@inproceedings{d0798c1be5ad4a329a0f4cb9c9037599,
title = "Help from the Neighbors: Estonian Dialect Normalization Using a Finnish Dialect Generator",
abstract = "While standard Estonian is not a low-resourced language, the different dialects of the language are under-resourced from the point of view of NLP, given that there are no vast hand normalized resources available for training a machine learning model to normalize dialectal Estonian to standard Estonian. In this paper, we crawl a small corpus of parallel dialectal Estonian - standard Estonian sentences. In addition, we take a savvy approach of generating more synthetic training data for the normalization task by using an existing dialect generator model built for Finnish to {"}dialectalize{"} standard Estonian sentences from the Universal Dependencies tree banks. Our BERT based normalization model achieves a word error rate that is 26.49 points lower when using both the synthetic data and Estonian data in comparison to training the model with only the available Estonian data. Our results suggest that synthetic data generated by a model trained on a more resourced related language can indeed boost the results for a less resourced language.",
author = "Tuuli Tuisk and H{\"a}m{\"a}l{\"a}inen Mika and Alnajjar Khalid",
note = "Publisher Copyright: {\textcopyright} 2022 Association for Computational Linguistics.",
year = "2022",
doi = "10.18653/v1/2022.deeplo-1.7",
language = "English",
series = "DeepLo 2022 - 3rd Workshop on Deep Learning Approaches for Low-Resource NLP, Proceedings of the DeepLo Workshop",
publisher = "Association for Computational Linguistics",
pages = "61--66",
editor = "Colin Cherry and Angela Fan and George Foster and Gholamreza Haffari and Shahram Khadivi and Nanyun Peng and Xiang Ren and Ehsan Shareghi and Swabha Swayamdipta",
booktitle = "DeepLo 2022 - 3rd Workshop on Deep Learning Approaches for Low-Resource NLP, Proceedings of the DeepLo Workshop",
address = "United States",
}