Machine Translation

"A renewed international effort is gearing up to design computers and software that smash language barriers and create a borderless global marketplace."

Machine translation (MT) is a procedure whereby a computer program analyzes a source text and produces a target text without further human involvement. In point of fact, machine translation typically does involve human intervention, in the form of pre-editing and post-editing. An exception to that rule might be, e.g., the translation of technical specifications (strings of technical terms and adjectives), using a dictionary-based machine-translation system.

So far, machine translation a major goal of natural-language processing has met with limited success. A November 6, 2007, example illustrates the hazards of uncritical reliance on machine translation. Machine translation has been brought to a large public by tools available on the Internet, such as Google, Babylon, Wikipedia etc. These tools produce a "gisting translation" a rough translation that, with luck, "gives the gist" of the source text.

With proper terminology work, with preparation of the source text for machine translation (pre-editing), and with re-working of the machine translation by a professional human translator (post-editing), commercial machine-translation tools can produce useful results, especially if the machine-translation system is integrated with a translation-memory or globalization-management system.

In regard to texts with limited ranges of vocabulary and simple sentence structure (e.g., weather reports), machine translation can deliver results that do not require much human intervention to be useful. Also, the use of a controlled language, combined with a machine-translation tool, will typically generate largely comprehensible translations.