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:
“The machine is impersonal, it takes the pride away from a piece of work, the individual merits and defects that go along with all work that is not done by a machine—which is to say, its little bit of humanity.”
—Friedrich Nietzsche (1844–1900)
“To translate, one must have a style of his own, for otherwise the translation will have no rhythm or nuance, which come from the process of artistically thinking through and molding the sentences; they cannot be reconstituted by piecemeal imitation. The problem of translation is to retreat to a simpler tenor of one’s own style and creatively adjust this to one’s author.”
—Paul Goodman (1911–1972)