When reading through the exam material, I came to the point where Vinary and Darbelnet’s model of translation was explained (Jeremy Munday: 2001: 56-59) Interestingly enough Vinary and Darbelnet list five steps for the translator to follow in moving from Source Text to Target Text, their first item being “identifying the units of translation”. It is next explained that “as far as the ‘unit of translation’ is concerned, the authors reject the individual word. They consider the unit of translation to be a combination of a lexicological unit and a unit of thought and define it (1995: 21) as: ‘the smallest segment of the utterance whose signs are linked in such a way that they should not be translated individually.”
Now to me, what the authors are suggesting is translation of “smallest units of ideas.” Again, to me this seems very important that a computer program would be able to deal with ideas and recognize smallest units of ideas in a text in order to provide better translations.