359 citations · 2k across the 127 of their papers we have counts for
26 papers · 1 filter
Diformer: Directional Transformer for Neural Machine Translation
Minghan Wang, Jiaxin Guo, Yuxia Wang +8
Autoregressive (AR) and Non-autoregressive (NAR) models have their own superiority on the performance and latency, combining them into one model may take advantage of both. Current…
Joint-training on Symbiosis Networks for Deep Nueral Machine Translation models
Zhengzhe Yu, Jiaxin Guo, Minghan Wang +11
Deep encoders have been proven to be effective in improving neural machine translation (NMT) systems, but it reaches the upper bound of translation quality when the number of encod…
Self-Distillation Mixup Training for Non-autoregressive Neural Machine Translation
Jiaxin Guo, Minghan Wang, Daimeng Wei +11
Recently, non-autoregressive (NAT) models predict outputs in parallel, achieving substantial improvements in generation speed compared to autoregressive (AT) models. While performi…
Charge resolution in the isochronous mass spectrometry and the mass of Co
Xu Zhou, Meng Wang, Yu-Hu Zhang +25
Isochronous mass spectrometry (IMS) of heavyion storage rings is a powerful tool for the mass measurements of short-lived nuclei. In IMS experiments, masses are determined through…
Alpha-robust investment-reinsurance strategy for a mean-variance insurer with delay
Min Zhang, Yong He
In this paper, a robust optimal reinsurance-investment problem with delay is studied under the -maxmin mean-variance criterion. The surplus process of an insurance company appro…
Interpreting Dense Retrieval as Mixture of Topics
Jingtao Zhan, Jiaxin Mao, Yiqun Liu +3
Dense Retrieval (DR) reaches state-of-the-art results in first-stage retrieval, but little is known about the mechanisms that contribute to its success. Therefore, in this work, we…