
Progressive MultiGranularity Training for NonAutoregressive Translation
Nonautoregressive translation (NAT) significantly accelerates the infer...
read it

Rejuvenating LowFrequency Words: Making the Most of Parallel Data in NonAutoregressive Translation
Knowledge distillation (KD) is commonly used to construct synthetic data...
read it

SelfGuided Curriculum Learning for Neural Machine Translation
In the field of machine learning, the welltrained model is assumed to b...
read it

Bridging the Gap Between Clean Data Training and RealWorld Inference for Spoken Language Understanding
Spoken language understanding (SLU) system usually consists of various p...
read it

Towards Efficiently Diversifying Dialogue Generation via Embedding Augmentation
Dialogue generation models face the challenge of producing generic and r...
read it

SLUA: A Super Lightweight Unsupervised Word Alignment Model via CrossLingual Contrastive Learning
Word alignment is essential for the downstreaming crosslingual languag...
read it

Understanding and Improving Encoder Layer Fusion in SequencetoSequence Learning
Encoder layer fusion (EncoderFusion) is a technique to fuse all the enco...
read it

Understanding and Improving Lexical Choice in NonAutoregressive Translation
Knowledge distillation (KD) is essential for training nonautoregressive...
read it

Predicting Terrain Mechanical Properties in Sight for Planetary Rovers with Semantic Clues
Nongeometric mobility hazards such as rover slippage and sinkage posing...
read it

ContextAware CrossAttention for NonAutoregressive Translation
Nonautoregressive translation (NAT) significantly accelerates the infer...
read it

Sample and Computationally Efficient Simulation Metamodeling in High Dimensions
Stochastic kriging has been widely employed for simulation metamodeling ...
read it

ZeroShot Translation Quality Estimation with Explicit CrossLingual Patterns
This paper describes our submission of the WMT 2020 Shared Task on Sente...
read it

SlotRefine: A Fast NonAutoregressive Model for Joint Intent Detection and Slot Filling
Slot filling and intent detection are two main tasks in spoken language ...
read it

A projected gradient method for αℓ_1βℓ_2 sparsity regularization
The nonconvex α·_ℓ_1β·_ℓ_2 (α≥β≥0) regularization has attracted attent...
read it

αℓ_1βℓ_2 sparsity regularization for nonlinear illposed problems
In this paper, we consider the α·_ℓ_1β·_ℓ_2 sparsity regularization wit...
read it

Fault Tolerant Free Gait and Footstep Planning for Hexapod Robot Based on MonteCarlo Tree
Legged robots can pass through complex field environments by selecting g...
read it

Overcoming the Curse of Dimensionality in Density Estimation with Mixed Sobolev GANs
We propose a novel GAN framework for nonparametric density estimation w...
read it

SelfAttention with CrossLingual Position Representation
Position encoding (PE), an essential part of selfattention networks (SA...
read it

Generalization Guarantees for Sparse Kernel Approximation with Entropic Optimal Features
Despite their success, kernel methods suffer from a massive computationa...
read it

BdryGP: a new Gaussian process model for incorporating boundary information
Gaussian processes (GPs) are widely used as surrogate models for emulati...
read it

Recurrent Graph Syntax Encoder for Neural Machine Translation
Syntaxincorporated machine translation models have been proven successf...
read it

The University of Sydney's Machine Translation System for WMT19
This paper describes the University of Sydney's submission of the WMT 20...
read it

Knowledge Gradient for Selection with Covariates: Consistency and Computation
Knowledge gradient is a design principle for developing Bayesian sequent...
read it

Scalable Stochastic Kriging with Markovian Covariances
Stochastic kriging is a popular technique for simulation metamodeling du...
read it

Efficient Learning of Optimal Markov Network Topology with kTree Modeling
The seminal work of Chow and Liu (1968) shows that approximation of a fi...
read it
Liang Ding
is this you? claim profile