Abstract: There is need to fill the gap between two entities which use different languages to communicate which can be done either via human translation or machine translation means. The world has over 7000 living natural languages, thus making it costly if human translation route is taken hence need for machine translation. There is need to know the available machine translation approaches and their requirement in order to decide which one suits for particular languages or not, hence the motivation for this survey. The survey provide overview and architectures of the three major techniques available namely: rule based translation, corpus based translation and hybrid based translation plus their subcategories available in each approach.