Character-level NMT and language similarity

• Main Authors: Jon, Josef, Bojar, Ondřej
• Format: Journal Article
• Language: English
• Published: 08-08-2023
• Subjects: Computer Science - Computation and Language
• DOI: 10.48550/arxiv.2308.04398

We explore the effectiveness of character-level neural machine translation
using Transformer architecture for various levels of language similarity and
size of the training dataset on translation between Czech and Croatian, German,
Hungarian, Slovak, and Spanish. We evaluate the models using automatic MT
metrics and show that translation between similar languages benefits from
character-level input segmentation, while for less related languages,
character-level vanilla Transformer-base often lags behind subword-level
segmentation. We confirm previous findings that it is possible to close the gap
by finetuning the already trained subword-level models to character-level.