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.
Abstract
This paper addresses reading order reconstruction in historical Armenian newspapers, which combine complex layouts with limited language resources. We introduce a new annotated dataset of 66 pages and compare 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. Our hybrid method achieves the lowest error rates of all evaluated approaches, reducing ordering errors by up to 76% over the strongest geometric baseline, and remains robust in multi-page settings and under noisy OCR. Rather than targeting production the method is designed as a data bootstrapping strategy enabling rapid annotation in highly under-resourced scenarios. Alongside the dataset, we release a specialized Tesseract OCR model for historical Armenian print.
Understanding newspaper images remains a challenging task due to their complex, nested hierarchical structures and dense, heterogeneous layouts. In this paper, we explore two complementary approaches for newspaper structure understanding. First, we present a modular bottom-up pipeline that combines state-of-the-art ope...
William Mocaër, Solène Tarride, Thomas Constum et al.· arXiv.org· 0 citations
A practical framework that integrates prompt compression and topic modeling is proposed that overcomes context window limitations by compressing inputs while explicitly supplementing them with extracted topic words, thereby preserving global contextual information.
Hayata Shinjo, Israel Mendonça, Masayoshi Aritsugi· 0 citations
A regression-guided routing approach that prioritizes segments by predicted CER improvement, paired with a safeguard layer that detects harmful LLM corrections and routes uncertain segments to human review, and substantially outperforms standard confidence-based approaches is introduced.
Stergios Konstantinidis, Hayman Lotfy, Michalis Vlachos· Proceedings of the 2026 ACM...· 0 citations
The Institutional Newspapers Pipeline is presented, a modular system designed to extract high-quality, structured datasets from historical newspaper scans that was architected so that each step remains interpretable and customizable, and so that the pipeline as a whole remains computationally frugal enough to run on wo...
Matteo Cargnelutti, Catherine Brobston, Eben English et al.· 0 citations
This paper designs a comprehensive prompt that includes detailed instructions and examples and further enhance it using an LLM to produce language-specific prompts, and presents an XML-inspired annotation scheme that is more suitable for LLMs than the provided formats.
John B. Pavelka· Proceedings of the 2nd Joint...· 0 citations
Multilingual documents encapsulate rich regional cultures, scientific discoveries, and historical records. Parsing this content into structured, machine-readable formats is critical for unlocking global knowledge. However, existing benchmarks predominantly focus on high-resource languages like English and Chinese, crea...
Long Xu, Binghong Wu, Ting-Ting Yu et al.· 3 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
