Controlled Languages for Machine Translation: State of the Art

A controlled language is a subset of a natural language with artificially restricted vocabulary, grammar, and style. Texts written in a controlled language are usually less complex and less ambiguous than those written in an uncontrolled language. The use of a controlled language therefore produces better results in machine translation. On the other hand, a controlled language reduces the power of expression and decreases the writing speed. In short, a controlled language brings out the maximum performance of machine translation systems at the cost of the burden on source text authors. So the controlled language approach is suitable for translation for dissemination of information. And a controlled language becomes more beneficial when texts are translated into multiple target languages. We should note the distinction between a controlled language and a sublanguage, which are sometimes confused. The term ‘sublanguage’, which means literally a subset of a language, is used when focus is put on a language used in a specific domain (for example, weather forecasting) rather than on the whole of a language. ‘Sublanguage’ does not imply artificially imposed restrictions. We should also mention pre-editing. Preediting is a form of human assistance in machine translation. It includes not only rewriting a source text but also inserting special symbols or tags within the text. Preediting is not always done by the authors of source texts, but the controlled language is originally expected to be used by the authors themselves.