An efficient graph search decoder for phrase-based statistical machine translation.

In this paper we describe an efficient implementation of a graph search algorithm for phrase-based statistical machine translation. Our goal was to create a decoder that could be used for both our research system and a real-time speech- to-speech machine translation demonstration system. The search algorithm is based on a Viterbi graph search with an A* heuristic. We were able to increase the speed of our de- coder substantially through the use of on-the-fly beam prun- ing and other algorithmic enhancements. The decoder sup- ports a variety of reordering constraints as well as arbitra ry n- gram decoding. In addition, we have implemented disk based translation models and a messaging interface to communi- cate with other components for use in our real-time speech translation system.