Dealing with common ground in Human Translation and Neural Machine Translation: A case study on Italian equivalents of German Modal Particles

Abstract

The purpose of this chapter is to examine the neural machine translation of modal particles and to compare it to human translation. The quantitatively-oriented study focuses on Italian lexical translation equivalents of German eben and einfach. The two modal particles have similar meaning, as the speaker uses both to underline the obvious character of their utterance. The study is based on a sample of human translations of literary texts as well as on the neural machine translations of these texts generated by Google Translate and DeepL. It will be analyzed to what extent the lexical translation equivalents proposed by the human translators and the NMT tools reflect the modal meaning of eben and einfach and provide information on the existence of modal particles in Italian.