2 papers
cs.CL2021
Neural OCR Post-Hoc Correction of Historical Corpora
Lijun Lyu, Maria Koutraki, Martin Krickl +1
Optical character recognition (OCR) is crucial for a deeper access to historical collections. OCR needs to account for orthographic variations, typefaces, or language evolution (i.…
cs.DL2020
Identifying Historical Travelogues in Large Text Corpora Using Machine Learning
Jan Rörden, Doris Gruber, Martin Krickl +1
Travelogues represent an important and intensively studied source for scholars in the humanities, as they provide insights into people, cultures, and places of the past. However, e…