Yulia Kovalskaya 

Yulia Kovalskaya said:

the working principle is the same as with the DeepL glossaries

Well, "jein", as we might say in German. Yes and no. At this point, the AI is just given the recognized terms, without any metadata. Insofar yes, your termbase is in a way reduced to a glossary. I hope this will change and there will be a way to choose other fields from the termbase to be handed to the AI.

If you prompt the AI to give you several suggestions, you will see that it varies which of the synonyms it uses. And you can instruct it to use a fitting synonym. Insofar, no, it's not like a DeepL glossary. That will always slot in the first fitting term it comes across, even if it makes little sense. With the AI, you can instruct it how to select a synonym. You might have to custom tailor your prompt for a particular translation to tell AI what the context is, but even a general instruction works. See screenshots below, I created a termbase with two translations for the English word "stain", and gave it two sentences. I also instructed AI to explain its choice.

In the first sentence, MT got the correct term, which is accepted by AI. In the second sentence, MT got the wrong term, and AI corrects it:

This is just a quick test. I am sure this could be refined substantially.

Daniel, hello!

In the first place, thank you for the answer! As far as I can understand, this is the interface of the AI Assistant in Trados 2024... And once, the MT result is corrected I have to click on it to insert it in the segment, right?

ANd then the prompts...they are written for each term?? Or a kind of a list of prompts can be created to "train" AI???

Yulia Kovalskaya 

a) Yes, that is the AI Assistant in Trados 2024.

b) The way I set it up, you have to click to insert it. But you could automate this and use it as a batch task. As Paul pointed out, the current AIs are fuzzy – that's their glory and their weakness. So you will want to look at what it's doing, at the very least check the results.

c) One prompt, hastily written in this case. It makes sense to refine prompts. I could imagine customizing a prompt for a project, like “The text you are working on is about cleaning textiles.” If you can give the LLM relevant information, by all means do.

The one serious weakness I see is how forbidden terms are handled. They, too, are just passed on to AI as relevant terms. If your termbase has a lot of those, you might have to create a separate termbase to get rid of those. In the above example, if I had "Klecks" as forbidden term, I doubt AI could reliably select "Fleck". All it get is a list like: "stain-Fleck, stain-Klecks, stain-Beize". Across the board, handling forbidden terms is a topic that urgently needs attention IMHO.

But as for your main question, AI's terminology-aware translations are seriously above a DeepL-style glossary if you prompt it well. As I said in other posts before, I believe this is a big game-changer technology for this industry, just like the ascent of MT was ten years ago.

Would be worth checking whether a plain terminology-redacting task requires GPT-4o, or whether it can run on a simpler, faster and cheaper model like 3.5turbo. There is so much that could be done!

Daniel

Dear Daniel, 

sorry for the late reply. Very grateful for the explanations, got it: we have to "train" the AI Assistant to make it apply out Multiterm terminology properly. Until I have the version and test it, I will not see how it actually works. 

However, what I see on your screenshots is that the MT modification is performed in a separate window below, not directly in the segment. That could be less "comfortable and more time consuming. However, we have to give it a try. 

Best regards, Daniel!

Yulia Kovalskaya 

Might be best to get your hands on that version and test it. No, you don't have to train the AI, it automatically pulls this information from your Termbase, if you select that option. The MT modification is done in a separate view, like your TM results, but you can update your translation with one keystroke or one mouse click, whichever you prefer. You can set it to query AI automatically for each segment that gets activated, so this is really seamless.

Dear Daniel!

Are you talking about the AI Assistant, right?? But as far as I can see, this assistant is only for OpenAI and Azure subscriptions. I have none. Only the Advanced Deepl. And there is no such option in the deepl provider configuration. Only the Glossaries, as before...

You need an Azure or OpenAI account to make use of the AI Assistant.

This is what I mean:

No option for Multiterm....

Hmmm, Paul  said in one of the answers in this thread that our TDB can be used with any MT provider....  :(...

Yulia Kovalskaya 

No, you have to export from MultiTerm and import into the DeepL glossary. And if you update your termbase you have to update your glossary as well. The DeepL glossary works pretty well, but not if you have synonyms. You can instruct AI to use the most fitting termbase term if there is more than one. But for that you need the AI Assistant and either an OpenAI account or an Azure account.

Ok, already talking with IT people about the AzureOpenAI...

Thanks for your advice, Daniel, I already did what you recoemmend in the  Trados 2022 version: export Multiterm - create Deepl glossaries...but, as I mentioned above, several weeks ago, it´s not the same. It´s too "direct", no synonyms allowed, constant updating and adaptation to each particular document needed.... 

The termbase I´ve been working on is really "extensive", with categories (per project, per train system), forbidden terms, definitions... And I update it on a daily basis (frequent updating deepl glossaries means a lot of time spent on eliminating synonyms from each exported cell, therefore, not feasible at all), this is why I am looking for a more interesting solution, I mean , the way to apply the database as it is, creating neccessary prompts, etc.

Ok, then, Merry Christmas to everyone! And I will for sure reopen this subject in January :)

Thank you very much for help!

Ok, already talking with IT people about the AzureOpenAI...

Thanks for your advice, Daniel, I already did what you recoemmend in the  Trados 2022 version: export Multiterm - create Deepl glossaries...but, as I mentioned above, several weeks ago, it´s not the same. It´s too "direct", no synonyms allowed, constant updating and adaptation to each particular document needed.... 

The termbase I´ve been working on is really "extensive", with categories (per project, per train system), forbidden terms, definitions... And I update it on a daily basis (frequent updating deepl glossaries means a lot of time spent on eliminating synonyms from each exported cell, therefore, not feasible at all), this is why I am looking for a more interesting solution, I mean , the way to apply the database as it is, creating neccessary prompts, etc.

Ok, then, Merry Christmas to everyone! And I will for sure reopen this subject in January :)

Thank you very much for help!