English

Syntax-based data augmentation for Hungarian-English machine translation

Computation and Language 2022-01-19 v1 Machine Learning

Abstract

We train Transformer-based neural machine translation models for Hungarian-English and English-Hungarian using the Hunglish2 corpus. Our best models achieve a BLEU score of 40.0 on HungarianEnglish and 33.4 on English-Hungarian. Furthermore, we present results on an ongoing work about syntax-based augmentation for neural machine translation. Both our code and models are publicly available.

Keywords

Cite

@article{arxiv.2201.06876,
  title  = {Syntax-based data augmentation for Hungarian-English machine translation},
  author = {Attila Nagy and Patrick Nanys and Balázs Frey Konrád and Bence Bial and Judit Ács},
  journal= {arXiv preprint arXiv:2201.06876},
  year   = {2022}
}
R2 v1 2026-06-24T08:53:26.496Z