Hierarchical Text Segmentation for Medieval Manuscripts
TL
TL;DR
It is shown that the main state-of-the-art segmentation methods are either inefficient or inapplicable for books of hours and a bottom-up greedy approach is proposed that considerably enhances the segmentation results.
Abstract
In this paper, we address the segmentation of books of hours, Latin devotional manuscripts of the late Middle Ages, that exhibit challenging issues: a complex hierarchical entangled structure, variable content, noisy transcriptions with no sentence markers, and strong correlations between sections for which topical information is no longer sufficient to draw segmentation boundaries. We show that the main state-of-the-art segmentation methods are either inefficient or inapplicable for books of hours and propose a bottom-up greedy approach that considerably enhances the segmentation results. We stress the importance of such hierarchical segmentation of books of hours for historians to explore their overarching differences underlying conception about Church.
References48 items
1
Multiple Document Datasets Pre-training Improves Text Line Detection With Deep Neural Networks
2
Books of Hours. the First Liturgical Data Set for Text Segmentation.
3
Using ASR Methods for OCR
4
SECTOR: A Neural Model for Coherent Topic Segmentation and Classification
5