Conference paper Open Access

SYSTRAN @ WMT 2021: Terminology Task

Pham, MinhQuang; Senellart, Antoine; Berrebbi, Dan; Crego, Josep; Senellart, Jean

This paper describes SYSTRAN submissions to the WMT 2021 terminology shared task. We participate in the English-to-French translation direction with a standard Transformer neural machine translation network that we enhance with the ability to dynamically include terminology constraints, a very common industrial practice. Two state-of-the-art terminology insertion methods are evaluated based (i) on the use of placeholders complemented with morphosyntactic annotation and (ii) on the use of target constraints injected in the source stream. Results show the suitability of the presented approaches in the evaluated scenario where terminology is used in a system trained on generic data only.

Files (192.7 kB)
Name Size
192.7 kB Download
All versions This version
Views 110110
Downloads 120120
Data volume 23.1 MB23.1 MB
Unique views 9595
Unique downloads 107107


Cite as