Machine translation, sometimes referred to by the abbreviation MT (not to be confused with computer-aided translation, machine-aided human translation or interactive translation) is a sub-field of computational linguistics that investigates the use of software to translate text or speech from one natural language to another.

In the 80s and 90s MT software was rule-based, but in the 2000s statistical analysis and the re-emergence of neural networking and more advanced machine learning techniques have proved to be far more successful.