Multi-task Learning for Hebrew Paleography: Script Classification and Date Estimation

Nour Atamni

doi:10.1007/978-3-032-04630-7_5

Multi-task Learning for Hebrew Paleography: Script Classification and Date Estimation

2026-01-01

0

PRE

AI

Daria Vasyutinsky Shapira

DOI：10.1007/978-3-032-04630-7_5

Original

Original request for help

Save

Abstract

En 中文

This paper presents a novel multi-task learning (MTL) approach for medieval Hebrew manuscripts, simultaneously addressing script classification and manuscript dating. To facilitate this, we collected a VML-MSH- a comprehensive dataset of medieval manuscripts spanning a period from 850 to 1540 CE. Each manuscript is accompanied by annotations of script type, script mode, and manuscript production date. The MTL enhances generalization across diverse script styles and periods by leveraging shared feature representations, and employs advanced architectures, including Vision Transformer (ViT), Mobile-ViT, Swin Transformer, FocalNet, BEiT, and ConvNeXT. Our training methodology combines classification and regression objectives with adaptive loss weighting, optimizing task performance. Experimental results demonstrate high accuracy in script type classification ranging from 84% to 100%, while highlighting challenges with a few script subtypes (60%-100%). For manuscript dating, the model achieves a mean error ranging from 1.37 to 8.97 decades. These findings underscore the effectiveness of the proposed MTL framework for advancing historical document image analysis and digital paleography. Code and dataset are available at https://github.com/atamnour/MTL-Hebrew-Paleography.

Keywords:

Historical document analysis

Automated dating

Historical dataset

Regression

Classification

Multi-task Learning for Hebrew Paleography: Script Classification and Date Estimation

Abstract

Journal

Organization