Handling Heavily Abbreviated Manuscripts: HTR engines vs text normalisation approaches
This work addresses the challenge of abbreviation expansion for researchers in digital humanities and historical linguistics, but it is incremental as it builds on existing HTR and normalization techniques.
The paper tackled the problem of expanding abbreviations in medieval Latin manuscripts by comparing two computational approaches: training handwritten text recognition (HTR) engines on normalized text versus using separate models for recognition, segmentation, and normalization. The result showed that both methods can produce normalized text, but no concrete performance numbers were provided.
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.