Translation Artifacts in Cross-lingual Transfer Learning

Understand

Both human and machine translation play a central role in cross-lingual transfer learning: many multilingual datasets have been created through professional translation services, and using machine translation to translate either the test set or the training set is a widely used transfer technique.

• In this paper, we show that such translation process can introduce subtle artifacts that have a notable impact in existing cross-lingual models.
• For instance, in natural language inference, translating the premise and the hypothesis independently can reduce the lexical overlap between them, which current models are highly sensitive to.
• We show that some previous findings in cross-lingual transfer learning need to be reconsidered in the light of this phenomenon.