3 papers
cs.LG2019
Distributed Equivalent Substitution Training for Large-Scale Recommender Systems
Haidong Rong, Yangzihao Wang, Feihu Zhou +8
We present Distributed Equivalent Substitution (DES) training, a novel distributed training framework for large-scale recommender systems with dynamic sparse features. DES introduc…
cs.CL2018
Neural Machine Translation with Key-Value Memory-Augmented Attention
Fandong Meng, Zhaopeng Tu, Yong Cheng +4
Although attention-based Neural Machine Translation (NMT) has achieved remarkable progress in recent years, it still suffers from issues of repeating and dropping translations. To…
cs.CL2018
Towards Robust Neural Machine Translation
Yong Cheng, Zhaopeng Tu, Fandong Meng +2
Small perturbations in the input can severely distort intermediate representations and thus impact translation quality of neural machine translation (NMT) models. In this paper, we…