Domain adapted machine translation: What does catastrophic forgetting forget and why?
This addresses the problem of maintaining generic translation quality for machine learning practitioners and researchers, but it is incremental as it builds on existing observations of forgetting.
The paper investigates catastrophic forgetting in neural machine translation during domain adaptation, showing that the amount and type of forgetting is linked to the target vocabulary coverage of the in-domain data.
Neural Machine Translation (NMT) models can be specialized by domain adaptation, often involving fine-tuning on a dataset of interest. This process risks catastrophic forgetting: rapid loss of generic translation quality. Forgetting has been widely observed, with many mitigation methods proposed. However, the causes of forgetting and the relationship between forgetting and adaptation data are under-explored. This paper takes a novel approach to understanding catastrophic forgetting during NMT adaptation by investigating the impact of the data. We provide a first investigation of what is forgotten, and why. We examine the relationship between forgetting and the in-domain data, and show that the amount and type of forgetting is linked to that data's target vocabulary coverage. Our findings pave the way toward better informed NMT domain adaptation.