Is text normalization relevant for classifying medieval charters?
This work addresses document analysis for historians and archivists, but it is incremental as it focuses on specific tasks and datasets.
The study investigated whether historical text normalization improves classification of medieval charters for dating and locating tasks, finding that normalization minimally aids locating but reduces dating accuracy, with support vector machines and gradient boosting outperforming transformers.
This study examines the impact of historical text normalization on the classification of medieval charters, specifically focusing on document dating and locating. Using a data set of Middle High German charters from a digital archive, we evaluate various classifiers, including traditional and transformer-based models, with and without normalization. Our results indicate that the given normalization minimally improves locating tasks but reduces accuracy for dating, implying that original texts contain crucial features that normalization may obscure. We find that support vector machines and gradient boosting outperform other models, questioning the efficiency of transformers for this use case. Results suggest a selective approach to historical text normalization, emphasizing the significance of preserving some textual characteristics that are critical for classification tasks in document analysis.