A Large-Scale Comparison of Historical Text Normalization Systems
This work addresses the problem of inconsistent evaluation in historical text normalization for researchers, providing a comprehensive benchmark, though it is incremental as it synthesizes existing methods.
The paper tackled the lack of consensus on state-of-the-art approaches to historical text normalization by conducting the largest study to date, comparing systems across eight languages and analyzing training data effects, with datasets and scripts made publicly available.
There is no consensus on the state-of-the-art approach to historical text normalization. Many techniques have been proposed, including rule-based methods, distance metrics, character-based statistical machine translation, and neural encoder--decoder models, but studies have used different datasets, different evaluation methods, and have come to different conclusions. This paper presents the largest study of historical text normalization done so far. We critically survey the existing literature and report experiments on eight languages, comparing systems spanning all categories of proposed normalization techniques, analysing the effect of training data quantity, and using different evaluation methods. The datasets and scripts are made publicly available.