Andrew Levine 

It will work easily one at a time.  Your question title says "all"  but the content of the thread suggests it won't work at all.  So first the working at all:

If that was your problem I hope it helps.  If you actually want to use AI to find and replace "All" then I'm afraid that isn't possible yet.  We'd need to have a batch task capability to do this which we don't have yet, and as you saw in the video it might be a problem anyway as it's not always right!

Hello Paul,

Thanks for the bespoke video to show off the capability. It does look like this will be a useful prompt but it's unfortunate that we cannot do a batch task to fix a recurring error. Hopefully in some future version.

-Andrew

Paul 

Yes, but there is no reason to believe that this would not work as a batch process.

Daniel Hug 

I love your optimism ;-)  But I would be surprised.  It certainly wasn't designed to work that way.

Paul said:

I love your optimism ;-) 

Paul  I am normally likened to Eeyore.

That aside, could you attach your sample file and a text version of your prompt from the above video? Let's find out.

Daniel Hug 

Sure... file:

subscripts.md_en-US_fr-FR.zip

Prompt:

Compare the use of subscript numbers in the source with the use in the already translated target.  If there is a difference report and offer a correction.

Paul , Andrew Levine 

I got it to work with your AI prompt, Paul:

Daniel Hug 

Well... hats off to you!  I still cannot make this work.  One interesting thing I noted in your demo is the before and after.

Before:

After:

The statuses are now all NMT, including the ones that had nothing wrong with them.  I am a bit suspicious of that.  I do think it needs more testing, and I will discuss with the developer.  I don't think we'll get back to this for a while as we don't really want to touch this anymore until the AI Assistant part has been separated and is part of the core product.  But the batch task requirement is noted.

Paul 

I should have told you that I edited your prompt. I found yours was not directive enough. Mine is:

“Contrary to what I told you before, you are not a translator, but an editor. Compare the use of subscript numbers in the source with the use in the already translated target. If there is a difference, correct the target according to the source.”

Why are all segments now marked NMT? Well, I'd say OpenAI touches each one of them and this causes the different origin. I think it reads each segment, applies AI, then writes the result. Even if the result is “don't change anything”, it still writes the unchanged segment. Your developers would be able to confirm that (or refute it).

What I am struggling with is a way to make it obvious to the translator what was changed. I am using Post-Edit Compare, which works but is a bit cumbersome to set up. If I could manage to get Trados to do its replacements in the review mode, that would be a dream come true. But thinking about what you noticed, it might well be that the AI Assistant replaces the entire segment content with its output (changed or not), in which case the track changes mode would not be very helpful.

In my other AI test project where I try to get AI to insert the correct synonym, I get this with Post-Edit Compare:

I found that the AI Assistant reliably keeps its fingers off translated text if I tell it explicitly that it is not a translator but an editor, but I still like to be sure. (See segment 9!)

The aim here is to be able to ask AI to apply a certain style to an entire text, such as making sure that British English is used throughout, and no US idioms. I'd definitely need to know what got changed.

Daniel

(Sorry, tried to update the screenshot but wasn't allowed to, so deleted the post and re-wrote it. Screenshot now has proper files as “original” and “updated”. Was very confusing before.)

Daniel Hug 

Daniel Hug said:

Why are all segments now marked NMT? Well, I'd say OpenAI touches each one of them and this causes the different origin. I think it reads each segment, applies AI, then writes the result. Even if the result is “don't change anything”, it still writes the unchanged segment.

Seems unlikely and if I could make this work I could check it easily enough in two ways:

1. add your initials to the start of each target segment before you run it and see if the result removed the initials, or
2. use fiddler to see what gets sent and what comes back

I already know this was never designed to work in this way, the developers would confirm this, so what we're testing here is almost a case of good bugs/bad bugs... and this may be a good bug ;-)

Paul 

Bless that bug! Fiddler Like this?

Daniel Hug 

So now edit the target in your original file before sending this request and see what happens.

Daniel Hug 

So now edit the target in your original file before sending this request and see what happens.

Paul 

It's corrected:

Daniel Hug 

So I think this proves that you cannot do this yet with a batch task because all that is happening is that OpenAI then replaces the content with a new translation.  The reason it was not noticed before is that I also used OpenAI to translate into French in the first place :-)

Paul 

Far be it from me to insist... but. What you see above is not simply a new "vanilla" translation that happens to match the old one because it's the same translation provider. I can prevent the AI Assistant from meddling with the existing translation with almost 100% certainty.

In the below examples, I completely rephrased the translation, and AI only does what it should do: fix the terminology, nothing else. Only when I enter something which is obviously wrong does AI step in and "fix it".

Here is the original, MT'd sentence:

Rephrased:

I admit this is a use of the AI Assistant that was not originally intended, but from a user's point of view, it works. And it's very useful.

Daniel Hug 

Daniel Hug said:

I admit this is a use of the AI Assistant that was not originally intended, but from a user's point of view, it works. And it's very useful.

I agree it is very useful.  But the point of this thread is all about being able to use AI via a batch task to apply the improvements found in the AI Assistant via a batch task.  The AI Assistant will do that perfectly and only change the parts you ask for.  But the batch task is changing the entire sentence.  That is not useful at all, in fact it's destructive.

Your Fiddler test demonstrated this quite well as the batch task removed your initials.

So I think if you understand what you're doing and understand how this is working then batch tasks are quite fine.  But only replacement of terminology has been supported via a batch task.  This very interesting usecase, which is not new of course, is not supported.