Raw Output Evaluator is a tool designed to allow students to compare the raw outputs from different machine translation engines, both to each other and to other translations of the same source text, and carry out comparative human quality assessment using standard industry metrics. The same program can also be used as a post-editing tool and to compare the time required to post-edit MT output with how long it takes to produce an unaided human translation thanks to a built-in timer. It was first developed for use during a postgraduate course module specifically aimed at teaching the use of machine translation and post-editing, and designed as part of the Master’s Degree in Specialist Translation and Conference Interpreting at the International University of Languages and Media (IULM), Milan, Italy. It was presented during a workshop at the 40th edition of the annual Translating and the Computer Conference in London in November 2018. A full paper was published in the proceedings.
- Buy Now