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 Xipeng Qiu

Xipeng Qiu

Towards More Effective and Economic Sparsely-Activated Model


Oct 14, 2021
Hao Jiang, Ke Zhan, Jianwei Qu, Yongkang Wu, Zhaoye Fei, Xinyu Zhang, Lei Chen, Zhicheng Dou, Xipeng Qiu, Zikai Guo, Ruofei Lai, Jiawen Wu, Enrui Hu, Yinxia Zhang, Yantao Jia, Fan Yu, Zhao Cao

Figure 1 for Towards More Effective and Economic Sparsely-Activated Model
Figure 2 for Towards More Effective and Economic Sparsely-Activated Model
Figure 3 for Towards More Effective and Economic Sparsely-Activated Model
Figure 4 for Towards More Effective and Economic Sparsely-Activated Model

  Access Paper or Ask Questions

Towards Efficient NLP: A Standard Evaluation and A Strong Baseline


Oct 13, 2021
Xiangyang Liu, Tianxiang Sun, Junliang He, Lingling Wu, Xinyu Zhang, Hao Jiang, Zhao Cao, Xuanjing Huang, Xipeng Qiu

Figure 1 for Towards Efficient NLP: A Standard Evaluation and A Strong Baseline
Figure 2 for Towards Efficient NLP: A Standard Evaluation and A Strong Baseline
Figure 3 for Towards Efficient NLP: A Standard Evaluation and A Strong Baseline
Figure 4 for Towards Efficient NLP: A Standard Evaluation and A Strong Baseline
* Preprint. Work in progress. 10 pages 
  Access Paper or Ask Questions

KNN-BERT: Fine-Tuning Pre-Trained Models with KNN Classifier


Oct 06, 2021
Linyang Li, Demin Song, Ruotian Ma, Xipeng Qiu, Xuanjing Huang

Figure 1 for KNN-BERT: Fine-Tuning Pre-Trained Models with KNN Classifier
Figure 2 for KNN-BERT: Fine-Tuning Pre-Trained Models with KNN Classifier
Figure 3 for KNN-BERT: Fine-Tuning Pre-Trained Models with KNN Classifier
Figure 4 for KNN-BERT: Fine-Tuning Pre-Trained Models with KNN Classifier
* preprint 
  Access Paper or Ask Questions

Paradigm Shift in Natural Language Processing


Sep 26, 2021
Tianxiang Sun, Xiangyang Liu, Xipeng Qiu, Xuanjing Huang

Figure 1 for Paradigm Shift in Natural Language Processing
Figure 2 for Paradigm Shift in Natural Language Processing
* https://txsun1997.github.io/nlp-paradigm-shift 
  Access Paper or Ask Questions

RetrievalSum: A Retrieval Enhanced Framework for Abstractive Summarization


Sep 16, 2021
Chenxin An, Ming Zhong, Zhichao Geng, Jianqiang Yang, Xipeng Qiu

Figure 1 for RetrievalSum: A Retrieval Enhanced Framework for Abstractive Summarization
Figure 2 for RetrievalSum: A Retrieval Enhanced Framework for Abstractive Summarization
Figure 3 for RetrievalSum: A Retrieval Enhanced Framework for Abstractive Summarization
Figure 4 for RetrievalSum: A Retrieval Enhanced Framework for Abstractive Summarization

  Access Paper or Ask Questions

CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation


Sep 14, 2021
Yunfan Shao, Zhichao Geng, Yitao Liu, Junqi Dai, Fei Yang, Li Zhe, Hujun Bao, Xipeng Qiu

Figure 1 for CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation
Figure 2 for CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation
Figure 3 for CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation
Figure 4 for CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation
* Preprint 
  Access Paper or Ask Questions

Learning to Teach with Student Feedback


Sep 10, 2021
Yitao Liu, Tianxiang Sun, Xipeng Qiu, Xuanjing Huang

Figure 1 for Learning to Teach with Student Feedback
Figure 2 for Learning to Teach with Student Feedback
Figure 3 for Learning to Teach with Student Feedback
Figure 4 for Learning to Teach with Student Feedback

  Access Paper or Ask Questions

Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning


Aug 31, 2021
Linyang Li, Demin Song, Xiaonan Li, Jiehang Zeng, Ruotian Ma, Xipeng Qiu

Figure 1 for Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning
Figure 2 for Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning
Figure 3 for Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning
Figure 4 for Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning
* Accepted by EMNLP2021 main conference 
  Access Paper or Ask Questions

A Survey of Transformers


Jun 15, 2021
Tianyang Lin, Yuxin Wang, Xiangyang Liu, Xipeng Qiu

Figure 1 for A Survey of Transformers
Figure 2 for A Survey of Transformers
Figure 3 for A Survey of Transformers
Figure 4 for A Survey of Transformers

  Access Paper or Ask Questions

Pre-Trained Models: Past, Present and Future


Jun 15, 2021
Xu Han, Zhengyan Zhang, Ning Ding, Yuxian Gu, Xiao Liu, Yuqi Huo, Jiezhong Qiu, Liang Zhang, Wentao Han, Minlie Huang, Qin Jin, Yanyan Lan, Yang Liu, Zhiyuan Liu, Zhiwu Lu, Xipeng Qiu, Ruihua Song, Jie Tang, Ji-Rong Wen, Jinhui Yuan, Wayne Xin Zhao, Jun Zhu

Figure 1 for Pre-Trained Models: Past, Present and Future
Figure 2 for Pre-Trained Models: Past, Present and Future
Figure 3 for Pre-Trained Models: Past, Present and Future
Figure 4 for Pre-Trained Models: Past, Present and Future

  Access Paper or Ask Questions

Accelerating BERT Inference for Sequence Labeling via Early-Exit


Jun 14, 2021
Xiaonan Li, Yunfan Shao, Tianxiang Sun, Hang Yan, Xipeng Qiu, Xuanjing Huang

Figure 1 for Accelerating BERT Inference for Sequence Labeling via Early-Exit
Figure 2 for Accelerating BERT Inference for Sequence Labeling via Early-Exit
Figure 3 for Accelerating BERT Inference for Sequence Labeling via Early-Exit
Figure 4 for Accelerating BERT Inference for Sequence Labeling via Early-Exit
* Accepted to the ACL 2021 
  Access Paper or Ask Questions

A Unified Generative Framework for Aspect-Based Sentiment Analysis


Jun 08, 2021
Hang Yan, Junqi Dai, Tuo ji, Xipeng Qiu, Zheng Zhang

Figure 1 for A Unified Generative Framework for Aspect-Based Sentiment Analysis
Figure 2 for A Unified Generative Framework for Aspect-Based Sentiment Analysis
Figure 3 for A Unified Generative Framework for Aspect-Based Sentiment Analysis
Figure 4 for A Unified Generative Framework for Aspect-Based Sentiment Analysis
* Accepted by ACL 2021 (long paper) 
  Access Paper or Ask Questions

A Unified Generative Framework for Various NER Subtasks


Jun 02, 2021
Hang Yan, Tao Gui, Junqi Dai, Qipeng Guo, Zheng Zhang, Xipeng Qiu

Figure 1 for A Unified Generative Framework for Various NER Subtasks
Figure 2 for A Unified Generative Framework for Various NER Subtasks
Figure 3 for A Unified Generative Framework for Various NER Subtasks
Figure 4 for A Unified Generative Framework for Various NER Subtasks
* Accepted in the main conference of ACL-IJCNLP 2021 
  Access Paper or Ask Questions

Early Exiting with Ensemble Internal Classifiers


May 28, 2021
Tianxiang Sun, Yunhua Zhou, Xiangyang Liu, Xinyu Zhang, Hao Jiang, Zhao Cao, Xuanjing Huang, Xipeng Qiu

Figure 1 for Early Exiting with Ensemble Internal Classifiers
Figure 2 for Early Exiting with Ensemble Internal Classifiers
Figure 3 for Early Exiting with Ensemble Internal Classifiers
Figure 4 for Early Exiting with Ensemble Internal Classifiers

  Access Paper or Ask Questions

Keyphrase Generation with Fine-Grained Evaluation-Guided Reinforcement Learning


Apr 18, 2021
Yichao Luo, Yige Xu, Jiacheng Ye, Xipeng Qiu, Qi Zhang

Figure 1 for Keyphrase Generation with Fine-Grained Evaluation-Guided Reinforcement Learning
Figure 2 for Keyphrase Generation with Fine-Grained Evaluation-Guided Reinforcement Learning
Figure 3 for Keyphrase Generation with Fine-Grained Evaluation-Guided Reinforcement Learning
Figure 4 for Keyphrase Generation with Fine-Grained Evaluation-Guided Reinforcement Learning

  Access Paper or Ask Questions

QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization


Apr 13, 2021
Ming Zhong, Da Yin, Tao Yu, Ahmad Zaidi, Mutethia Mutuma, Rahul Jha, Ahmed Hassan Awadallah, Asli Celikyilmaz, Yang Liu, Xipeng Qiu, Dragomir Radev

Figure 1 for QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization
Figure 2 for QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization
Figure 3 for QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization
Figure 4 for QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization
* Accepted by NAACL 2021 
  Access Paper or Ask Questions

Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTa


Apr 11, 2021
Junqi Dai, Hang Yan, Tianxiang Sun, Pengfei Liu, Xipeng Qiu

Figure 1 for Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTa
Figure 2 for Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTa
Figure 3 for Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTa
Figure 4 for Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTa
* Accepted by NAACL 2021 
  Access Paper or Ask Questions

Enhancing Scientific Papers Summarization with Citation Graph


Apr 07, 2021
Chenxin An, Ming Zhong, Yiran Chen, Danqing Wang, Xipeng Qiu, Xuanjing Huang

Figure 1 for Enhancing Scientific Papers Summarization with Citation Graph
Figure 2 for Enhancing Scientific Papers Summarization with Citation Graph
Figure 3 for Enhancing Scientific Papers Summarization with Citation Graph
Figure 4 for Enhancing Scientific Papers Summarization with Citation Graph
* accepted by AAAI 2021 
  Access Paper or Ask Questions

TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing


Apr 06, 2021
Tao Gui, Xiao Wang, Qi Zhang, Qin Liu, Yicheng Zou, Xin Zhou, Rui Zheng, Chong Zhang, Qinzhuo Wu, Jiacheng Ye, Zexiong Pang, Yongxin Zhang, Zhengyan Li, Ruotian Ma, Zichu Fei, Ruijian Cai, Jun Zhao, Xinwu Hu, Zhiheng Yan, Yiding Tan, Yuan Hu, Qiyuan Bian, Zhihua Liu, Bolin Zhu, Shan Qin, Xiaoyu Xing, Jinlan Fu, Yue Zhang, Minlong Peng, Xiaoqing Zheng, Yaqian Zhou, Zhongyu Wei, Xipeng Qiu, Xuanjing Huang

Figure 1 for TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing
Figure 2 for TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing
Figure 3 for TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing
Figure 4 for TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing

  Access Paper or Ask Questions

Fork or Fail: Cycle-Consistent Training with Many-to-One Mappings


Jan 25, 2021
Qipeng Guo, Zhijing Jin, Ziyu Wang, Xipeng Qiu, Weinan Zhang, Jun Zhu, Zheng Zhang, David Wipf

Figure 1 for Fork or Fail: Cycle-Consistent Training with Many-to-One Mappings
Figure 2 for Fork or Fail: Cycle-Consistent Training with Many-to-One Mappings
Figure 3 for Fork or Fail: Cycle-Consistent Training with Many-to-One Mappings
Figure 4 for Fork or Fail: Cycle-Consistent Training with Many-to-One Mappings
* A condensed version is accepted to AISTATS 2021 
  Access Paper or Ask Questions

Generating Adversarial Examples in Chinese Texts Using Sentence-Pieces


Dec 29, 2020
Linyang Li, Yunfan Shao, Demin Song, Xipeng Qiu, Xuanjing Huang

Figure 1 for Generating Adversarial Examples in Chinese Texts Using Sentence-Pieces
Figure 2 for Generating Adversarial Examples in Chinese Texts Using Sentence-Pieces
Figure 3 for Generating Adversarial Examples in Chinese Texts Using Sentence-Pieces
Figure 4 for Generating Adversarial Examples in Chinese Texts Using Sentence-Pieces
* pre-print 
  Access Paper or Ask Questions

Finding Sparse Structure for Domain Specific Neural Machine Translation


Dec 19, 2020
Jianze Liang, Chengqi Zhao, Mingxuan Wang, Xipeng Qiu, Lei Li

Figure 1 for Finding Sparse Structure for Domain Specific Neural Machine Translation
Figure 2 for Finding Sparse Structure for Domain Specific Neural Machine Translation
Figure 3 for Finding Sparse Structure for Domain Specific Neural Machine Translation
Figure 4 for Finding Sparse Structure for Domain Specific Neural Machine Translation
* Accepted to AAAI 2021 
  Access Paper or Ask Questions

Text Information Aggregation with Centrality Attention


Nov 16, 2020
Jingjing Gong, Hang Yan, Yining Zheng, Xipeng Qiu, Xuanjing Huang

Figure 1 for Text Information Aggregation with Centrality Attention
Figure 2 for Text Information Aggregation with Centrality Attention
Figure 3 for Text Information Aggregation with Centrality Attention
Figure 4 for Text Information Aggregation with Centrality Attention

  Access Paper or Ask Questions

Pre-trained Model for Chinese Word Segmentation with Meta Learning


Oct 23, 2020
Zhen Ke, Liang Shi, Erli Meng, Bin Wang, Xipeng Qiu

Figure 1 for Pre-trained Model for Chinese Word Segmentation with Meta Learning
Figure 2 for Pre-trained Model for Chinese Word Segmentation with Meta Learning
Figure 3 for Pre-trained Model for Chinese Word Segmentation with Meta Learning
Figure 4 for Pre-trained Model for Chinese Word Segmentation with Meta Learning

  Access Paper or Ask Questions

CDEvalSumm: An Empirical Study of Cross-Dataset Evaluation for Neural Summarization Systems


Oct 22, 2020
Yiran Chen, Pengfei Liu, Ming Zhong, Zi-Yi Dou, Danqing Wang, Xipeng Qiu, Xuanjing Huang

Figure 1 for CDEvalSumm: An Empirical Study of Cross-Dataset Evaluation for Neural Summarization Systems
Figure 2 for CDEvalSumm: An Empirical Study of Cross-Dataset Evaluation for Neural Summarization Systems
Figure 3 for CDEvalSumm: An Empirical Study of Cross-Dataset Evaluation for Neural Summarization Systems
Figure 4 for CDEvalSumm: An Empirical Study of Cross-Dataset Evaluation for Neural Summarization Systems
* 13 pages, Findings of EMNLP2020 
  Access Paper or Ask Questions