How Does Selective Mechanism Improve Self-Attention Networks?

May 03, 2020
Xinwei Geng, Longyue Wang, Xing Wang, Bing Qin, Ting Liu, Zhaopeng Tu

* ACL 2020 

  Access Model/Code and Paper
On the Inference Calibration of Neural Machine Translation

May 03, 2020
Shuo Wang, Zhaopeng Tu, Shuming Shi, Yang Liu

* Accepted by ACL2020 

  Access Model/Code and Paper
Assessing the Bilingual Knowledge Learned by Neural Machine Translation Models

Apr 28, 2020
Shilin He, Xing Wang, Shuming Shi, Michael R. Lyu, Zhaopeng Tu

* 10 pages 

  Access Model/Code and Paper
Go From the General to the Particular: Multi-Domain Translation with Domain Transformation Networks

Nov 22, 2019
Yong Wang, Longyue Wang, Shuming Shi, Victor O. K. Li, Zhaopeng Tu

* AAAI 2020 

  Access Model/Code and Paper
Neuron Interaction Based Representation Composition for Neural Machine Translation

Nov 22, 2019
Jian Li, Xing Wang, Baosong Yang, Shuming Shi, Michael R. Lyu, Zhaopeng Tu

* AAAI 2020 

  Access Model/Code and Paper
EmpGAN: Multi-resolution Interactive Empathetic Dialogue Generation

Nov 20, 2019
Qintong Li, Hongshen Chen, Zhaochun Ren, Zhumin Chen, Zhaopeng Tu, Jun Ma


  Access Model/Code and Paper
Towards Understanding Neural Machine Translation with Word Importance

Sep 17, 2019
Shilin He, Zhaopeng Tu, Xing Wang, Longyue Wang, Michael R. Lyu, Shuming Shi

* EMNLP 2019 

  Access Model/Code and Paper
Multi-Granularity Self-Attention for Neural Machine Translation

Sep 05, 2019
Jie Hao, Xing Wang, Shuming Shi, Jinfeng Zhang, Zhaopeng Tu

* EMNLP 2019 

  Access Model/Code and Paper
Towards Better Modeling Hierarchical Structure for Self-Attention with Ordered Neurons

Sep 04, 2019
Jie Hao, Xing Wang, Shuming Shi, Jinfeng Zhang, Zhaopeng Tu

* EMNLP 2019 

  Access Model/Code and Paper
Self-Attention with Structural Position Representations

Sep 01, 2019
Xing Wang, Zhaopeng Tu, Longyue Wang, Shuming Shi

* Accepted by EMNLP 2019 

  Access Model/Code and Paper
One Model to Learn Both: Zero Pronoun Prediction and Translation

Sep 01, 2019
Longyue Wang, Zhaopeng Tu, Xing Wang, Shuming Shi

* EMNLP 2019 

  Access Model/Code and Paper
Exploiting Sentential Context for Neural Machine Translation

Jun 04, 2019
Xing Wang, Zhaopeng Tu, Longyue Wang, Shuming Shi

* Accepted by ACL 2019 

  Access Model/Code and Paper
Assessing the Ability of Self-Attention Networks to Learn Word Order

Jun 03, 2019
Baosong Yang, Longyue Wang, Derek F. Wong, Lidia S. Chao, Zhaopeng Tu

* ACL 2019 

  Access Model/Code and Paper
Dynamic Past and Future for Neural Machine Translation

Apr 21, 2019
Zaixiang Zheng, Shujian Huang, Zhaopeng Tu, Xin-Yu Dai, Jiajun Chen

* In progress 

  Access Model/Code and Paper
Convolutional Self-Attention Networks

Apr 05, 2019
Baosong Yang, Longyue Wang, Derek Wong, Lidia S. Chao, Zhaopeng Tu

* NAACL 2019 

  Access Model/Code and Paper
Information Aggregation for Multi-Head Attention with Routing-by-Agreement

Apr 05, 2019
Jian Li, Baosong Yang, Zi-Yi Dou, Xing Wang, Michael R. Lyu, Zhaopeng Tu

* NAACL 2019 

  Access Model/Code and Paper
Modeling Recurrence for Transformer

Apr 05, 2019
Jie Hao, Xing Wang, Baosong Yang, Longyue Wang, Jinfeng Zhang, Zhaopeng Tu

* NAACL 2019 

  Access Model/Code and Paper
Dynamic Layer Aggregation for Neural Machine Translation with Routing-by-Agreement

Feb 15, 2019
Zi-Yi Dou, Zhaopeng Tu, Xing Wang, Longyue Wang, Shuming Shi, Tong Zhang

* AAAI 2019 

  Access Model/Code and Paper
Context-Aware Self-Attention Networks

Feb 15, 2019
Baosong Yang, Jian Li, Derek Wong, Lidia S. Chao, Xing Wang, Zhaopeng Tu

* AAAI 2019 

  Access Model/Code and Paper
Learning to Refine Source Representations for Neural Machine Translation

Dec 26, 2018
Xinwei Geng, Longyue Wang, Xing Wang, Bing Qin, Ting Liu, Zhaopeng Tu


  Access Model/Code and Paper
Neural Machine Translation with Adequacy-Oriented Learning

Nov 21, 2018
Xiang Kong, Zhaopeng Tu, Shuming Shi, Eduard Hovy, Tong Zhang

* AAAI 2019 

  Access Model/Code and Paper
Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory

Nov 02, 2018
Deng Cai, Yan Wang, Victoria Bi, Zhaopeng Tu, Xiaojiang Liu, Wai Lam, Shuming Shi


  Access Model/Code and Paper
Convolutional Self-Attention Network

Oct 31, 2018
Baosong Yang, Longyue Wang, Derek F. Wong, Lidia S. Chao, Zhaopeng Tu


  Access Model/Code and Paper
Multi-Head Attention with Disagreement Regularization

Oct 24, 2018
Jian Li, Zhaopeng Tu, Baosong Yang, Michael R. Lyu, Tong Zhang

* EMNLP 2018 

  Access Model/Code and Paper
Modeling Localness for Self-Attention Networks

Oct 24, 2018
Baosong Yang, Zhaopeng Tu, Derek F. Wong, Fandong Meng, Lidia S. Chao, Tong Zhang

* EMNLP 2018 

  Access Model/Code and Paper
Exploiting Deep Representations for Neural Machine Translation

Oct 24, 2018
Zi-Yi Dou, Zhaopeng Tu, Xing Wang, Shuming Shi, Tong Zhang

* EMNLP 2018 

  Access Model/Code and Paper
Learning to Jointly Translate and Predict Dropped Pronouns with a Shared Reconstruction Mechanism

Oct 15, 2018
Longyue Wang, Zhaopeng Tu, Andy Way, Qun Liu

* EMNLP 2018 

  Access Model/Code and Paper
Generative Stock Question Answering

Sep 20, 2018
Zhaopeng Tu, Yong Jiang, Xiaojiang Liu, Lei Shu, Shuming Shi

* data: http://ai.tencent.com/ailab/nlp/data/stockQA.tar.gz 

  Access Model/Code and Paper
Neural Machine Translation with Key-Value Memory-Augmented Attention

Jun 29, 2018
Fandong Meng, Zhaopeng Tu, Yong Cheng, Haiyang Wu, Junjie Zhai, Yuekui Yang, Di Wang

* Accepted at IJCAI 2018 

  Access Model/Code and Paper