Handling Heavily Abbreviated Manuscripts: HTR engines vs text normalisation approaches - Archive ouverte HAL
Conference Papers Year : 2021

Handling Heavily Abbreviated Manuscripts: HTR engines vs text normalisation approaches

Jean-Baptiste Camps
Chahan Vidal-Gorène

Abstract

Although abbreviations are fairly common in handwritten sources, particularly in medieval and modern Western manuscripts, previous research dealing with computational approaches to their expansion is scarce. Yet abbreviations present particular challenges to computational approaches such as handwritten text recognition and natural language processing tasks. Often, pre-processing ultimately aims to lead from a digitised image of the source to a normalised text, which includes expansion of the abbreviations. We explore different setups to obtain such a normalised text, either directly, by training HTR engines on normalised (i.e., expanded, disabbreviated) text, or by decomposing the process into discrete steps, each making use of specialist models for recognition, word segmentation and normalisation. The case studies considered here are drawn from the medieval Latin tradition.
Fichier principal
Vignette du fichier
IWCP2021_Handling_Abreviations_ArXiv.pdf (3.99 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03279602 , version 1 (06-07-2021)

Licence

Identifiers

Cite

Jean-Baptiste Camps, Chahan Vidal-Gorène, Marguerite Vernet. Handling Heavily Abbreviated Manuscripts: HTR engines vs text normalisation approaches. International Conference on Document Analysis and Recognition 2021, 2021, Lausanne, Switzerland. pp.306-316, ⟨10.1007/978-3-030-86159-9_21⟩. ⟨hal-03279602⟩
204 View
237 Download

Altmetric

Share

More