Webinar: How to Run a Data-Driven MT Evaluation

There are many machine translation systems on the market today. Choosing the most effective system for a particular production workflow can be a difficult task. Lilt’s CEO and co-founder, Spence Green, recently hosted a webinar to show a principled, data-driven method that is used by researchers to score systems.

The webinar covered automatic measures such as BLEU and TER that can be used to rank systems quickly, as well as human evaluation of translation quality and finally how to measure translation productivity, which is known to be correlated with input machine translation quality.

The recorded webinar can be found in two parts here: Part 1 and Part 2. Accompanying slides can also be viewed here.

Leave a Reply

Your email address will not be published. Required fields are marked *