Multitasking with Translation Memories: How to Laugh, Cough and Sneeze in Parallel
Track: Multilingual AI | TA5 |
Friday, October 28, 2016, 9:00am – 9:45am
Held in: Fontaine CD
Alex Yanishevsky - Welocalize
Host: Anne-Marie Colliander Lind
In this presentation we will cover the entire translation memory (TM) life cycle to outline how translation memories can do double, triple or even quadruple duty such as validation, extracting customized domain-specific dictionaries, creating language models, advanced leveraging and machine translation using domain customized engines as well as digital style forensics for linguistic quality assurance (LQA) evaluation of translations.
Takeaways: Build targeted, domain-specific machine translation engines to improve translator productivity. Build language models and use digital style forensics to evaluate LQA errors that may be related to source or target content issues. Fix inconsistencies between glossaries and TMs to improve quality and consistency.