Round-trip translation: no more entertainment with PNMT™ systems

Round-trip translation (RTT), also known as back-and-forth translation, recursive translation and bi-directional translation, is the process of translating a word, phrase or text into another language (forward translation), then translating the result back into the original language (back translation), using machine translation (MT) software.
It is often used by laypeople to evaluate a machine translation system, or to test whether a text is suitable for MT when they are unfamiliar with the target language. Because the resulting text can often differ substantially from the original, RTT can also be a source of entertainment*.

When we translate the paragraph below…

…with SYSTRAN Pure Neural™ Machine Translation (PNMT™) we get the translation into French :

Let’s imagine we don’t read French and we need to back-translate the above paragraph into English in order to understand and also evaluate the PNMT™ using .

Not only the pragmatic knowledge thus the cognition is transferred but also the PNMT™ RTT reverts into a simplified lexicon and grammatical structure to render it more explicit and understandable.

Both can be considered originals. One might even say that the PNMT™ RTT result is better than the original. Authoring is not far.

The eye of the expert detects that the only word we lose is technicalities: “RTT”.
RTT that can be many things depending on neural model used. Like a child who has not discovered everything yet or a non-expert of the domain. If that is the case the expert that would need to publish that text will replace “Routière” by “RTT” in french using SYSTRAN Dictionary Editor specifying that it is not the days-off in the French Labour Law but the Round-trip translation.

Beyond language SYSTRAN PNMT™ transfers cognition allowing the expert to interact with the neural system by replacing one function by another.

I tend to become complicated please RTT me with


Author: Elsa Sklavounou, Senior Linguistic Expert-Partner Business Developer SYSTRAN SAS