Korean-to-Chinese Machine Translation using Chinese Character as Pivot Clue
This addresses a specific low-resource translation problem for Korean-Chinese language pairs, offering an incremental improvement using linguistic insights.
The paper tackled the problem of low-resource Korean-to-Chinese machine translation by leveraging shared Sino-Korean vocabulary, converting these words to Chinese characters as a pivot. The result was an improvement in translation quality by up to 1.5 BLEU points compared to baseline models.
Korean-Chinese is a low resource language pair, but Korean and Chinese have a lot in common in terms of vocabulary. Sino-Korean words, which can be converted into corresponding Chinese characters, account for more than fifty of the entire Korean vocabulary. Motivated by this, we propose a simple linguistically motivated solution to improve the performance of the Korean-to-Chinese neural machine translation model by using their common vocabulary. We adopt Chinese characters as a translation pivot by converting Sino-Korean words in Korean sentences to Chinese characters and then train the machine translation model with the converted Korean sentences as source sentences. The experimental results on Korean-to-Chinese translation demonstrate that the models with the proposed method improve translation quality up to 1.5 BLEU points in comparison to the baseline models.