Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Yeyun Gong

Yeyun Gong

EL-Attention: Memory Efficient Lossless Attention for Generation


May 11, 2021
Yu Yan, Jiusheng Chen, Weizhen Qi, Nikhil Bhendawade, Yeyun Gong, Nan Duan, Ruofei Zhang

Figure 1 for EL-Attention: Memory Efficient Lossless Attention for Generation
Figure 2 for EL-Attention: Memory Efficient Lossless Attention for Generation
Figure 3 for EL-Attention: Memory Efficient Lossless Attention for Generation
Figure 4 for EL-Attention: Memory Efficient Lossless Attention for Generation
* ICML 2021 
  Access Paper or Ask Questions

Poolingformer: Long Document Modeling with Pooling Attention


May 10, 2021
Hang Zhang, Yeyun Gong, Yelong Shen, Weisheng Li, Jiancheng Lv, Nan Duan, Weizhu Chen

Figure 1 for Poolingformer: Long Document Modeling with Pooling Attention
Figure 2 for Poolingformer: Long Document Modeling with Pooling Attention
Figure 3 for Poolingformer: Long Document Modeling with Pooling Attention
Figure 4 for Poolingformer: Long Document Modeling with Pooling Attention
* Accepted by ICML 2021 
  Access Paper or Ask Questions

ProphetNet-X: Large-Scale Pre-training Models for English, Chinese, Multi-lingual, Dialog, and Code Generation


Apr 16, 2021
Weizhen Qi, Yeyun Gong, Yu Yan, Can Xu, Bolun Yao, Bartuer Zhou, Biao Cheng, Daxin Jiang, Jiusheng Chen, Ruofei Zhang, Houqiang Li, Nan Duan

Figure 1 for ProphetNet-X: Large-Scale Pre-training Models for English, Chinese, Multi-lingual, Dialog, and Code Generation
Figure 2 for ProphetNet-X: Large-Scale Pre-training Models for English, Chinese, Multi-lingual, Dialog, and Code Generation
Figure 3 for ProphetNet-X: Large-Scale Pre-training Models for English, Chinese, Multi-lingual, Dialog, and Code Generation
Figure 4 for ProphetNet-X: Large-Scale Pre-training Models for English, Chinese, Multi-lingual, Dialog, and Code Generation

  Access Paper or Ask Questions

Mask Attention Networks: Rethinking and Strengthen Transformer


Mar 25, 2021
Zhihao Fan, Yeyun Gong, Dayiheng Liu, Zhongyu Wei, Siyuan Wang, Jian Jiao, Nan Duan, Ruofei Zhang, Xuanjing Huang

Figure 1 for Mask Attention Networks: Rethinking and Strengthen Transformer
Figure 2 for Mask Attention Networks: Rethinking and Strengthen Transformer
Figure 3 for Mask Attention Networks: Rethinking and Strengthen Transformer
Figure 4 for Mask Attention Networks: Rethinking and Strengthen Transformer
* Accepted as a long paper to NAACL 2021 
  Access Paper or Ask Questions

BANG: Bridging Autoregressive and Non-autoregressive Generation with Large Scale Pretraining


Dec 31, 2020
Weizhen Qi, Yeyun Gong, Jian Jiao, Yu Yan, Dayiheng Liu, Weizhu Chen, Kewen Tang, Houqiang Li, Jiusheng Chen, Ruofei Zhang, Ming Zhou, Nan Duan

Figure 1 for BANG: Bridging Autoregressive and Non-autoregressive Generation with Large Scale Pretraining
Figure 2 for BANG: Bridging Autoregressive and Non-autoregressive Generation with Large Scale Pretraining
Figure 3 for BANG: Bridging Autoregressive and Non-autoregressive Generation with Large Scale Pretraining
Figure 4 for BANG: Bridging Autoregressive and Non-autoregressive Generation with Large Scale Pretraining

  Access Paper or Ask Questions

Uncertainty-Aware Label Refinement for Sequence Labeling


Dec 19, 2020
Tao Gui, Jiacheng Ye, Qi Zhang, Zhengyan Li, Zichu Fei, Yeyun Gong, Xuanjing Huang

Figure 1 for Uncertainty-Aware Label Refinement for Sequence Labeling
Figure 2 for Uncertainty-Aware Label Refinement for Sequence Labeling
Figure 3 for Uncertainty-Aware Label Refinement for Sequence Labeling
Figure 4 for Uncertainty-Aware Label Refinement for Sequence Labeling
* Accepted by EMNLP 2020 
  Access Paper or Ask Questions

An Enhanced Knowledge Injection Model for Commonsense Generation


Dec 01, 2020
Zhihao Fan, Yeyun Gong, Zhongyu Wei, Siyuan Wang, Yameng Huang, Jian Jiao, Xuanjing Huang, Nan Duan, Ruofei Zhang

Figure 1 for An Enhanced Knowledge Injection Model for Commonsense Generation
Figure 2 for An Enhanced Knowledge Injection Model for Commonsense Generation
Figure 3 for An Enhanced Knowledge Injection Model for Commonsense Generation
Figure 4 for An Enhanced Knowledge Injection Model for Commonsense Generation
* Accepted to COLING 2020 
  Access Paper or Ask Questions

GLGE: A New General Language Generation Evaluation Benchmark


Nov 24, 2020
Dayiheng Liu, Yu Yan, Yeyun Gong, Weizhen Qi, Hang Zhang, Jian Jiao, Weizhu Chen, Jie Fu, Linjun Shou, Ming Gong, Pengcheng Wang, Jiusheng Chen, Daxin Jiang, Jiancheng Lv, Ruofei Zhang, Winnie Wu, Ming Zhou, Nan Duan

Figure 1 for GLGE: A New General Language Generation Evaluation Benchmark
Figure 2 for GLGE: A New General Language Generation Evaluation Benchmark
Figure 3 for GLGE: A New General Language Generation Evaluation Benchmark
Figure 4 for GLGE: A New General Language Generation Evaluation Benchmark
* 11 pages 
  Access Paper or Ask Questions

ProphetNet-Ads: A Looking Ahead Strategy for Generative Retrieval Models in Sponsored Search Engine


Oct 21, 2020
Weizhen Qi, Yeyun Gong, Yu Yan, Jian Jiao, Bo Shao, Ruofei Zhang, Houqiang Li, Nan Duan, Ming Zhou

Figure 1 for ProphetNet-Ads: A Looking Ahead Strategy for Generative Retrieval Models in Sponsored Search Engine
Figure 2 for ProphetNet-Ads: A Looking Ahead Strategy for Generative Retrieval Models in Sponsored Search Engine
Figure 3 for ProphetNet-Ads: A Looking Ahead Strategy for Generative Retrieval Models in Sponsored Search Engine
Figure 4 for ProphetNet-Ads: A Looking Ahead Strategy for Generative Retrieval Models in Sponsored Search Engine
* Accepted to NLPCC 2020 
  Access Paper or Ask Questions

Tell Me How to Ask Again: Question Data Augmentation with Controllable Rewriting in Continuous Space


Oct 04, 2020
Dayiheng Liu, Yeyun Gong, Jie Fu, Yu Yan, Jiusheng Chen, Jiancheng Lv, Nan Duan, Ming Zhou

Figure 1 for Tell Me How to Ask Again: Question Data Augmentation with Controllable Rewriting in Continuous Space
Figure 2 for Tell Me How to Ask Again: Question Data Augmentation with Controllable Rewriting in Continuous Space
Figure 3 for Tell Me How to Ask Again: Question Data Augmentation with Controllable Rewriting in Continuous Space
Figure 4 for Tell Me How to Ask Again: Question Data Augmentation with Controllable Rewriting in Continuous Space
* Accepted at EMNLP 2020 
  Access Paper or Ask Questions

RikiNet: Reading Wikipedia Pages for Natural Question Answering


Apr 30, 2020
Dayiheng Liu, Yeyun Gong, Jie Fu, Yu Yan, Jiusheng Chen, Daxin Jiang, Jiancheng Lv, Nan Duan

Figure 1 for RikiNet: Reading Wikipedia Pages for Natural Question Answering
Figure 2 for RikiNet: Reading Wikipedia Pages for Natural Question Answering
Figure 3 for RikiNet: Reading Wikipedia Pages for Natural Question Answering
Figure 4 for RikiNet: Reading Wikipedia Pages for Natural Question Answering
* Accepted at ACL 2020 
  Access Paper or Ask Questions

XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation


Apr 19, 2020
Yaobo Liang, Nan Duan, Yeyun Gong, Ning Wu, Fenfei Guo, Weizhen Qi, Ming Gong, Linjun Shou, Daxin Jiang, Guihong Cao, Xiaodong Fan, Bruce Zhang, Rahul Agrawal, Edward Cui, Sining Wei, Taroon Bharti, Ying Qiao, Jiun-Hung Chen, Winnie Wu, Shuguang Liu, Fan Yang, Rangan Majumder, Ming Zhou

Figure 1 for XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation
Figure 2 for XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation
Figure 3 for XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation
Figure 4 for XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation

  Access Paper or Ask Questions

Diverse, Controllable, and Keyphrase-Aware: A Corpus and Method for News Multi-Headline Generation


Apr 08, 2020
Dayiheng Liu, Yeyun Gong, Jie Fu, Wei Liu, Yu Yan, Bo Shao, Daxin Jiang, Jiancheng Lv, Nan Duan

Figure 1 for Diverse, Controllable, and Keyphrase-Aware: A Corpus and Method for News Multi-Headline Generation
Figure 2 for Diverse, Controllable, and Keyphrase-Aware: A Corpus and Method for News Multi-Headline Generation
Figure 3 for Diverse, Controllable, and Keyphrase-Aware: A Corpus and Method for News Multi-Headline Generation
Figure 4 for Diverse, Controllable, and Keyphrase-Aware: A Corpus and Method for News Multi-Headline Generation
* 11 pages, 3 figures 
  Access Paper or Ask Questions

ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training


Feb 22, 2020
Yu Yan, Weizhen Qi, Yeyun Gong, Dayiheng Liu, Nan Duan, Jiusheng Chen, Ruofei Zhang, Ming Zhou

Figure 1 for ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training
Figure 2 for ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training
Figure 3 for ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training
Figure 4 for ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training

  Access Paper or Ask Questions

Neural Semantic Parsing in Low-Resource Settings with Back-Translation and Meta-Learning


Sep 12, 2019
Yibo Sun, Duyu Tang, Nan Duan, Yeyun Gong, Xiaocheng Feng, Bing Qin, Daxin Jiang

Figure 1 for Neural Semantic Parsing in Low-Resource Settings with Back-Translation and Meta-Learning
Figure 2 for Neural Semantic Parsing in Low-Resource Settings with Back-Translation and Meta-Learning
Figure 3 for Neural Semantic Parsing in Low-Resource Settings with Back-Translation and Meta-Learning
Figure 4 for Neural Semantic Parsing in Low-Resource Settings with Back-Translation and Meta-Learning

  Access Paper or Ask Questions