Post-processing
Post processing is a kind of rule-based system. Suppose you are developing a machine translation application and your generated model makes some specific mistakes. You want that machine translation (MT) model to avoid these kinds of mistakes, but avoiding that takes a lot of features that make the training process slow and make the model too complex. On the other hand, if you know that there are certain straightforward rules or approximations that can help you once the output has been generated in order to make it more accurate, then we can use post-processing for our MT model. What is the difference between a hybrid model and post-processing? Let me clear your confusion. In the given example, I have used word approximation. ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access