Statistical machine translation (SMT) is a machine translation paradigm where translations are generated on the basis of statistical models whose parameters are derived from the analysis of bilingual text corpora. The statistical approach contrasts with the rule-based approaches to machine translation as well as with example-based machine translation.
The first ideas of statistical machine translation were introduced by Warren Weaver in 1949, including the ideas of applying Claude Shannon's information theory. Statistical machine translation was re-introduced in 1991 by researchers at IBM's Thomas J. Watson Research Center and has contributed to the significant resurgence in interest in machine translation in recent years. Nowadays it is by far the most widely studied machine translation method.
Read more about Statistical Machine Translation: Basis, Benefits, Shortcomings, Word-based Translation, Phrase-based Translation, Syntax-based Translation, Hierarchical Phrase-based Translation
Famous quotes containing the words machine and/or translation:
“But a man must keep an eye on his servants, if he would not have them rule him. Man is a shrewd inventor, and is ever taking the hint of a new machine from his own structure, adapting some secret of his own anatomy in iron, wood, and leather, to some required function in the work of the world. But it is found that the machine unmans the user. What he gains in making cloth, he loses in general power.”
—Ralph Waldo Emerson (1803–1882)
“Any translation which intends to perform a transmitting function cannot transmit anything but information—hence, something inessential. This is the hallmark of bad translations.”
—Walter Benjamin (1892–1940)