Chinese Unknown Word Translation by Subword Re-segmentation

We propose a general approach for translating Chinese unknown words (UNK) for SMT. This approach takes advantage of the properties of Chinese word composition rules, i.e., all Chinese words are formed by sequential characters. According to the proposed approach, the unknown word is re-split into a subword sequence followed by subword translation with a subwordbased translation model. “Subword” is a unit between character and long word. We found the proposed approach significantly improved translation quality on the test data of NIST MT04 and MT05. We also found that the translation quality was further improved if we applied named entity translation to translate parts of unknown words before using the subword-based translation.