SDL Trados Studio
SDL Trados GroupShare
SDL Trados Business Manager
SDL Trados Live
SDL Speech to Text
SDL Managed Translation - Enterprise
Translation Management Connectors
SDL LiveContent S1000D
SDL Contenta S1000D
SDL Tridion Docs
SDL Tridion Sites
SDL Content Assistant
SDL Machine Translation Cloud
SDL Machine Translation Connectors
SDL Machine Translation Edge
Tridion Docs Developers
SDL User Experience
Language Products - GCS Internal Community
SDL Community Internal Group
SDL Access Customer Portal
SDL Professional Services
SDL Training & Certification
Language Technology Partner Group
SDL Academic Partners
SDL Enterprise Technology Partners
ETUG (European Trados User Group) Public Information
Machine Translation User Group
Nordic SDL Tridion Docs User Group
SDL Tridion UK Meetup
SDL Tridion User Group New England
SDL Tridion West Coast User Group
SDL WorldServer User Group
Tridion Docs Europe & APAC User Group
Tridion User Group Benelux
Tridion User Group Ohio Valley
SDL MultiTerm Ideas
SDL Passolo Ideas
SDL Trados GroupShare Ideas
SDL Trados Studio Ideas
SDL Machine Translation Cloud Ideas
SDL Machine Translation Edge Ideas
SDL Language Cloud TMS Ideas
SDL Language Cloud Terminology Ideas
SDL Language Cloud Online Editor Ideas
SDL Managed Translation - Enterprise Ideas
SDL TMS Ideas
SDL WorldServer Ideas
SDL Tridion Docs Ideas
SDL Tridion Sites Ideas
SDL LiveContent S1000D Ideas
SDL Contenta S1000D
SDL XPP Ideas
Events & Webinars
To SDL Documentation
To SDL Support
What's New in SDL
Detecting language please wait for.......
I have noticed that NMT engine tends to truncate or totally distort some drug molecule names. It totally scrambles everything and invents words instead. See screenshot hereunder. I would like to point out that this does NOT happen with Language Cloud engines (I checked it on the same file, same segments, etc.), and since NMT is supposed to be more powerful and efficient than Language Cloud, this should be resolved ASAP.
Isla ... on behalf of all medical translators
SDL Machine Translation Cloud (aka BeGlobal v4 NMT) translation provider plugin for SDL Trados Studio 2019 does not yet support Dictionary. There are plans to add it, but don't know when that will be.…
would it help / be possible for the NMT engines to use an SDL Language Cloud Terminology termbase (which includes such non-translatable medical terms) as an MT dictionary?
Though the MT dictionaries…
There is an upgrade path to a paid subscription of SDL Machine Translation that will allow you to use its Dictionary feature: https://docs.sdl.com/LiveContent/content/en-US/SDL%20BeGlobal…
Isla, as Martin pointed out, NMT will struggle with very long strings full of tags and unknown words, not normally found in English dictionary (or in corpora used to train the MT engine). These are a domain specific terms (Medical) for which more useful would be a custom-trained engine.
The quality of the MT output also depends on what filter on MT side is used to parse the content. You may get different results when you send the same string with tags converted to XLIFF, SDLXLIFF or HTML format
In your example I can see the segmentation could be improved e.g. ( <p> <ul> and <li> tags should be set as Structure tags), so you get each list item on a new segment. In that case you'll get better leverage from a TM and Machine translation.
Though the MT dictionaries just provide an override mechanism / simple search and replace of dictionary entries in the NMT output, it might actually provide to be very beneficial in this case.
See https://gateway.sdl.com/apex/communityknowledge?articleName=000004051 - I think it is still valid for NMT?
SDL Machine Translation Cloud (aka BeGlobal v4 NMT) translation provider plugin for SDL Trados Studio 2019 does not yet support Dictionary. There are plans to add it, but don't know when that will be.
SDL Language Cloud provider does provide Dictionary support, but it is for SMT (Statistical MT) and soon to be deprecated.
In Isla's case the first step should be to resolve the segmentation which should help. If the medical terms in brackets () don't need to be translated then in Studio they could be added to a Variable Lists within Language resource Template alternatively crafting some Regex rules in filter settings to lock them/turn them into placeholders during text extraction.
There is an upgrade path to a paid subscription of SDL Machine Translation that will allow you to use its Dictionary feature: https://docs.sdl.com/LiveContent/content/en-US/SDL%20BeGlobal%20Online%20Help-v1/GUID-C0E595E6-28F5-4C59-8BBB-CAF8620FB4FA.
The Trados Studio to SDL Machine Translation Cloud plugin is being updated to include the ability for users to select which Dictionary to use while they're in Trados Studio. You can watch for updates here: https://appstore.sdl.com/language/app/sdl-machine-translation-cloud/941/.
If you are interested in the upgrade plan, SDL sales reps can walk you through your options.