• State Not Answered
  • Replies 1 reply
  • Subscribers 432 subscribers
  • Views 21 views
  • Users 0 members are here
Options
Related

How to achieve document-level or project-level context for MT and AI

Daniel Hug

I am looking for a way to achieve at least document-level context for MT and AI. The current solution is to run an AI platform in parallel and copy/paste from Trados Studio to the AI platform. There, and agent is equipped with the entire document (and reference material, if there is). I then manually paste the response back into Studio. So far, so good, but this is painfully manual and very slow.

I'd like to be able to tell Studio's AI assistant:

“Include the preceding X segments (or paragraphs) in your request. With (or without) translation.”

“Include the succeeding X segments (or paragraphs) in your request. (With or without translation, for the sake of completion, although this will usually be without unless I am in the role of the reviewer.)

I created an idea for this, please support:  Context-awareness for AI Assistent 

For terminology, very, very important: Include such-and-such a field in your request. This is how I can tell AI not to use TB entries with the status “deprecated” or “superseded”. There is an idea for this already, please support:  OpenAI Provider for Trados Studio: option to include term information in system prompt 

A lot happened recently with the AI Assistant (user can modify the system prompt)! Thank you for that!

Removed AI Suggestion
[edited by: Daniel Hug at 10:17 AM (GMT 0) on 13 Dec 2025]
emoji
Rate translation
×
Suggest better translation
×
Moderator UI
×
  • Get AI Suggestion
  • 0

    For MT, I remember Globalese (now bought up by MemoQ) offered only “asynchronous” MT – you had to send the whole document to their MT engine, wait some, and get the whole document back (all target segments filled in). I was thinking along these lines when thinking about context-aware MT. It could store the segments in a TM.

    I can do this already, manually: Get the whole document translated by MT (or AI), perform an alignment (works really well with AI), create a TM and populate it with the TUs resulting from the alignment. It's very possible already, just very slow. I could write a script to speed up parts of it, but I think it would be timely for any translation tool to offer as out-of-the-box functionality. Could be done as part of the core product or as an app.
    emoji