Google Translate vs. DeepL

The present research analyses the performance of two free open-source neural machine translation (NMT) systems —Google Translate and DeepL— in (ES>EN) somatisms such as tomar el pelo meter la pata, their nominal variants (tomadura/tomada de metedura/metida pata), other lower-frequency pata hasta corvejón, gamba gamba. outcomes will be contrasted classified depending on whether these idioms are presented continuous or discontinuous form (Anastasiou 2010), i.e., different n-grams split idiomatic sequence (or not), which may pose some difficulties for automatic detection translation. Overall, insights gained from this study prove useful determining scenarios either Google DeepL delivers a better under challenge phraseological variation discontinuity.