wubi2en: Character-level Chinese-English Translation through ASCII Encoding
share
Character-level Neural Machine Translation (NMT) models have recently achieved impressive results on many language pairs. They particularly do well for Indo-European language pairs, where the languages share the same writing system. However, for translating between Chinese and English, the gap between the two different writing systems poses a major challenge due to a lack of systematic correspondence between the individual linguistic units. In this paper, we enable character-level NMT for Chinese, by breaking down Chinese characters to linguistic units similar to that of Indo-European languages using the Wubi encoding scheme. We show promising results from training Wubi-based models on the subword- and character-level with recurrent as well as convolutional models.
READ FULL TEXT
