A Large-Scale Comparison of Historical Text Normalization Systems

Abstract

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.

Accepted at NAACL 2019

References in corpus (1)

• An Evaluation of Neural Machine Translation Models on Historical Spelling Normalization

Cited by in corpus (7)

• Digitizing Historical Balance Sheet Data: A Practitioner's Guide
• When Word Embeddings Become Endangered
• Summarising Historical Text in Modern Languages
• ChroniclingAmericaQA: A Large-scale Question Answering Dataset based on Historical American Newspaper Pages
• Corpus and Models for Lemmatisation and POS-tagging of Classical French Theatre
• Normalization of Different Swedish Dialects Spoken in Finland
• Is text normalization relevant for classifying medieval charters?