A Case Study on How Neural MT Has Improved the Quality of MT Output

Home/A Case Study on How Neural MT Has Improved the Quality of MT Output
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.
A Case Study on How Neural MT Has Improved the Quality of MT Output
Track: TAUS | TS4 |
Wednesday, February 27, 2019, 4:15pm – 5:00pm
Held in: Kelantan
Presenters:
Michael Cárdenas - Local Concept 
Denis Gachot - SYSTRAN Software, Inc.
Host: Anne-Maj van der Meer

In this presentation we will share a case study where translators evaluated a neural machine translation (MT), a hybrid MT and a traditional human-based translation. Translators were also asked whether hybrid and neural MT throughput were good enough to edit, and what the time spent editing all three types of output was.

Takeaways: Attendees will learn how neural MT has improved the grading of the throughput.