Character-level NMT and language similarity

2023/08/08 by Josef Jon, Jon, Josef, Ondřej Bojar +1
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Text Readability and Simplification #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2308.04398

openalex publication_date 2023/08/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Related

• How Grammatical is Character-level Neural Machine Translation? Assessing MT Quality with Contrastive Translation Pairs
• Fully Character-Level Neural Machine Translation without Explicit Segmentation
• On the Importance of Word Boundaries in Character-level Neural Machine\n Translation
• Character-Level Translation with Self-attention
• Character-level Transformer-based Neural Machine Translation