# Mapping Armenian Paris: Extracting and Geocoding Commercial Advertisements from the 20th-Century Diaspora Press

arXiv: https://arxiv.org/abs/2608.05911 · HTML: https://mlsanity.com/paper/2608.05911/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 19 references that are in the map.
- First posted on arXiv 6 Aug 2026.

## Builds on (most cited first, 8 of 8)

- [LayoutLM: Pre-training of Text and Layout for Document Image Understanding](https://mlsanity.com/paper/1912.13318/) (2019)
- [Character Region Awareness for Text Detection](https://mlsanity.com/paper/1904.01941/) (2019)
- [DeepSeek-OCR: Contexts Optical Compression](https://mlsanity.com/paper/2510.18234/) (2025)
- [DeepSeek-OCR 2: Visual Causal Flow](https://mlsanity.com/paper/2601.20552/) (2026)
- [GLM-OCR Technical Report](https://mlsanity.com/paper/2603.10910/) (2026)
- [CHURRO: Making History Readable with an Open-Weight Large Vision-Language Model for High-Accuracy, Low-Cost Historical Text Recognition](https://mlsanity.com/paper/2509.19768/) (2025)
- [Under-resourced studies of under-resourced languages: lemmatization and POS-tagging with LLM annotators for historical Armenian, Georgian, Greek and Syriac](https://mlsanity.com/paper/2602.15753/) (2026)
- [Semantic-Guided Reading Order Reconstruction in Historical Armenian Newspapers with LLMs](https://mlsanity.com/paper/2607.00596/) (2026)

## Abstract (arXiv)

This paper presents an end-to-end, IIIF-based pipeline that turns the digitised Armenian press of France into an interactive map of the 20th-century Parisian Armenian commercial community. On each page, commercial advertisements are located, read, and parsed into structured records, which are then geocoded and placed on the map. Western Armenian is under-resourced and unsupported by off-the-shelf layout and OCR models, so the pipeline uses vision-language models (VLMs) as a data-bootstrapping strategy: they produce usable structured records at a scale hand annotation could not reach, and stay reliable on the strongly curved scans where conventional line-level CRNN OCR breaks down. The contribution includes a 500-page Western Armenian press corpus with 3,270 advertisement-level annotations, a Label Studio template that captures detection and semantic fields in a single annotation pass, and a reproducible workflow transposable to other under-resourced historical corpora. More broadly, the work shows that VLM-driven data bootstrapping is an effective lever for under-resourced historical languages such as (Western) Armenian.