International Workshop on Spoken Language Translation (IWSLT) 2006

Keihanna Science City, Kyoto, Japan
November 27-28, 2006

An Efficient Graph Search Decoder for Phrase-Based Statistical Machine Translation

Wade Shen (1), Brian Delaney (1), Timothy Anderson (2)

(1) MIT Lincoln Laboratory, Lexington, MA, USA
(2) Air Force Research Laboratory, Wright-Patterson AFB, OH, USA

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 speechto- 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 decoder substantially through the use of on-the-fly beam pruning and other algorithmic enhancements. The decoder supports a variety of reordering constraints as well as arbitrary ngramdecoding. In addition, we have implemented disk based translation models and a messaging interface to communicate with other components for use in our real-time speech translation system.

Full Paper     Presentation

Bibliographic reference.  Shen, Wade / Delaney, Brian / Anderson, Timothy (2006): "An efficient graph search decoder for phrase-based statistical machine translation", In IWSLT-2006, 197-204.