Родительская модель
otherentity
ID: parentmodel
Related Papers
An Empirical Study of Language Relatedness for Transfer Learning in Neural Machine Translation
Neural Machine Translation (NMT) is known to outperform Phrase Based Sta- tistical Machine Translation (PBSMT) for resource rich language pairs but not for resource poor ones. Transfer Learning (Zoph et …...
Trivial Transfer Learning for Low-Resource Neural Machine Translation
AbstractTransfer learning has been proven as an effective technique for neural machine translation under low-resource conditions. Existing methods require a common target language, language relatedness, or specific training tricks and …...
Addressing word-order Divergence in Multilingual Neural Machine Translation for extremely Low Resource Languages
AbstractTransfer learning approaches for Neural Machine Translation (NMT) train a NMT model on an assisting language-target language pair (parent model) which is later fine-tuned for the source language-target language pair …...