Preprint
Jul 2026
Semantic-Guided Reading Order Reconstruction in Historical Armenian Newspapers with LLMs
This paper addresses reading order reconstruction in historical Armenian newspapers with a new annotated dataset of 66 pages and compares geometric heuristics, YOLO-based layout parsing, an end-to-end document model ECLAIR, and a hybrid method combining semantic zone detection with a generative LLM.
Chahan Vidal-Gorène, Nadi Tomeh, Victoria Khurshudyan
· 1 citation