


They can be trained for specific industries or disciplines using additional data relevant to the sector needed. Instead they "learn" to translate by analysing large amounts of data for each language pair. Statistical systems have no knowledge of language rules.Rules-based systems typically deliver consistent translations with accurate terminology when trained with specialist dictionaries.

Specialist dictionaries are created to focus on certain industries or disciplines. Rules-based systems use a combination of language and grammar rules plus dictionaries for common words.There are three types of machine translation system: rules-based, statistical and neural:
