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.
| Name | Size | |
|---|---|---|
|
main-2327-PhamMinhQuang.pdf
md5:c2db23c132297b90a385481171fff2c2 |
284.7 kB | Download |
| All versions | This version | |
|---|---|---|
| Views | 96 | 96 |
| Downloads | 68 | 68 |
| Data volume | 19.4 MB | 19.4 MB |
| Unique views | 79 | 79 |
| Unique downloads | 65 | 65 |
- Publication date:
- February 12, 2021
- DOI:
-
- Keyword(s):
- Neural Machine Translation Multi-domain MT Domain Adaptation
- Published in:
- Transactions of the Association for Computational Linguistics: 9.
- Grants:
-
European Commission:
- ANITA - Advanced tools for fighting oNline Illegal TrAfficking (787061)
- Communities:
- License (for files):
- Creative Commons Attribution 4.0 International