This site uses cookies.
Some of these cookies are essential to the operation of the site,
while others help to improve your experience by providing insights into how the site is being used.
For more information, please see the ProZ.com privacy policy.
Adding a glossary to an MT output can give mixed results. It may be very helpful but also make a lot of unwanted/unwarranted changes especially for words that can have different meanings or those that can be a Noun, a Verb, an Adjective etc. that's the kind of things that can confuse an engine.
So, is anybody using it? and what type of results are you experiencing in the field you're translating in?
By the way, the only other official information I could find was this: https://support.deepl.com/hc/en-us/articles/360021638100-Glossary-availability I think, it would be useful if DeepL would produce a quick and simple guide on how to prepare a glossary for MT, since it will impact very much your results. As a 2 cents advice, I would suggest avoiding the kind of words described above, sticking to the most important words for you (i.e. those that MT usually get wrong) and making sure you have only 1 source word and one target word (no additional information like variants etc.). Last suggestion would be to keep it slim (few words, not a massive glossary). If what I'm saying is wrong, please correct me
Translation Office 3000 is an advanced accounting tool for freelance translators and small agencies. TO3000 easily and seamlessly integrates with the business life of professional freelance translators.
Translate faster & easier, using a sophisticated CAT tool built by a translator / developer.
Accept jobs from clients who use Trados, MemoQ, Wordfast & major CAT tools.
Download and start using CafeTran Espresso -- for free