UPDATE: Zenodo migration postponed to Oct 13 from 06:00-08:00 UTC. Read the announcement.

Journal article Open Access

Revisiting Multi-Domain Machine Translation

MinhQuang Pham; Josep Crego; François Yvon

When building machine translation systems, one often needs to make the best out of heterogeneous sets of parallel data in training, and to robustly handle inputs from un-expected domains in testing. This multi-domain scenario has attracted a lot of recent work, that fall under the general umbrella of transfer learning. In this study, we revisit multi-domain machine translation, with the aim to formulate the motivations for developing such systems and the associated expectations with respect to performance. Our experiments with a large sample of multi-domain systems show that most of these expectations are hardly met and suggest that further work is needed to better analyze the current behaviour of multi-domain systems and to make them fully hold their promises.

Files (284.7 kB)
Name Size
284.7 kB Download
All versions This version
Views 9696
Downloads 6868
Data volume 19.4 MB19.4 MB
Unique views 7979
Unique downloads 6565


Cite as