Tradares: A Tool for the Automatic Evaluation of Human Translation Quality within a MOOC Environment

Abstract

In this paper, we introduce TradARES, a tool for the automatic evaluation of human translation quality developed in the context of an OpenEdx MOOC (Massive Open Online Course), setting the foundation for a tool that provides efficient and trustful feedback to students. Our further goal is to release a small corpus of Arabic-Spanish translations from the first edition of the course. The evaluation tool is based on prediction models and at the moment is able to indicate the quality of a given piece of text—in the numerical scale {1,2,3,4}—as a translation of another piece of text.