# Character-level NMT and language similarity

arXiv: https://arxiv.org/abs/2308.04398 · HTML: https://mlsanity.com/paper/2308.04398/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 24 references that are in the map.
- First posted on arXiv 8 Aug 2023.

## Builds on (most cited first, 14 of 14)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [Marian: Fast Neural Machine Translation in C++](https://mlsanity.com/paper/1804.00344/) (2018)
- [Fully Character-Level Neural Machine Translation without Explicit Segmentation](https://mlsanity.com/paper/1610.03017/) (2016)
- [Why don't people use character-level machine translation?](https://mlsanity.com/paper/2110.08191/) (2021)
- [A Character-Level Decoder without Explicit Segmentation for Neural Machine Translation](https://mlsanity.com/paper/1603.06147/) (2016)
- [Character-Level Translation with Self-attention](https://mlsanity.com/paper/2004.14788/) (2020)
- [Character-based NMT with Transformer](https://mlsanity.com/paper/1911.04997/) (2019)
- [Character-level Transformer-based Neural Machine Translation](https://mlsanity.com/paper/2005.11239/) (2020)
- [How Transformer Revitalizes Character-based Neural Machine Translation: An Investigation on Japanese-Vietnamese Translation Systems](https://mlsanity.com/paper/1910.02238/) (2019)
- [CUNI systems for WMT21: Multilingual Low-Resource Translation for Indo-European Languages Shared Task](https://mlsanity.com/paper/2109.09354/) (2021)

## Abstract (arXiv)

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.