Бір доменді шығарып тастау арқылы оқыту
method
ID: leaveonedomainouttraining
Related Papers
Domain Generalisation of NMT: Fusing Adapters with Leave-One-Domain-Out Training
AbstractGeneralising to unseen domains is under-explored and remains a challenge in neural machine translation. Inspired by recent research in parameter-efficient transfer learning from pretrained models, this paper proposes a fusion-based …...