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 a...
Saved in:
| Main Authors: | |
|---|---|
| Corporate Author: | |
| Format: | Book part |
| Published: |
2022
|
| Series: | Magyar Számítógépes Nyelvészeti Konferencia
18 |
| Kulcsszavak: | Nyelvészet - számítógép alkalmazása, Gépi fordítás - számítógép alkalmazása |
| Subjects: | |
| Online Access: | http://acta.bibl.u-szeged.hu/75885 |
| Summary: | 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. |
|---|---|
| Physical Description: | 343-356 |
| ISBN: | 978-963-306-848-9 |