-
BERTTune: Fine-Tuning Neural Machine Translation with BERTScore
Neural machine translation models are often biased toward the limited translation references seen during training. To amend this, we propose fine-tuning the models with a novel... -
Chinese–Japanese Unsupervised Neural Machine Translation Using Sub-character ...
Chinese–Japanese Unsupervised Neural Machine Translation Using Sub-character Level Information -
Multilingual denoising pre-training for neural machine translation
Multilingual denoising pre-training for neural machine translation -
WMT17 Chinese-English, WMT14 English-French, WAT17 English-Japanese
The dataset used in the paper is a large-scale dataset for neural machine translation (NMT) task, consisting of 20.6M sentence pairs for Chinese-English, 35.5M sentence pairs... -
Tensor2Tensor for Neural Machine Translation
Tensor2Tensor for neural machine translation. -
Exploring the Effect of Noise and Architecture on Neural Machine Translation
A dataset for exploring the effect of noise and architecture on neural machine translation.