Toward a Period-Specific Optimized Neural Network for OCR Error Correction of Historical Hebrew Texts
This work addresses the challenge of improving OCR accuracy for historical Hebrew documents, which is an incremental advance in domain-specific text processing.
The paper tackled the problem of OCR error correction for historical Hebrew texts by developing a multi-phase method to generate artificial training datasets and optimize hyperparameters, resulting in an effective neural network for this task.
Over the past few decades, large archives of paper-based historical documents, such as books and newspapers, have been digitized using the Optical Character Recognition (OCR) technology. Unfortunately, this broadly used technology is error-prone, especially when an OCRed document was written hundreds of years ago. Neural networks have shown great success in solving various text processing tasks, including OCR post-correction. The main disadvantage of using neural networks for historical corpora is the lack of sufficiently large training datasets they require to learn from, especially for morphologically-rich languages like Hebrew. Moreover, it is not clear what are the optimal structure and values of hyperparameters (predefined parameters) of neural networks for OCR error correction in Hebrew due to its unique features. Furthermore, languages change across genres and periods. These changes may affect the accuracy of OCR post-correction neural network models. To overcome these challenges, we developed a new multi-phase method for generating artificial training datasets with OCR errors and hyperparameters optimization for building an effective neural network for OCR post-correction in Hebrew.