1. Fixing weight decay regularization in Adam;loshchilov;arXiv 1711 05101,2017
2. RoBERTa: A robustly optimized BERT pretraining approach;liu;arXiv 1907 11692,2019
3. Improving unsupervised word-by-word translation using language model and denoising autoencoder;kim;Proc EMNLP,0
4. AER: Do we need to ‘improve’ our alignments?;vilar;Proc Int Workshop Spoken Lang Transl,2006
5. Introduction of the Asian Language Treebank