Chinese-Japanese Unsupervised Neural Machine Translation Using Sub-character Level Information
This work addresses translation for Chinese-Japanese language users by introducing a novel approach for logographic languages, though it is incremental as it builds on existing UNMT methods.
The paper tackled unsupervised neural machine translation for Chinese-Japanese, a logographic language pair not previously studied, by using sub-character level data (ideograph or stroke) and found that stroke-level systems outperformed ideograph-level ones, enhancing performance beyond character-level data.
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.