Customizing NMT Engines – Automated In-domain Adaptation

Home/Customizing NMT Engines – Automated In-domain Adaptation
We are monitoring the COVID-19 situation with concern for the well-being of all our LocWorld network. We plan to hold LocWorld42 Berlin and hope to see you there. Should your conference plans be impacted by travel restrictions, illness or health concerns, please rest assured that your registration fee will be fully refunded.
Customizing NMT Engines - Automated In-domain Adaptation
Track: TAUS | S3 |
Wednesday, April 4, 2018, 2:45pm – 3:30pm
Held in: S
Gábor Bessenyei - Globalese 
Riki Izawa - Kawamura International
Host: Anne-Maj van der Meer

One of the challenges in neural machine translation (NMT) is its lack of customizability — the ability to configure the engines with glossary and style guides. Globalese 3.1, an NMT system developed by Morphologic Localisation, introduces the new feature augmented in-domain adaptation where a user can use a smaller amount of core corpora and larger auxiliary corpora to build an NMT engine which is trained for a specific domain. In this presentation, we will explain this new feature and present some case studies in Asian and European languages.

Takeaways: Attendees will learn the latest development in research on the customization of NMT engines and tips on building an effective domain-specific NMT engine.