Diacritics Restoration using BERT with Analysis on Czech language
Computation and Language
2021-05-25 v1
Abstract
We propose a new architecture for diacritics restoration based on contextualized embeddings, namely BERT, and we evaluate it on 12 languages with diacritics. Furthermore, we conduct a detailed error analysis on Czech, a morphologically rich language with a high level of diacritization. Notably, we manually annotate all mispredictions, showing that roughly 44% of them are actually not errors, but either plausible variants (19%), or the system corrections of erroneous data (25%). Finally, we categorize the real errors in detail. We release the code at https://github.com/ufal/bert-diacritics-restoration.
Cite
@article{arxiv.2105.11408,
title = {Diacritics Restoration using BERT with Analysis on Czech language},
author = {Jakub Náplava and Milan Straka and Jana Straková},
journal= {arXiv preprint arXiv:2105.11408},
year = {2021}
}