Viewing Knowledge Transfer in Multilingual Machine Translation Through a Representational Lens

Understand

We argue that translation quality alone is not a sufficient metric for measuring knowledge transfer in multilingual neural machine translation.

• To support this claim, we introduce Representational Transfer Potential (RTP), which measures representational similarities between languages.
• We show that RTP can measure both positive and negative transfer (interference), and find that RTP is strongly correlated with changes in translation quality, indicating that transfer does occur.
• Furthermore, we investigate data and language characteristics that are relevant for transfer, and find that multi-parallel overlap is an important yet under-explored feature.