Problem

Sometimes it makes sense to let a pre-translation be automatically post-edited.

If quality estimation is available for segments, it should be taken into account and potentially retriggered in loops.

Solution

Introduce a new tab analogous to the tabs for language resources, pivot language resources and TQE language resources, where a resource for automatic post-editing can be assigned.

Like TQE it should only be possible to assign 1 language resource per task.

Definition for pre-defined language resources  for automated post-editing is done analogous as for TQE, including InstantTranslate.

In addition we need the following configuration options, that are only chooseable, if a TQE language resource is also assigned:

• Do auto-post-editing, if TQE below X
• Repeat auto-post-editing up to X times, if TQE stays below Y
• Only in case the same language resource is assigned for TQE as for auto-post-editing: checkbox: Query for auto-post-editing in same prompt as for TQE

In the automatic post-editing we pass the AI source and target and ask it to post-edit the translation where it thinks, it needs to be enhanced. Like all other AI resources prompts from the prompt library can be used to customize the prompting.

If a TQE result and reasoning exists, we pass this along and ask it to enhance things.