Two Decades of Statistical Machine Translation
Yongzeng Xue · 2011
Statistical Machine Translation is the general term for the various data-driven methods that apply statistical models as the core mechanism to automatically translating from one language to another. Since the first practical approach was proposed in 1990, many attempts have been made to improve the state of the art. We review them here, make a clear clue of the achievements over the past twenty years, and point out a few promising directions.