This study compares Slate™ Desktop customized statistical MT (CSMT) to Google’s neural MT (GNMT). We evaluated roughly 2,300 segment pairs from each of 31 professional translators.
The study uses two well-established quality estimation scores to predict the impact of machine translation on a translator’s productivity. On average, CSMT exactly matched a translator quality 7 times more often than GNMT and reduced the remaining post-editing work by 50%.
Download the free report for the complete analysis and results.
You can review summaries of the 31 experiences here: Click here.