Paper: Chinese Unknown Word Translation by Subword Re-segmentation

ACL ID I08-1030
Title Chinese Unknown Word Translation by Subword Re-segmentation
Venue International Joint Conference on Natural Language Processing
Session Main Conference
Year 2008
  • Ruiqiang Zhang (City University of Hong Kong, Kowloon Hong Kong)
  • Eiichiro Sumita (National Institute of Information and Communications Technology, Kyoto Japan; ATR Spoken Language Communication Research Laboratories, Kyoto Japan)

We propose a general approach for trans- lating 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 subword- based 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 im- proved if we applied named entity transla- tion to translate parts of unknown words be- fore using the subword-based translation.