Search Results for author:
Found 18 papers, 5 papers with code
The NiuTrans System for the WMT 2021 Efficiency Task
This paper describes the NiuTrans system for the WMT21 translation efficiency task.
Orthogonal greedy algorithm for linear operator learning with shallow neural network
Greedy algorithms, particularly the orthogonal greedy algorithm (OGA), have proven effective in training shallow neural networks for fitting functions and solving partial differential equations (PDEs).
Green Multigrid Network
Second, the asymptotic smoothness property of Green's function is used to leverage the Multi-Level Multi-Integration (MLMI) algorithm for both the training and inference stages.
Understanding Parameter Sharing in Transformers
Inspired by this, we tune the training hyperparameters related to model convergence in a targeted manner.
MobileNMT: Enabling Translation in 15MB and 30ms
With the co-design of model and engine, compared with the existing system, we speed up 47. 0x and save 99. 5% of memory with only 11. 6% loss of BLEU.
Multi-Path Transformer is Better: A Case Study on Neural Machine Translation
For years the model performance in machine learning obeyed a power-law relationship with the model size.
The NiuTrans System for WNGT 2020 Efficiency Task
This paper describes the submissions of the NiuTrans Team to the WNGT 2020 Efficiency Shared Task.
The NiuTrans System for the WMT21 Efficiency Task
This paper describes the NiuTrans system for the WMT21 translation efficiency task (http://statmt. org/wmt21/efficiency-task. html).
Bag of Tricks for Optimizing Transformer Efficiency
Improving Transformer efficiency has become increasingly attractive recently.
An Efficient Transformer Decoder with Compressed Sub-layers
The large attention-based encoder-decoder network (Transformer) has become prevailing recently due to its effectiveness.
A Simple and Effective Approach to Robust Unsupervised Bilingual Dictionary Induction
Our experiments show that this simple method does not hamper the performance of similar language pairs and achieves an accuracy of 13. 64~55. 53% between English and four distant languages, i. e., Chinese, Japanese, Vietnamese and Thai.
Weight Distillation: Transferring the Knowledge in Neural Network Parameters
Inspired by this, we investigate methods of model acceleration and compression in another line of research.
Towards Fully 8-bit Integer Inference for the Transformer Model
8-bit integer inference, as a promising direction in reducing both the latency and storage of deep neural networks, has made great progress recently.
General-Purpose User Embeddings based on Mobile App Usage
In this paper, we report our recent practice at Tencent for user modeling based on mobile app usage.
CSRN: Collaborative Sequential Recommendation Networks for News Retrieval
Recurrent Neural Network (RNN)-based sequential recommendation is a popular approach that utilizes users' recent browsing history to predict future items.
Unsupervised Many-to-Many Image-to-Image Translation Across Multiple Domains
To improve the image quality, we propose an effective many-to-many mapping framework for unsupervised multi-domain image-to-image translation.
The NiuTrans Machine Translation Systems for WMT19
We participated in 13 translation directions, including 11 supervised tasks, namely EN↔{ZH, DE, RU, KK, LT}, GU→EN and the unsupervised DE↔CS sub-track.
The NiuTrans Machine Translation System for WMT18
This paper describes the submission of the NiuTrans neural machine translation system for the WMT 2018 Chinese ↔ English news translation tasks.
