Reasoned Translation: Putting Neural Machine Translation and Generative Artificial Intelligence Systems to the “Delisle Test”

This paper reports on a 2-stage experiment aimed at assessing machines’ ability to “reason” in translation The experiment was built around Jean Delisle’s pedagogy textbook La traduction raisonnée which has been used in English-French translator training for more than 40 years, in Canada and around the world. We put Bing Translator, Google Translate and DeepL – neural machine translation systems – as well as ChatGPT, NotionAI and Gaby-T – generative AI systems – to the test, using a selection of examples taken from the textbook and analyzing the results considering the background information and explanations provided, more specifically in the 30 chapters from where the examples were taken. In this paper, we first explore what inspired Delisle’s work and what he means by “reasoned translation”. Then, we focus on presenting the methodology and the results of our two pilot main experiments. Lastly, we offer some insights into potential future research avenues in translator training and beyond.