Domain robustness in neural machine translation

Translating text that diverges from the training domain is a key challenge for machine translation. Domain robustnes - the generalization of models to unseen test domains - is low for both statistical (SMT) and neural machine translation (NMT). In this paper, we study the performance of SMT and NMT models on out-of-domain test sets. We find that in unknown domains, SMT and NMT suffer from very different problems: SMT systems are mostly adequate but not fluent, while NMT systems are mostly fluent, but not adequate. For NMT, we identify such hallucinations (translations that are fluent but unrelated to the source) as a key reason for low domain robustness. To mitigate this problem, we empirically compare methods that are reported to improve adequacy or in-domain robustness in terms of their effectiveness at improving domain robustness. In experiments on German→English OPUS data, and German→Romansh (a low-resource setting) we find that several methods improve domain robustness. While thosemethods do lead to higher BLEU scores overall, they only slightly increase the adequacy of translations compared to SMT