Better Neural Machine Translation by Extracting Linguistic Information from BERT
Hassan S. Shavarani, Anoop Sarkar · 2021
Adding linguistic information (syntax or semantics) to neural machine translation (NMT) has mostly focused on using point estimates from pre-trained models.Directly using the capacity of massive pre-trained contextual word embedding models such as BERT (Devlin et al., 2019) has been marginally useful in NMT because effective fine-tuning is difficult to obtain for NMT without making training brittle and unreliable.We augment NMT by extracting dense fine-tuned vector-based linguistic information from BERT instead of using point estimates.Experimental results show that our method of incorporating linguistic information helps NMT to generalize better in a variety of training contexts and is no more difficult to train than conventional Transformerbased NMT.