","sequence":"additional","affiliation":[{"name":"University of Missouri-Kansas City, Columbia, MO, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1859-0438","authenticated-orcid":false,"given":"Praveen","family":"Rao","sequence":"additional","affiliation":[{"name":"Electrical Engineering and Computer Science, The University of Missouri, Columbia, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,3,13]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3475720.3484443"},{"key":"e_1_3_2_1_2_1","first-page":"1","article-title":"Character Recognition of Seventeenth-Century Spanish American Notary Records Using Deep Learning","volume":"15","author":"Alrasheed Nouf","year":"2021","unstructured":"Nouf Alrasheed, Praveen Rao, and Viviana Grieco. 2021. Character Recognition of Seventeenth-Century Spanish American Notary Records Using Deep Learning. Digital Humanities Quarterly (DHQ) 15, 4 (2021), 1--16.","journal-title":"Digital Humanities Quarterly (DHQ)"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Nouf Alrasheed Shraboni Sarker Viviana Grieco and Praveen Rao. 2023. Few-Shot Learning for Word Recognition in Handwritten Seventeenth-Century Spanish American Notary Records. In ACM Multimedia Asia. Tainan Taiwan 1--5.","DOI":"10.1145\/3595916.3626365"},{"key":"e_1_3_2_1_4_1","volume-title":"Spanish Pre-trained BERT Model and Evaluation Data. arXiv preprint arXiv:2308.02976","author":"Ca\u00f1ete Jos\u00e9","year":"2023","unstructured":"Jos\u00e9 Ca\u00f1ete, Gabriel Chaperon, Rodrigo Fuentes, Jou-Hui Ho, Hojin Kang, and Jorge P\u00e9rez. 2023. Spanish Pre-trained BERT Model and Evaluation Data. arXiv preprint arXiv:2308.02976 (2023)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/1631862.1631865"},{"key":"e_1_3_2_1_6_1","unstructured":"Databricks. 2024. Databricks spent $10M on new DBRX generative AI model. https:\/\/techcrunch.com\/2024\/03\/27\/databricks-spent-10m-on-a-generative-ai-model-that-still-cant-beat-gpt-4"},{"key":"e_1_3_2_1_7_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Association for Computational Linguistics, Minneapolis, Minnesota, 4171--4186."},{"key":"e_1_3_2_1_8_1","unstructured":"Hugging Face. 2023. Fine-tuning a masked language model. https:\/\/huggingface.co\/learn\/nlp-course\/en\/chapter7\/3."},{"volume-title":"Deep Learning","author":"Goodfellow Ian J.","key":"e_1_3_2_1_9_1","unstructured":"Ian J. Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep Learning. MIT Press, Cambridge, MA, USA."},{"volume-title":"2019 International Conference on Document Analysis and Recognition (ICDAR). 17--24","author":"Ingle R. Reeve","key":"e_1_3_2_1_10_1","unstructured":"R. Reeve Ingle, Yasuhisa Fujii, Thomas Deselaers, Jonathan Baccash, and Ashok C. Popat. 2019. A Scalable Handwritten Text Recognition System. In 2019 International Conference on Document Analysis and Recognition (ICDAR). 17--24."},{"key":"e_1_3_2_1_11_1","volume-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach. ArXiv abs\/1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. ArXiv abs\/1907.11692 (2019)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging6100110"},{"volume-title":"Proceedings of the LREC 2020 Workshop on Multilingual Biomedical Text Processing (Multilingual-BIO)","author":"\u00dabeda Pilar L\u00f3pez","key":"e_1_3_2_1_13_1","unstructured":"Pilar L\u00f3pez \u00dabeda, Manuel Carlos D\u00edaz-Galiano, L. Alfonso Urena Lopez, Maite Martin, Teodoro Mart\u00edn-Noguerol, and Antonio Luna. 2020. Transfer learning applied to text classification in Spanish radiological reports. Proceedings of the LREC 2020 Workshop on Multilingual Biomedical Text Processing (Multilingual-BIO), Marseille, France, 29--32."},{"key":"e_1_3_2_1_14_1","unstructured":"Meta. 2023. Llama2. https:\/\/llama.meta.com\/llama2\/"},{"key":"e_1_3_2_1_15_1","unstructured":"Prasad Nageshkar. 2021. Multi-label Text Classification using Transformers (BERT). https:\/\/medium.com\/analytics-vidhya\/multi-label-text-classification-using-transformers-bert-93460838e62b."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3332997"},{"key":"e_1_3_2_1_17_1","unstructured":"National Archives of Argentina. 2024. Archivo General de la Naci\u00f3n. https:\/\/www.argentina.gob.ar\/."},{"key":"e_1_3_2_1_18_1","unstructured":"Catalogue of Tools & Metrics for Trustworthy AI. 2023. Exact Match Metric. https:\/\/oecd.ai\/en\/catalogue\/metrics\/exact-match"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"OpenAI. 2023. ChatGPT-3.5. https:\/\/www.openai.com Accessed: 2024-05-27.","DOI":"10.5114\/phr.2023.133714"},{"key":"e_1_3_2_1_20_1","unstructured":"OpenAI. 2024. ChatGPT-4.0. https:\/\/www.openai.com Accessed: 2024-05-27."},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL). 311--318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. BLEU: a Method for Automatic Evaluation of Machine Translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL). 311--318."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1493"},{"key":"e_1_3_2_1_23_1","unstructured":"Natalia Silva Prada. 2023. Paleograf\u00edas Americanas (Americans Paleographies). https:\/\/paleografi.hypotheses.org\/."},{"key":"e_1_3_2_1_24_1","volume-title":"KGSAR: A Knowledge Graph-Based Tool for Managing Spanish Colonial Notary Records. International Semantic Web Conference","author":"Prasanna Shivika","year":"2022","unstructured":"Shivika Prasanna, Nouf Alrasheed, Parshad Suthar, Pooja Purushatma, Praveen Rao, and Viviana Grieco. 2022. KGSAR: A Knowledge Graph-Based Tool for Managing Spanish Colonial Notary Records. International Semantic Web Conference, Hangzhou, China, 1--5."},{"key":"e_1_3_2_1_25_1","unstructured":"Label Studio. 2024. LabelImg. https:\/\/github.com\/HumanSignal\/labelImg"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2595188.2595193"},{"key":"e_1_3_2_1_27_1","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141 ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems, Vol. 30. Curran Associates, Inc."},{"volume-title":"Introduction to Paleography: Tools for Reading and Analyzing Ancient Documents","author":"Ezequiel Wasserman Mart\u00edn Leandro","key":"e_1_3_2_1_28_1","unstructured":"Mart\u00edn Leandro Ezequiel Wasserman. 2019. La escritura paleogr\u00e1fica iberoamericana: letras procesales y encadenadas (Ibero-American paleographic writing: procedural and chained letters). In Introduction to Paleography: Tools for Reading and Analyzing Ancient Documents. National University of La Plata. Faculty of Humanities and Educational Sciences, 199--217."},{"key":"e_1_3_2_1_29_1","unstructured":"Wikidata. 2023. Welcome to Wikidata. https:\/\/www.wikidata.org\/ Accessed: 2024-06-03."},{"key":"e_1_3_2_1_30_1","unstructured":"Yazhou Zhang Mengyao Wang Chenyu Ren Qiuchi Li Prayag Tiwari Benyou Wang and Jing Qin. 2024. Pushing The Limit of LLM Capacity for Text Classification. arXiv:2402.07470 [cs.CL]"}],"event":{"name":"JCDL '24: 24th ACM\/IEEE Joint Conference on Digital Libraries","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","IEEE TCDL"],"location":"Hong Kong China","acronym":"JCDL '24"},"container-title":["Proceedings of the 24th ACM\/IEEE Joint Conference on Digital Libraries"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3677389.3702578","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3677389.3702578","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:19:07Z","timestamp":1750295947000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3677389.3702578"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,16]]},"references-count":30,"alternative-id":["10.1145\/3677389.3702578","10.1145\/3677389"],"URL":"https:\/\/doi.org\/10.1145\/3677389.3702578","relation":{},"subject":[],"published":{"date-parts":[[2024,12,16]]},"assertion":[{"value":"2025-03-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}