# Chinese-Japanese Unsupervised Neural Machine Translation Using Sub-character Level Information

arXiv: https://arxiv.org/abs/1903.00149 · HTML: https://mlsanity.com/paper/1903.00149/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Mar 2019.

## Built on by (most cited first, 1 of 1)

- [Breaking the Representation Bottleneck of Chinese Characters: Neural Machine Translation with Stroke Sequence Modeling](https://mlsanity.com/paper/2211.12781/) (2022)

## Abstract (arXiv)

Unsupervised neural machine translation (UNMT) requires only monolingual data of similar language pairs during training and can produce bi-directional translation models with relatively good performance on alphabetic languages (Lample et al., 2018). However, no research has been done to logographic language pairs. This study focuses on Chinese-Japanese UNMT trained by data containing sub-character (ideograph or stroke) level information which is decomposed from character level data. BLEU scores of both character and sub-character level systems were compared against each other and the results showed that despite the effectiveness of UNMT on character level data, sub-character level data could further enhance the performance, in which the stroke level system outperformed the ideograph level system.