The transformer has been shown to outperform recurrent neural network-based sequence-to-
sequence models in various word-level NLP tasks. Yet for character-level transduction tasks …

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 …

GRAC is a large reference corpus of Ukrainian spanning over 200 years. The system of
morphological analysis used to mark up the corpus was originally designed only for modern …

Historical documents are an important part of our cultural heritage. Among other task related
to their processing, it is important to modernize their language in order to make them …

This paper presents a study on automatic normalisation of 16th century documents written in
Middle French. These documents present a large variety of wordforms which require …

Historical text normalization, the task of mapping historical word forms to their modern
counterparts, has recently attracted a lot of interest (Bollmann, 2019; Tang et al., 2018; …

L'étude des états de langue anciens se heurte à un double problème: d'une part la distance
d'avec l'orthographe actuelle, qui empêche de recourir aux solutions standards de TAL, et …

Etymology, and the field of lexicography, is often constrained by unstructured data formats
buried in scholarly articles and dictionaries. This paper presents a methodology and an …

Training neural sequence-to-sequence models with simple token-level log-likelihood is now
a standard approach to historical text normalization, albeit often outperformed by phrase …

The nature of human language and the lack of a spelling convention make historical
documents hard to handle for natural language processing. Spelling normalization tackles …