Fast, Scalable Phrase-Based SMT Decoding
This work addresses the problem of slow decoding speeds for commercial SMT applications, though it is incremental as it optimizes existing components rather than introducing a new paradigm.
The paper tackled the need for faster and more scalable phrase-based statistical machine translation decoding for commercial use, resulting in a drop-in replacement for the Moses decoder that is up to fifteen times faster and scales monotonically with multicore machines.
The utilization of statistical machine translation (SMT) has grown enormously over the last decade, many using open-source software developed by the NLP community. As commercial use has increased, there is need for software that is optimized for commercial requirements, in particular, fast phrase-based decoding and more efficient utilization of modern multicore servers. In this paper we re-examine the major components of phrase-based decoding and decoder implementation with particular emphasis on speed and scalability on multicore machines. The result is a drop-in replacement for the Moses decoder which is up to fifteen times faster and scales monotonically with the number of cores.