arXiv subjects

Bence Bial

Publications and source records attributed to Bence Bial.

2 recordsLinked to original sources

arXiv2022

Syntax-based data augmentation for Hungarian-English machine translation

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.

cs.CL↗

arXiv2021

Automatic punctuation restoration with BERT models

We present an approach for automatic punctuation restoration with BERT models for English and Hungarian. For English, we conduct our experiments on Ted Talks, a commonly used benchmark for punctuation restoration, while for Hungarian we evaluate our models on the Szeged Treebank dataset. Our best models achieve a macro-averaged $F_1$-score of 79.8 in English and 82.2 in Hungarian. Our code is publicly available.

cs.CL↗