Emi Amber 

You might have resolved this by now, but in the Settings screenshot above, you definitely have to check the option "Enable Terminology-aware Translation Suggestions" in order for ChatGPT to work with your termbase.

Daniel

Hi Daniel :-)

I have changed my settings for both AI Assistand and OpenAI. I am not sure what "Ignore translated segments" does, so I left it out.

Unfortunately, Terminology aware translation does not work as I expected, i.e. the terms that are recognized in Termbase are not used by either OpenAI or AI Assistant. 

As you can see the term that was recognized in the Termbase was not used in the translation, but when I try to type itin  by hand it shows up as a suggestion... so I have no idea what I am doing wrong. Maybe you can give me a suggestion what I should write in my prompts??

My prompt is as follows:
"Please refine the translation to populate it with the terminology from the current Termbase assignet to this project. Behold the same formatting as in the source text. "

Do you have any suggestions?

I have tried several different prompts now and OpenAi is still not working as it should, it is not populating the translations with terms from the Termbase.... Can anyone suggest any solution, please? Or give me an example of the prompts you are using yourself?

Hello!!! Is there anyone who can help me to write the prompt which works??? I have tried to change it at least 20 times and the result is the same. Neither OpenAI or AI Assistand is populating translations with terms from the Termbases. It literally doeas not care about the Termbase at all. What can be the problem, please help! 
Should I open a case on that ? 

Hi Emi Amber , as discussed via your case with RWS Support, I logged the issue for our Development (as CRQ-40545), to investigate further and implement a fix in a future Studio/plug-in update.

Hello Emi Amber , I just wanted to let you know that a new version of the OpenAI plug-in (version 1.1.4.0) is available on the RWS Appstore. Can you please install it and let us know if the terms are used as expected with this one?

Please remember to uninstall the current version of the plug-in before installing the new version.

Hi,

I will try to install this one, THANK you! but I dont know if I am able to uninstall the old one, it was ready to use with Trados Studio 2024. I did not install it myself... How do I do it? 

I dont seem to have this plug in, do you mean Copilot?

Hi Emi Amber , yes, you will be able to uninstall the old version of the plug-in, as described here: https://gateway.sdl.com/apex/communityknowledge?articleName=000010617. Please let me know if you encounter any issues.

Thank you! I will try this this weekend and let you know  

Hi again,

I am testing the updated plugin but it is still not working for the polish & norwegian languages, unfortunately. As you can se the term "poradnia urazowo ortopedyczna" has been properly recognized and is available in the Term Recognition window, the value is 89 because the term does not have a hyphen but it is such a small difference that OpenAI should be able to recognize it as the same or at least a very similar term. In stead it suggests its own translation. Example nr 2. "bez kolizji z korzeniami nerwów rdzeniowych" THIS one has been translated wrong so many times that I have saved it as a term, it is perfectly recognized with 80 % value but still not used by the OpenAI. I suspect this is because these terms have a value less than 100 and then they are ignored by the plugin and the Copilot. I suggest to update the plugin so that it takes into consideration also terms with less than 100% value or it will not be usable for languages with a more complex language system than f. eks English, German, French etc. Slavic languages like Polish have a number of casus which means that the same word, be it an object, verb or an adjectiv can be written in 7 different forms, and just one change in one letter results in unproper recognition of the word which get a lower value than 100. It would be literally impossible to save each termn in 7 different cases (forms) so that it is recognized properly, so the plug in needs to understand that even if the word is written in a different casus it is still the same word. 

SO my question is> Does OpenAI make use of terms that have a value less than 100 ? In my opinion it does not, at least I have not seen one example of it using a term from the Termbase with the value less than 100. This must be fixed, or the plugin will be useless for us who translate from a language which has a more complicated structure than English. 

I strongly recommend to do this.  
. 

Hi again,

I am testing the updated plugin but it is still not working for the polish & norwegian languages, unfortunately. As you can se the term "poradnia urazowo ortopedyczna" has been properly recognized and is available in the Term Recognition window, the value is 89 because the term does not have a hyphen but it is such a small difference that OpenAI should be able to recognize it as the same or at least a very similar term. In stead it suggests its own translation. Example nr 2. "bez kolizji z korzeniami nerwów rdzeniowych" THIS one has been translated wrong so many times that I have saved it as a term, it is perfectly recognized with 80 % value but still not used by the OpenAI. I suspect this is because these terms have a value less than 100 and then they are ignored by the plugin and the Copilot. I suggest to update the plugin so that it takes into consideration also terms with less than 100% value or it will not be usable for languages with a more complex language system than f. eks English, German, French etc. Slavic languages like Polish have a number of casus which means that the same word, be it an object, verb or an adjectiv can be written in 7 different forms, and just one change in one letter results in unproper recognition of the word which get a lower value than 100. It would be literally impossible to save each termn in 7 different cases (forms) so that it is recognized properly, so the plug in needs to understand that even if the word is written in a different casus it is still the same word. 

SO my question is> Does OpenAI make use of terms that have a value less than 100 ? In my opinion it does not, at least I have not seen one example of it using a term from the Termbase with the value less than 100. This must be fixed, or the plugin will be useless for us who translate from a language which has a more complicated structure than English. 
Please address the issue stated below:
"

In Trados Studio 2024, the OpenAI plugin's Terminology-aware Translation Suggestions feature is designed to incorporate terms from your termbase into AI-generated translations. However, there are known issues where the plugin may not utilize termbase entries with a match value less than 100%, even when the "Enable Terminology-aware Translation Suggestions" option is activated.

Possible Causes:

1. Plugin Limitations: The current implementation may not effectively handle fuzzy matches (i.e., matches below 100%) from the termbase. This limitation can result in the AI-generated translations not incorporating these terms."

I strongly recommend to do this.  It will make our work much easier and the limitations described above make this plugin in many ways unusable. 

Please, send me a message or reply to this post when the new plugin addressing this issue is available!. Thank you.   ♥ 
. 

Hi again,

I am testing the updated plugin but it is still not working for the polish & norwegian languages, unfortunately. As you can se the term "poradnia urazowo ortopedyczna" has been properly recognized and is available in the Term Recognition window, the value is 89 because the term does not have a hyphen but it is such a small difference that OpenAI should be able to recognize it as the same or at least a very similar term. In stead it suggests its own translation. Example nr 2. "bez kolizji z korzeniami nerwów rdzeniowych" THIS one has been translated wrong so many times that I have saved it as a term, it is perfectly recognized with 80 % value but still not used by the OpenAI. I suspect this is because these terms have a value less than 100 and then they are ignored by the plugin and the Copilot. I suggest to update the plugin so that it takes into consideration also terms with less than 100% value or it will not be usable for languages with a more complex language system than f. eks English, German, French etc. Slavic languages like Polish have a number of casus which means that the same word, be it an object, verb or an adjectiv can be written in 7 different forms, and just one change in one letter results in unproper recognition of the word which get a lower value than 100. It would be literally impossible to save each termn in 7 different cases (forms) so that it is recognized properly, so the plug in needs to understand that even if the word is written in a different casus it is still the same word. 

SO my question is> Does OpenAI make use of terms that have a value less than 100 ? In my opinion it does not, at least I have not seen one example of it using a term from the Termbase with the value less than 100. This must be fixed, or the plugin will be useless for us who translate from a language which has a more complicated structure than English. 
Please address the issue stated below:
"

In Trados Studio 2024, the OpenAI plugin's Terminology-aware Translation Suggestions feature is designed to incorporate terms from your termbase into AI-generated translations. However, there are known issues where the plugin may not utilize termbase entries with a match value less than 100%, even when the "Enable Terminology-aware Translation Suggestions" option is activated.

Possible Causes:

1. Plugin Limitations: The current implementation may not effectively handle fuzzy matches (i.e., matches below 100%) from the termbase. This limitation can result in the AI-generated translations not incorporating these terms."

I strongly recommend to do this.  It will make our work much easier and the limitations described above make this plugin in many ways unusable. 

Please, send me a message or reply to this post when the new plugin addressing this issue is available!. Thank you.   ♥ 
.