# Digital Editions as Distant Supervision for Layout Analysis of Printed Books

arXiv: https://arxiv.org/abs/2112.12703 · HTML: https://mlsanity.com/paper/2112.12703/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 26 references that are in the map.
- First posted on arXiv 23 Dec 2021.

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

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [PubLayNet: largest dataset ever for document layout analysis](https://mlsanity.com/paper/1908.07836/) (2019)
- [ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation](https://mlsanity.com/paper/1606.02147/) (2016)
- [ICDAR2017 Competition on Reading Chinese Text in the Wild (RCTW-17)](https://mlsanity.com/paper/1708.09585/) (2017)
- [The Newspaper Navigator Dataset: Extracting And Analyzing Visual Content from 16 Million Historic Newspaper Pages in Chronicling America](https://mlsanity.com/paper/2005.01583/) (2020)
- [BADAM: A Public Dataset for Baseline Detection in Arabic-script Manuscripts](https://mlsanity.com/paper/1907.04041/) (2019)
- [Multi-Task Handwritten Document Layout Analysis](https://mlsanity.com/paper/1806.08852/) (2018)

## Built on by (most cited first, 1 of 1)

- [RefLAM: A Reference-Grounded Line Annotation Pipeline for Historical Arabic Manuscripts](https://mlsanity.com/paper/2608.25140/) (2026)

## Abstract (arXiv)

Archivists, textual scholars, and historians often produce digital editions of historical documents. Using markup schemes such as those of the Text Encoding Initiative and EpiDoc, these digital editions often record documents' semantic regions (such as notes and figures) and physical features (such as page and line breaks) as well as transcribing their textual content. We describe methods for exploiting this semantic markup as distant supervision for training and evaluating layout analysis models. In experiments with several model architectures on the half-million pages of the Deutsches Textarchiv (DTA), we find a high correlation of these region-level evaluation methods with pixel-level and word-level metrics. We discuss the possibilities for improving accuracy with self-training and the ability of models trained on the DTA to generalize to other historical printed books.