As traditional SMT systems treat all words as single tokens without considering their internal structure, major problems of data sparsity occur for less frequent tokens.

Another source of data sparsity that occurs in all languages is proper names, which have been handled by using cognates or transliteration to improve translation (Knight and Graehl, 1998; Kondrak et al., 2003; Finch and Sumita, 2007), and more sophisticated methods for named entity translation that combine translation and transliteration have also been proposed (Al-Onaizan and Knight, 2002).

We have enumerated these related works to demonstrate the myriad of data sparsity problems and proposed solutions.