148 citations · 708 across the 141 of their papers we have counts for
13 papers · 1 filter
A Sparse Expansion For Deep Gaussian Processes
Liang Ding, Rui Tuo, Shahin Shahrampour
In this work, we use Deep Gaussian Processes (DGPs) as statistical surrogates for stochastic processes with complex distributions. Conventional inferential methods for DGP models c…
On the Complementarity between Pre-Training and Back-Translation for Neural Machine Translation
Xuebo Liu, Longyue Wang, Derek F. Wong +4
Pre-training (PT) and back-translation (BT) are two simple and powerful methods to utilize monolingual data for improving the model performance of neural machine translation (NMT).…
Unified Instance and Knowledge Alignment Pretraining for Aspect-based Sentiment Analysis
Juhua Liu, Qihuang Zhong, Liang Ding +3
Aspect-based Sentiment Analysis (ABSA) aims to determine the sentiment polarity towards an aspect. Because of the expensive and limited labelled data, the pretraining strategy has…
Improving Neural Machine Translation by Bidirectional Training
Liang Ding, Di Wu, Dacheng Tao
We present a simple and effective pretraining strategy -- bidirectional training (BiT) for neural machine translation. Specifically, we bidirectionally update the model parameters…
The USYD-JD Speech Translation System for IWSLT 2021
Liang Ding, Di Wu, Dacheng Tao
This paper describes the University of Sydney& JD's joint submission of the IWSLT 2021 low resource speech translation task. We participated in the Swahili-English direction and go…
On the Copying Behaviors of Pre-Training for Neural Machine Translation
Xuebo Liu, Longyue Wang, Derek F. Wong +4
Previous studies have shown that initializing neural machine translation (NMT) models with the pre-trained language models (LM) can speed up the model training and boost the model…
Progressive Multi-Granularity Training for Non-Autoregressive Translation
Liang Ding, Longyue Wang, Xuebo Liu +3
Non-autoregressive translation (NAT) significantly accelerates the inference process via predicting the entire target sequence. However, recent studies show that NAT is weak at lea…
Rejuvenating Low-Frequency Words: Making the Most of Parallel Data in Non-Autoregressive Translation
Liang Ding, Longyue Wang, Xuebo Liu +3
Knowledge distillation (KD) is commonly used to construct synthetic data for training non-autoregressive translation (NAT) models. However, there exists a discrepancy on low-freque…
Self-Guided Curriculum Learning for Neural Machine Translation
Lei Zhou, Liang Ding, Kevin Duh +3
In the field of machine learning, the well-trained model is assumed to be able to recover the training labels, i.e. the synthetic labels predicted by the model should be as close t…
Bridging the Gap Between Clean Data Training and Real-World Inference for Spoken Language Understanding
Di Wu, Yiren Chen, Liang Ding +1
Spoken language understanding (SLU) system usually consists of various pipeline components, where each component heavily relies on the results of its upstream ones. For example, In…
Towards Efficiently Diversifying Dialogue Generation via Embedding Augmentation
Yu Cao, Liang Ding, Zhiliang Tian +1
Dialogue generation models face the challenge of producing generic and repetitive responses. Unlike previous augmentation methods that mostly focus on token manipulation and ignore…
MirrorAlign: A Super Lightweight Unsupervised Word Alignment Model via Cross-Lingual Contrastive Learning
Di Wu, Liang Ding, Shuo Yang +1
Word alignment is essential for the downstream cross-lingual language understanding and generation tasks. Recently, the performance of the neural word alignment models has exceeded…
Understanding and Improving Lexical Choice in Non-Autoregressive Translation
Liang Ding, Longyue Wang, Xuebo Liu +3
Knowledge distillation (KD) is essential for training non-autoregressive translation (NAT) models by reducing the complexity of the raw data with an autoregressive teacher model. I…