Viewing Knowledge Transfer in Multilingual Machine Translation Through a Representational Lens
Submission Type: Regular Long Paper
Submission Track: Machine Translation
Submission Track 2: Multilinguality and Linguistic Diversity
Keywords: multilingual machine translation, cross-lingual knowledge transfer
Abstract: 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 \textit{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. Based on this, we develop a novel training scheme, which uses an auxiliary similarity loss that encourages representations to be more invariant across languages by taking advantage of multi-parallel data. We show that our method yields increased translation quality for low- and mid-resource languages across multiple data and model setups.\footnote{We will release our code upon acceptance.}
Submission Number: 1632
Loading