{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T17:21:01Z","timestamp":1769102461108,"version":"3.49.0"},"reference-count":14,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,15]]},"DOI":"10.1109\/bigdata62323.2024.10826028","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:23Z","timestamp":1737052283000},"page":"8620-8622","source":"Crossref","is-referenced-by-count":1,"title":["Making History Readable"],"prefix":"10.1109","author":[{"given":"Bipasha","family":"Banerjee","sequence":"first","affiliation":[{"name":"University Libraries Virginia Tech,Blacksburg,VA,USA"}]},{"given":"Jennifer","family":"Goyne","sequence":"additional","affiliation":[{"name":"University Libraries Virginia Tech,Blacksburg,VA,USA"}]},{"given":"William A.","family":"Ingram","sequence":"additional","affiliation":[{"name":"University Libraries Virginia Tech,Blacksburg,VA,USA"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Digital Libraries & Repositories","author":"Platform","year":"2024"},{"key":"ref2","first-page":"1326","volume-title":"Optical character recognition (OCR)","author":"Srihari","year":"2003"},{"key":"ref3","article-title":"The 6 Biggest OCR Problems and How to Overcome Them","author":"Marketing"},{"key":"ref4","article-title":"pytesseract: Python-tesseract is a python wrapper for Google\u2019s Tesseract-OCR","author":"Hoffstaetter"},{"key":"ref5","article-title":"Tesseract documentation"},{"key":"ref6","article-title":"OCR Software, Data Extraction Tool - Amazon Textract - AWS","author":"Services","year":"2019"},{"key":"ref7","first-page":"5998","article-title":"Attention is all you need","volume-title":"Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA","author":"Vaswani"},{"key":"ref8","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"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)","author":"Devlin"},{"key":"ref9","article-title":"Llama 3.2 model card","year":"2024"},{"key":"ref10","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref11","article-title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","author":"Abdin","year":"2024"},{"key":"ref12","article-title":"Virginia Tech Digital Libraries | Silas H. Stepp Letters"},{"key":"ref13","article-title":"Virginia Tech Digital Libraries | Montgomery Museum"},{"key":"ref14","article-title":"Virginia Tech Digital Libraries | Newman Library Map Collection"}],"event":{"name":"2024 IEEE International Conference on Big Data (BigData)","location":"Washington, DC, USA","start":{"date-parts":[[2024,12,15]]},"end":{"date-parts":[[2024,12,18]]}},"container-title":["2024 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10824975\/10824942\/10826028.pdf?arnumber=10826028","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:08:58Z","timestamp":1737101338000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10826028\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,15]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/bigdata62323.2024.10826028","relation":{},"subject":[],"published":{"date-parts":[[2024,12,15]]}}}