This paper investigates a new approach for computing the inference of defeasible logic. The algorithm proposed can substantially reduced the theory size increase due to transformat...
In this paper, we propose forest-to-string rules to enhance the expressive power of tree-to-string translation models. A forestto-string rule is capable of capturing nonsyntactic ...
This paper proposes a novel lexicalized approach for rule selection for syntax-based statistical machine translation (SMT). We build maximum entropy (MaxEnt) models which combine ...