research
∙
06/15/2023
Understanding Parameter Sharing in Transformers
Parameter sharing has proven to be a parameter-efficient approach. Previ...
share
research
∙
06/07/2023
MobileNMT: Enabling Translation in 15MB and 30ms
Deploying NMT models on mobile devices is essential for privacy, low lat...
research
∙
05/10/2023
Multi-Path Transformer is Better: A Case Study on Neural Machine Translation
For years the model performance in machine learning obeyed a power-law r...
research
∙
09/16/2021
The NiuTrans System for WNGT 2020 Efficiency Task
This paper describes the submissions of the NiuTrans Team to the WNGT 20...
research
∙
09/16/2021
The NiuTrans System for the WMT21 Efficiency Task
This paper describes the NiuTrans system for the WMT21 translation effic...
research
∙
09/09/2021
Bag of Tricks for Optimizing Transformer Efficiency
Improving Transformer efficiency has become increasingly attractive rece...
research
∙
01/03/2021
An Efficient Transformer Decoder with Compressed Sub-layers
The large attention-based encoder-decoder network (Transformer) has beco...
research
∙
11/30/2020
A Simple and Effective Approach to Robust Unsupervised Bilingual Dictionary Induction
Unsupervised Bilingual Dictionary Induction methods based on the initial...
research
∙
09/19/2020
Weight Distillation: Transferring the Knowledge in Neural Network Parameters
Knowledge distillation has been proven to be effective in model accelera...
research
∙
09/17/2020
Towards Fully 8-bit Integer Inference for the Transformer Model
8-bit integer inference, as a promising direction in reducing both the l...
research
∙
05/27/2020
General-Purpose User Embeddings based on Mobile App Usage
In this paper, we report our recent practice at Tencent for user modelin...
research
∙
04/07/2020
CSRN: Collaborative Sequential Recommendation Networks for News Retrieval
Nowadays, news apps have taken over the popularity of paper-based media,...
research
∙
11/28/2019