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.
Experimenting with DeepL: trying to improve inter-segment term consistency
Thread poster: Hans Lenting
Hans Lenting Netherlands Member (2006) German to Dutch
Mar 29, 2018
By default, DeepL will segment the input that you present to the system:
So, if you send these 4 related segments, they will be treated as 'not related', which can lead to inconsistent translation of terms (here: Gesamtanlage):
Maßzeichnung der Gesamtanlage Gesamtanlage starten Gesamtanlage nach Sicherheitsstopp starten Beschickung der Gesamtanlage
This result matches the results of the 4 individual segments:
However, when you force DeepL to interpret the 4 segments as 1 segment, thus making them related, you'll get a better result ('Gesamtanlage' is translated consistently):
(On a side note: This approach has the disadvantage that the chapter titles in the example are interpreted as instructions.)
Of course, the peepl at DeepL are working hard on improving inter-segment consistency (which is considered to be the Holy Grail of MT).
In the meantime we could try to let CT offer several segments at the same time and re-segment the translated result to the TM.
Subject:
Comment:
The contents of this post will automatically be included in the ticket generated. Please add any additional comments or explanation (optional)
Hans Lenting Netherlands Member (2006) German to Dutch
TOPIC STARTER
English as the inter-language
Mar 29, 2018
As long as DeepL makes this kind of 'mistakes', we human translators have nothing to fear:
Subject:
Comment:
The contents of this post will automatically be included in the ticket generated. Please add any additional comments or explanation (optional)
Hans Lenting Netherlands Member (2006) German to Dutch
TOPIC STARTER
Chopping up your source text in chunks of 5000 characters
Apr 5, 2018
Here are some nice macros to chop up your source text in chunks of 5000 characters, which is the maximum number of characters to insert in DeepL web:
One idea that comes to mind is to save these chunks of 5000 characters and the DeepL-generated translations as bitexts and import these in CafeTran Espresso 2018.
I'd have to investigate if this approach would improve terminological consistency. ▲ Collapse
Subject:
Comment:
The contents of this post will automatically be included in the ticket generated. Please add any additional comments or explanation (optional)
Hans Lenting Netherlands Member (2006) German to Dutch
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.
Manage your TMs and Terms ... and boost your translation business
Are you ready for something fresh in the industry? TM-Town is a unique new site for you -- the freelance translator -- to store, manage and share translation memories (TMs) and glossaries...and potentially meet new clients on the basis of your prior work.