In this paper, we present a stochastic language model for Japanese using dependency. The prediction unit in this model is all attribute of "bunsetsu". This is represented by the product of the head of content words and that of function words. The relation between the attributes of "bunsetsu" is ruled by a context-free grammar. The word sequences axe predicted from the attribute using word n-gram model. The spell of U n k n o w word is predicted using character n-grain model.