This report provides a summary of how market-leading MT software solutions perform on two popular automated metrics (BLEU and LEPOR) that attempt to measure relative MT quality. These metrics provide a rough guide to the automatic translation quality users can expect from these products. Keep in mind that this is a single measure of a single dimension of product performance and fit. Buyers and evaluators of MT should consider their overall requirements and business objectives when evaluating any technology, including machine translation.
Top Comments