Diachronic Document Dataset for Semantic Layout Analysis
This provides a resource for document recreation workflows, addressing layout complexities across historical periods and genres, but it is incremental as it focuses on dataset creation and evaluation.
The authors tackled the problem of semantic layout analysis by creating a new dataset of 7,254 annotated pages spanning 1600-2024, and found that a 1280-pixel input size for YOLO is optimal and subset-based training works best when incorporated into a generic model.
We present a novel, open-access dataset designed for semantic layout analysis, built to support document recreation workflows through mapping with the Text Encoding Initiative (TEI) standard. This dataset includes 7,254 annotated pages spanning a large temporal range (1600-2024) of digitised and born-digital materials across diverse document types (magazines, papers from sciences and humanities, PhD theses, monographs, plays, administrative reports, etc.) sorted into modular subsets. By incorporating content from different periods and genres, it addresses varying layout complexities and historical changes in document structure. The modular design allows domain-specific configurations. We evaluate object detection models on this dataset, examining the impact of input size and subset-based training. Results show that a 1280-pixel input size for YOLO is optimal and that training on subsets generally benefits from incorporating them into a generic model rather than fine-tuning pre-trained weights.