Conference paper Open Access

Integrating Domain Terminology into Neural Machine Translation

Elise Michon; Josep Crego; Jean Senellart

This paper extends existing work on terminology integration into Neural Machine Translation, a common industrial practice to dynamically adapt translation to a specific domain. Our method, based on the use of placeholders complemented with morphosyntactic annotation, efficiently taps into the ability of the neural network to deal with symbolic knowledge to surpass the surface generalization shown by alternative techniques. We compare our approach to state-of-the-art systems and benchmark them through a well-defined evaluation framework, focusing on actual application of terminology and not just on the overall performance. Results indicate the suitability of our method in the use-case where terminology is used in a system trained on generic data only.

Files (268.4 kB)
Name Size
2020.coling-main.348.pdf
md5:fc8e91b7e16396d94491fe75542f0378
268.4 kB Download
33
20
views
downloads
Views 33
Downloads 20
Data volume 5.4 MB
Unique views 22
Unique downloads 19

Share

Cite as