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 Qun Liu

Qun Liu

UniDS: A Unified Dialogue System for Chit-Chat and Task-oriented Dialogues


Oct 15, 2021
Xinyan Zhao, Bin He, Yasheng Wang, Yitong Li, Fei Mi, Yajiao Liu, Xin Jiang, Qun Liu, Huanhuan Chen

Figure 1 for UniDS: A Unified Dialogue System for Chit-Chat and Task-oriented Dialogues
Figure 2 for UniDS: A Unified Dialogue System for Chit-Chat and Task-oriented Dialogues
Figure 3 for UniDS: A Unified Dialogue System for Chit-Chat and Task-oriented Dialogues
Figure 4 for UniDS: A Unified Dialogue System for Chit-Chat and Task-oriented Dialogues

  Access Paper or Ask Questions

bert2BERT: Towards Reusable Pretrained Language Models


Oct 14, 2021
Cheng Chen, Yichun Yin, Lifeng Shang, Xin Jiang, Yujia Qin, Fengyu Wang, Zhi Wang, Xiao Chen, Zhiyuan Liu, Qun Liu

Figure 1 for bert2BERT: Towards Reusable Pretrained Language Models
Figure 2 for bert2BERT: Towards Reusable Pretrained Language Models
Figure 3 for bert2BERT: Towards Reusable Pretrained Language Models
Figure 4 for bert2BERT: Towards Reusable Pretrained Language Models

  Access Paper or Ask Questions

Multi-Semantic Image Recognition Model and Evaluating Index for explaining the deep learning models


Sep 28, 2021
Qianmengke Zhao, Ye Wang, Qun Liu

Figure 1 for Multi-Semantic Image Recognition Model and Evaluating Index for explaining the deep learning models
Figure 2 for Multi-Semantic Image Recognition Model and Evaluating Index for explaining the deep learning models
Figure 3 for Multi-Semantic Image Recognition Model and Evaluating Index for explaining the deep learning models
Figure 4 for Multi-Semantic Image Recognition Model and Evaluating Index for explaining the deep learning models

  Access Paper or Ask Questions

DyLex: Incorporating Dynamic Lexicons into BERT for Sequence Labeling


Sep 22, 2021
Baojun Wang, Zhao Zhang, Kun Xu, Guang-Yuan Hao, Yuyang Zhang, Lifeng Shang, Linlin Li, Xiao Chen, Xin Jiang, Qun Liu

Figure 1 for DyLex: Incorporating Dynamic Lexicons into BERT for Sequence Labeling
Figure 2 for DyLex: Incorporating Dynamic Lexicons into BERT for Sequence Labeling
Figure 3 for DyLex: Incorporating Dynamic Lexicons into BERT for Sequence Labeling
Figure 4 for DyLex: Incorporating Dynamic Lexicons into BERT for Sequence Labeling
* EMNLP 2021 Long Paper 
  Access Paper or Ask Questions

Improving Unsupervised Question Answering via Summarization-Informed Question Generation


Sep 16, 2021
Chenyang Lyu, Lifeng Shang, Yvette Graham, Jennifer Foster, Xin Jiang, Qun Liu

Figure 1 for Improving Unsupervised Question Answering via Summarization-Informed Question Generation
Figure 2 for Improving Unsupervised Question Answering via Summarization-Informed Question Generation
Figure 3 for Improving Unsupervised Question Answering via Summarization-Informed Question Generation
Figure 4 for Improving Unsupervised Question Answering via Summarization-Informed Question Generation
* EMNLP 2021 Long Paper 
  Access Paper or Ask Questions

CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systems


Sep 14, 2021
Fei Mi, Yitong Li, Yasheng Wang, Xin Jiang, Qun Liu

Figure 1 for CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systems
Figure 2 for CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systems
Figure 3 for CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systems
Figure 4 for CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systems

  Access Paper or Ask Questions

UniMS: A Unified Framework for Multimodal Summarization with Knowledge Distillation


Sep 13, 2021
Zhengkun Zhang, Xiaojun Meng, Yasheng Wang, Xin Jiang, Qun Liu, Zhenglu Yang

Figure 1 for UniMS: A Unified Framework for Multimodal Summarization with Knowledge Distillation
Figure 2 for UniMS: A Unified Framework for Multimodal Summarization with Knowledge Distillation
Figure 3 for UniMS: A Unified Framework for Multimodal Summarization with Knowledge Distillation
Figure 4 for UniMS: A Unified Framework for Multimodal Summarization with Knowledge Distillation

  Access Paper or Ask Questions

CINS: Comprehensive Instruction for Few-shot Learning in Task-orientedDialog Systems


Sep 10, 2021
Fei Mi, Yitong Li, Yasheng Wang, Xin Jiang, Qun Liu

Figure 1 for CINS: Comprehensive Instruction for Few-shot Learning in Task-orientedDialog Systems
Figure 2 for CINS: Comprehensive Instruction for Few-shot Learning in Task-orientedDialog Systems
Figure 3 for CINS: Comprehensive Instruction for Few-shot Learning in Task-orientedDialog Systems
Figure 4 for CINS: Comprehensive Instruction for Few-shot Learning in Task-orientedDialog Systems

  Access Paper or Ask Questions

KELM: Knowledge Enhanced Pre-Trained Language Representations with Message Passing on Hierarchical Relational Graphs


Sep 09, 2021
Yinquan Lu, Haonan Lu, Guirong Fu, Qun Liu

Figure 1 for KELM: Knowledge Enhanced Pre-Trained Language Representations with Message Passing on Hierarchical Relational Graphs
Figure 2 for KELM: Knowledge Enhanced Pre-Trained Language Representations with Message Passing on Hierarchical Relational Graphs
Figure 3 for KELM: Knowledge Enhanced Pre-Trained Language Representations with Message Passing on Hierarchical Relational Graphs
Figure 4 for KELM: Knowledge Enhanced Pre-Trained Language Representations with Message Passing on Hierarchical Relational Graphs

  Access Paper or Ask Questions

NumGPT: Improving Numeracy Ability of Generative Pre-trained Models


Sep 07, 2021
Zhihua Jin, Xin Jiang, Xingbo Wang, Qun Liu, Yong Wang, Xiaozhe Ren, Huamin Qu

Figure 1 for NumGPT: Improving Numeracy Ability of Generative Pre-trained Models
Figure 2 for NumGPT: Improving Numeracy Ability of Generative Pre-trained Models
Figure 3 for NumGPT: Improving Numeracy Ability of Generative Pre-trained Models
Figure 4 for NumGPT: Improving Numeracy Ability of Generative Pre-trained Models
* 8 pages, 3 figures 
  Access Paper or Ask Questions

Generate & Rank: A Multi-task Framework for Math Word Problems


Sep 07, 2021
Jianhao Shen, Yichun Yin, Lin Li, Lifeng Shang, Xin Jiang, Ming Zhang, Qun Liu

Figure 1 for Generate & Rank: A Multi-task Framework for Math Word Problems
Figure 2 for Generate & Rank: A Multi-task Framework for Math Word Problems
Figure 3 for Generate & Rank: A Multi-task Framework for Math Word Problems
Figure 4 for Generate & Rank: A Multi-task Framework for Math Word Problems
* Findings of EMNLP2021 
  Access Paper or Ask Questions

Integrating Regular Expressions with Neural Networks via DFA


Sep 07, 2021
Shaobo Li, Qun Liu, Xin Jiang, Yichun Yin, Chengjie Sun, Bingquan Liu, Zhenzhou Ji, Lifeng Shang

Figure 1 for Integrating Regular Expressions with Neural Networks via DFA
Figure 2 for Integrating Regular Expressions with Neural Networks via DFA
Figure 3 for Integrating Regular Expressions with Neural Networks via DFA
Figure 4 for Integrating Regular Expressions with Neural Networks via DFA

  Access Paper or Ask Questions

Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Training


Sep 06, 2021
Minghao Wu, Yitong Li, Meng Zhang, Liangyou Li, Gholamreza Haffari, Qun Liu

Figure 1 for Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Training
Figure 2 for Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Training
Figure 3 for Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Training
Figure 4 for Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Training
* 15 pages, 4 figures, to appear at EMNLP 2021 main conference 
  Access Paper or Ask Questions

AutoTinyBERT: Automatic Hyper-parameter Optimization for Efficient Pre-trained Language Models


Jul 29, 2021
Yichun Yin, Cheng Chen, Lifeng Shang, Xin Jiang, Xiao Chen, Qun Liu

Figure 1 for AutoTinyBERT: Automatic Hyper-parameter Optimization for Efficient Pre-trained Language Models
Figure 2 for AutoTinyBERT: Automatic Hyper-parameter Optimization for Efficient Pre-trained Language Models
Figure 3 for AutoTinyBERT: Automatic Hyper-parameter Optimization for Efficient Pre-trained Language Models
Figure 4 for AutoTinyBERT: Automatic Hyper-parameter Optimization for Efficient Pre-trained Language Models
* ACL 2021. The code and models are released at https://github.com/huawei-noah/Pretrained-Language-Model/tree/master/AutoTinyBERT 
  Access Paper or Ask Questions

Multilingual Speech Translation with Unified Transformer: Huawei Noah's Ark Lab at IWSLT 2021


Jun 22, 2021
Xingshan Zeng, Liangyou Li, Qun Liu

Figure 1 for Multilingual Speech Translation with Unified Transformer: Huawei Noah's Ark Lab at IWSLT 2021
Figure 2 for Multilingual Speech Translation with Unified Transformer: Huawei Noah's Ark Lab at IWSLT 2021
Figure 3 for Multilingual Speech Translation with Unified Transformer: Huawei Noah's Ark Lab at IWSLT 2021
Figure 4 for Multilingual Speech Translation with Unified Transformer: Huawei Noah's Ark Lab at IWSLT 2021
* IWSLT 2021 
  Access Paper or Ask Questions

A Mutual Information Maximization Approach for the Spurious Solution Problem in Weakly Supervised Question Answering


Jun 14, 2021
Zhihong Shao, Lifeng Shang, Qun Liu, Minlie Huang

Figure 1 for A Mutual Information Maximization Approach for the Spurious Solution Problem in Weakly Supervised Question Answering
Figure 2 for A Mutual Information Maximization Approach for the Spurious Solution Problem in Weakly Supervised Question Answering
Figure 3 for A Mutual Information Maximization Approach for the Spurious Solution Problem in Weakly Supervised Question Answering
Figure 4 for A Mutual Information Maximization Approach for the Spurious Solution Problem in Weakly Supervised Question Answering
* ACL2021 main conference 
  Access Paper or Ask Questions

Learning Multilingual Representation for Natural Language Understanding with Enhanced Cross-Lingual Supervision


Jun 09, 2021
Yinpeng Guo, Liangyou Li, Xin Jiang, Qun Liu

Figure 1 for Learning Multilingual Representation for Natural Language Understanding with Enhanced Cross-Lingual Supervision
Figure 2 for Learning Multilingual Representation for Natural Language Understanding with Enhanced Cross-Lingual Supervision
Figure 3 for Learning Multilingual Representation for Natural Language Understanding with Enhanced Cross-Lingual Supervision
Figure 4 for Learning Multilingual Representation for Natural Language Understanding with Enhanced Cross-Lingual Supervision

  Access Paper or Ask Questions

RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformer


Jun 09, 2021
Xingshan Zeng, Liangyou Li, Qun Liu

Figure 1 for RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformer
Figure 2 for RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformer
Figure 3 for RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformer
Figure 4 for RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformer
* Accepted by ACL2021 Findings 
  Access Paper or Ask Questions

HyKnow: End-to-End Task-Oriented Dialog Modeling with Hybrid Knowledge Management


Jun 02, 2021
Silin Gao, Ryuichi Takanobu, Wei Peng, Qun Liu, Minlie Huang

Figure 1 for HyKnow: End-to-End Task-Oriented Dialog Modeling with Hybrid Knowledge Management
Figure 2 for HyKnow: End-to-End Task-Oriented Dialog Modeling with Hybrid Knowledge Management
Figure 3 for HyKnow: End-to-End Task-Oriented Dialog Modeling with Hybrid Knowledge Management
Figure 4 for HyKnow: End-to-End Task-Oriented Dialog Modeling with Hybrid Knowledge Management
* Findings of ACL-IJCNLP 2021, long paper 
  Access Paper or Ask Questions

Improved OOD Generalization via Adversarial Training and Pre-training


May 24, 2021
Mingyang Yi, Lu Hou, Jiacheng Sun, Lifeng Shang, Xin Jiang, Qun Liu, Zhi-Ming Ma

Figure 1 for Improved OOD Generalization via Adversarial Training and Pre-training
Figure 2 for Improved OOD Generalization via Adversarial Training and Pre-training
Figure 3 for Improved OOD Generalization via Adversarial Training and Pre-training
Figure 4 for Improved OOD Generalization via Adversarial Training and Pre-training
* published in ICML2021 
  Access Paper or Ask Questions

PanGu-$Ξ±$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation


Apr 26, 2021
Wei Zeng, Xiaozhe Ren, Teng Su, Hui Wang, Yi Liao, Zhiwei Wang, Xin Jiang, ZhenZhang Yang, Kaisheng Wang, Xiaoda Zhang, Chen Li, Ziyan Gong, Yifan Yao, Xinjing Huang, Jun Wang, Jianfeng Yu, Qi Guo, Yue Yu, Yan Zhang, Jin Wang, Hengtao Tao, Dasen Yan, Zexuan Yi, Fang Peng, Fangqing Jiang, Han Zhang, Lingfeng Deng, Yehong Zhang, Zhe Lin, Chao Zhang, Shaojie Zhang, Mingyue Guo, Shanzhi Gu, Gaojun Fan, Yaowei Wang, Xuefeng Jin, Qun Liu, Yonghong Tian

Figure 1 for PanGu-$Ξ±$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation
Figure 2 for PanGu-$Ξ±$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation
Figure 3 for PanGu-$Ξ±$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation
Figure 4 for PanGu-$Ξ±$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation
* The technique report for PanGu-$\alpha$ 
  Access Paper or Ask Questions

Extract then Distill: Efficient and Effective Task-Agnostic BERT Distillation


Apr 24, 2021
Cheng Chen, Yichun Yin, Lifeng Shang, Zhi Wang, Xin Jiang, Xiao Chen, Qun Liu

Figure 1 for Extract then Distill: Efficient and Effective Task-Agnostic BERT Distillation
Figure 2 for Extract then Distill: Efficient and Effective Task-Agnostic BERT Distillation
Figure 3 for Extract then Distill: Efficient and Effective Task-Agnostic BERT Distillation
Figure 4 for Extract then Distill: Efficient and Effective Task-Agnostic BERT Distillation

  Access Paper or Ask Questions

Improving Neural Machine Translation with Compact Word Embedding Tables


Apr 18, 2021
Krtin Kumar, Mehdi Rezagholizadeh, Yiu Sing Lau, Qun Liu

Figure 1 for Improving Neural Machine Translation with Compact Word Embedding Tables
Figure 2 for Improving Neural Machine Translation with Compact Word Embedding Tables
Figure 3 for Improving Neural Machine Translation with Compact Word Embedding Tables
Figure 4 for Improving Neural Machine Translation with Compact Word Embedding Tables

  Access Paper or Ask Questions

An Approach to Improve Robustness of NLP Systems against ASR Errors


Mar 25, 2021
Tong Cui, Jinghui Xiao, Liangyou Li, Xin Jiang, Qun Liu

Figure 1 for An Approach to Improve Robustness of NLP Systems against ASR Errors
Figure 2 for An Approach to Improve Robustness of NLP Systems against ASR Errors
Figure 3 for An Approach to Improve Robustness of NLP Systems against ASR Errors
Figure 4 for An Approach to Improve Robustness of NLP Systems against ASR Errors
* 9 pages, 3 figures 
  Access Paper or Ask Questions

Dependency Graph-to-String Statistical Machine Translation


Mar 20, 2021
Liangyou Li, Andy Way, Qun Liu

Figure 1 for Dependency Graph-to-String Statistical Machine Translation
Figure 2 for Dependency Graph-to-String Statistical Machine Translation
Figure 3 for Dependency Graph-to-String Statistical Machine Translation
Figure 4 for Dependency Graph-to-String Statistical Machine Translation

  Access Paper or Ask Questions

Reweighting Augmented Samples by Minimizing the Maximal Expected Loss


Mar 16, 2021
Mingyang Yi, Lu Hou, Lifeng Shang, Xin Jiang, Qun Liu, Zhi-Ming Ma

Figure 1 for Reweighting Augmented Samples by Minimizing the Maximal Expected Loss
Figure 2 for Reweighting Augmented Samples by Minimizing the Maximal Expected Loss
Figure 3 for Reweighting Augmented Samples by Minimizing the Maximal Expected Loss
Figure 4 for Reweighting Augmented Samples by Minimizing the Maximal Expected Loss
* published in ICLR2021 
 * 14 pages 
  Access Paper or Ask Questions

LightMBERT: A Simple Yet Effective Method for Multilingual BERT Distillation


Mar 11, 2021
Xiaoqi Jiao, Yichun Yin, Lifeng Shang, Xin Jiang, Xiao Chen, Linlin Li, Fang Wang, Qun Liu

Figure 1 for LightMBERT: A Simple Yet Effective Method for Multilingual BERT Distillation
Figure 2 for LightMBERT: A Simple Yet Effective Method for Multilingual BERT Distillation
Figure 3 for LightMBERT: A Simple Yet Effective Method for Multilingual BERT Distillation
Figure 4 for LightMBERT: A Simple Yet Effective Method for Multilingual BERT Distillation

  Access Paper or Ask Questions

Training Multilingual Pre-trained Language Model with Byte-level Subwords


Jan 23, 2021
Junqiu Wei, Qun Liu, Yinpeng Guo, Xin Jiang

Figure 1 for Training Multilingual Pre-trained Language Model with Byte-level Subwords
Figure 2 for Training Multilingual Pre-trained Language Model with Byte-level Subwords
Figure 3 for Training Multilingual Pre-trained Language Model with Byte-level Subwords
Figure 4 for Training Multilingual Pre-trained Language Model with Byte-level Subwords

  Access Paper or Ask Questions