Terminology-aware machine translation in Trados 2024

Dear Community!

We are currently analyzing the upgrade of current 2022 licenses to 2024, therefore studying all the novelties offered by this new version.

According to the information available, MT results can be modified by the terminology available in the Multiterm dictionary, isn´t it?

So as far as I can understand, the working principle is the same as with the DeepL glossaries (which I personally prefer to call "MT correction lists", cause they are 100% personalized to the type of text translated and provide almost no information for a better understanding of a specific term). Or are there other benefits that I don´t see?

However, the "handicap" I see is how the MT provider will "choose" the term from the list of terms available in the Multiterm database?

Practical example 1: 

PLANO (Spanish term): in our corporate MDB we have three entries for "plano": 1) wheel tread defect 2) plane (vertical, horizontal...) and 3 ) drawing. 

In this particular case, which term would the AI Assistant 2024 be aware???? 

Practical case 2:

Bocina de agudos: this entry has 3 synonym terms in English: high-pitch horn, high-pitched horn and whistle.

Which synonym of the three would the AI Assistant use in this case? 

DeepL glossaries are more specific, i.e. they allow to correct a specific word with another specific word, only one. 

However, if the Multiterm glossary is applied in Trados 2024 following the same principle...how will the algorythm  work? And then, can Multiterm termonology be used on the MT provided by DeepL? Or is is mandatory to use other MT resources (Azure, Open Ai, etc?)

Thanks in advance!

emoji
Parents
  •  

    So as far as I can understand, the working principle is the same as with the DeepL glossaries (which I personally prefer to call "MT correction lists", cause they are 100% personalized to the type of text translated and provide almost no information for a better understanding of a specific term). Or are there other benefits that I don´t see?

    Similar... but not the same.

    DeepL changes the terms at the point of receiving the source so the MT results returned already contains the corrected term.

    The AI solution corrects the MT results that has been returned based on the terminology you have in your termbase.  But since it's AI you also benefit from the AI ensuring that the term is grammatically accurate in the context of the overall sentence.

    However, the "handicap"

    That is a good question.  I would typically respond by saying it's up to you to ensure you have a data structure that is suitable to support a solution like this.  I'm not sure how well the AI would do in ensuring the correct term is used in your example... it could lead to some odd translations.  Longer term we have discussed seeing how best to improve this but for now I think the solution to be sure (as sure as you can be with a tool that may not deliver consistent results 100% of the time due to the nature of AI right now) is to work on your termbase.

    But definitely worth playing with it a bit to see what sort of results you get.

    And then, can Multiterm termonology be used on the MT provided by DeepL?

    Yes it can.  You can use it with any MT provider.

    Paul Filkin | RWS Group

    ________________________
    Design your own training!

    You've done the courses and still need to go a little further, or still not clear? 
    Tell us what you need in our Community Solutions Hub

    emoji
Reply
  •  

    So as far as I can understand, the working principle is the same as with the DeepL glossaries (which I personally prefer to call "MT correction lists", cause they are 100% personalized to the type of text translated and provide almost no information for a better understanding of a specific term). Or are there other benefits that I don´t see?

    Similar... but not the same.

    DeepL changes the terms at the point of receiving the source so the MT results returned already contains the corrected term.

    The AI solution corrects the MT results that has been returned based on the terminology you have in your termbase.  But since it's AI you also benefit from the AI ensuring that the term is grammatically accurate in the context of the overall sentence.

    However, the "handicap"

    That is a good question.  I would typically respond by saying it's up to you to ensure you have a data structure that is suitable to support a solution like this.  I'm not sure how well the AI would do in ensuring the correct term is used in your example... it could lead to some odd translations.  Longer term we have discussed seeing how best to improve this but for now I think the solution to be sure (as sure as you can be with a tool that may not deliver consistent results 100% of the time due to the nature of AI right now) is to work on your termbase.

    But definitely worth playing with it a bit to see what sort of results you get.

    And then, can Multiterm termonology be used on the MT provided by DeepL?

    Yes it can.  You can use it with any MT provider.

    Paul Filkin | RWS Group

    ________________________
    Design your own training!

    You've done the courses and still need to go a little further, or still not clear? 
    Tell us what you need in our Community Solutions Hub

    emoji
Children
No Data