Creativity in translation: machine translation as a constraint for literary texts
This highlights limitations in neural MT for literary translation, showing it can hinder creativity and produce poorer-quality outputs, which is incremental as it builds on existing concerns about MT in creative domains.
The study evaluated creativity in translating a literary text using machine translation (MT), post-editing (PE), and human translation (HT), finding that HT scored highest in creativity, followed by PE and then MT, with MT producing literal solutions and constraining translator creativity.
This article presents the results of a study involving the translation of a short story by Kurt Vonnegut from English to Catalan and Dutch using three modalities: machine-translation (MT), post-editing (PE) and translation without aid (HT). Our aim is to explore creativity, understood to involve novelty and acceptability, from a quantitative perspective. The results show that HT has the highest creativity score, followed by PE, and lastly, MT, and this is unanimous from all reviewers. A neural MT system trained on literary data does not currently have the necessary capabilities for a creative translation; it renders literal solutions to translation problems. More importantly, using MT to post-edit raw output constrains the creativity of translators, resulting in a poorer translation often not fit for publication, according to experts.