TY  - GEN
ID  - heidok31416
CY  - Taipeh, ROC
AV  - public
N1  - Chinese Title: ??????????????????????
Y1  - 2024///
TI  - Language Model Assisted OCR Classification for Republican Chinese Newspaper Text
PB  - Taiwanese Association for Digital Humanities
N2  - In this work, we present methods to obtain a neural optical character recognition (OCR) tool for article blocks in a Republican Chinese newspaper. Our basis is a small fraction of the image corpus for which text ground truth exists. We introduce a character segmentation method which produces over 90,000 labeled images of single characters and train a GoogLeNet classifier as an OCR model. In addition, we create synthetic training data from character images extracted from Song-Ti fonts. Randomly augmented on the fly and used for pre-training, they increase OCR accuracy from 95.49% to 96.95% on our test set. Finally, we employ post-OCR correction based on a pre-trained masked language model and present heuristics to select the required hyperparameters, by which we are able to correct 16% of remaining classification errors, increasing accuracy on the test set to 97.44%.
A1  - Henke, Konstantin
A1  - Arnold, Matthias
UR  - http://doi.org/10.6853/DADH.202310_(12).0001
ER  -