Machine Translation Post Editing Rates. The concept of post-editing is linked to that of pre-editing. Put simply TER measures the number of edits that are necessary to go from the raw MT output to a final edited version.
Post-editing means that a human translator is editing or revising text that has been translated by machine translation software. Translators could either be paid their full per word rate for a 1000 words translation starting from scratch or the same rate for a lower number of equivalent words such as 700 1000 raw words 300 words discount due to MT matches 700 words for post-editing machine translation output. With this quality I can post edit about 3000 words in a couple of hours whereas something like that usually takes me an entire day from scratch.
Some of these cookies are essential to the operation of the site while others help to improve your experience by providing insights into how the site is being used.
1 the hypothetical price for the source and the final translation post-edited version of the source obtained through a fuzzy-match pricing model and 2 the cost of post-editing the raw MT output through a productivity assessment to test the results and refine assumptions. I have to admit that the quality of neural machine translation is getting better all the time. But lets stop for a minute and take a closer look at what post-editing really entails. A customer has a post-editing assignment with no strict quality requirements that he has an approved translation rate of 003word for.
