PHD: Pixel-Based Language Modeling of Historical Documents
This work addresses the challenge for historians of analyzing noisy OCR-converted historical documents by treating them as images, offering a novel approach with potential domain-specific impact.
The paper tackles the problem of analyzing historical documents by proposing a pixel-based language model that reconstructs masked image patches, trained on synthetic and real historical scans, and demonstrates its proficiency in reconstruction and language understanding, achieving successful application to a historical QA task.
The digitisation of historical documents has provided historians with unprecedented research opportunities. Yet, the conventional approach to analysing historical documents involves converting them from images to text using OCR, a process that overlooks the potential benefits of treating them as images and introduces high levels of noise. To bridge this gap, we take advantage of recent advancements in pixel-based language models trained to reconstruct masked patches of pixels instead of predicting token distributions. Due to the scarcity of real historical scans, we propose a novel method for generating synthetic scans to resemble real historical documents. We then pre-train our model, PHD, on a combination of synthetic scans and real historical newspapers from the 1700-1900 period. Through our experiments, we demonstrate that PHD exhibits high proficiency in reconstructing masked image patches and provide evidence of our model's noteworthy language understanding capabilities. Notably, we successfully apply our model to a historical QA task, highlighting its usefulness in this domain.