325 citations · 1.4k across the 89 of their papers we have counts for
13 papers · 1 filter
Learning to Refine Source Representations for Neural Machine Translation
Xinwei Geng, Longyue Wang, Xing Wang +3
Neural machine translation (NMT) models generally adopt an encoder-decoder architecture for modeling the entire translation process. The encoder summarizes the representation of in…
Neural Machine Translation with Adequacy-Oriented Learning
Xiang Kong, Zhaopeng Tu, Shuming Shi +2
Although Neural Machine Translation (NMT) models have advanced state-of-the-art performance in machine translation, they face problems like the inadequate translation. We attribute…
Multi-Head Attention with Disagreement Regularization
Jian Li, Zhaopeng Tu, Baosong Yang +2
Multi-head attention is appealing for the ability to jointly attend to information from different representation subspaces at different positions. In this work, we introduce a disa…
Modeling Localness for Self-Attention Networks
Baosong Yang, Zhaopeng Tu, Derek F. Wong +3
Self-attention networks have proven to be of profound value for its strength of capturing global dependencies. In this work, we propose to model localness for self-attention networ…
Exploiting Deep Representations for Neural Machine Translation
Zi-Yi Dou, Zhaopeng Tu, Xing Wang +2
Advanced neural machine translation (NMT) models generally implement encoder and decoder as multiple layers, which allows systems to model complex functions and capture complicated…
Learning to Jointly Translate and Predict Dropped Pronouns with a Shared Reconstruction Mechanism
Longyue Wang, Zhaopeng Tu, Andy Way +1
Pronouns are frequently omitted in pro-drop languages, such as Chinese, generally leading to significant challenges with respect to the production of complete translations. Recentl…
Convolutional Self-Attention Network
Baosong Yang, Longyue Wang, Derek F. Wong +2
Self-attention network (SAN) has recently attracted increasing interest due to its fully parallelized computation and flexibility in modeling dependencies. It can be further enhanc…
Design Space Exploration of Neural Network Activation Function Circuits
Tao Yang, Yadong Wei, Zhijun Tu +4
The widespread application of artificial neural networks has prompted researchers to experiment with FPGA and customized ASIC designs to speed up their computation. These implement…
Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory
Deng Cai, Yan Wang, Victoria Bi +4
For dialogue response generation, traditional generative models generate responses solely from input queries. Such models rely on insufficient information for generating a specific…
Neural Machine Translation with Key-Value Memory-Augmented Attention
Fandong Meng, Zhaopeng Tu, Yong Cheng +4
Although attention-based Neural Machine Translation (NMT) has achieved remarkable progress in recent years, it still suffers from issues of repeating and dropping translations. To…
Towards Robust Neural Machine Translation
Yong Cheng, Zhaopeng Tu, Fandong Meng +2
Small perturbations in the input can severely distort intermediate representations and thus impact translation quality of neural machine translation (NMT) models. In this paper, we…
Generative Stock Question Answering
Zhaopeng Tu, Yong Jiang, Xiaojiang Liu +2
We study the problem of stock related question answering (StockQA): automatically generating answers to stock related questions, just like professional stock analysts providing act…
Translating Pro-Drop Languages with Reconstruction Models
Longyue Wang, Zhaopeng Tu, Shuming Shi +3
Pronouns are frequently omitted in pro-drop languages, such as Chinese, generally leading to significant challenges with respect to the production of complete translations. To date…