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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Cross-Linguistic Syntactic Difference in Multilingual BERT: How Good is It and How Does It Affect Transfer?


Dec 21, 2022
Ningyu Xu, Tao Gui, Ruotian Ma, Qi Zhang, Jingting Ye, Menghan Zhang, Xuanjing Huang

Add code

* EMNLP 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Rethinking Label Smoothing on Multi-hop Question Answering


Dec 19, 2022
Zhangyue Yin, Yuxin Wang, Yiguang Wu, Hang Yan, Xiannian Hu, Xinyu Zhang, Zhao Cao, Xuanjing Huang, Xipeng Qiu

Add code

* 8 pages, 2 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models


Nov 30, 2022
Zhengfu He, Tianxiang Sun, Kuanning Wang, Xuanjing Huang, Xipeng Qiu

Add code

* Work in progress. Code publicly available at https://github.com/Hzfinfdu/Diffusion-BERT 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Efficient Adversarial Training with Robust Early-Bird Tickets


Nov 15, 2022
Zhiheng Xi, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang

Add code

* EMNLP 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Robust Lottery Tickets for Pre-trained Language Models


Nov 06, 2022
Rui Zheng, Rong Bao, Yuhao Zhou, Di Liang, Sirui Wang, Wei Wu, Tao Gui, Qi Zhang, Xuanjing Huang

Add code

* ACL 2022. https://aclanthology.org/2022.acl-long.157 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Late Prompt Tuning: A Late Prompt Could Be Better Than Many Prompts


Oct 20, 2022
Xiangyang Liu, Tianxiang Sun, Xuanjing Huang, Xipeng Qiu

Add code

* Accepted by Findings of EMNLP 2022. Camera-ready version 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation


Oct 14, 2022
Tianxiang Sun, Junliang He, Xipeng Qiu, Xuanjing Huang

Add code

* Accepted to EMNLP 2022 (main conference). Data and code are available at https://github.com/txsun1997/Metric-Fairness 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Multi-Task Pre-Training of Modular Prompt for Few-Shot Learning


Oct 14, 2022
Tianxiang Sun, Zhengfu He, Qin Zhu, Xipeng Qiu, Xuanjing Huang

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Kernel-Whitening: Overcome Dataset Bias with Isotropic Sentence Embedding


Oct 14, 2022
Songyang Gao, Shihan Dou, Qi Zhang, Xuanjing Huang

Add code

* Accepted by EMNLP2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Learning "O" Helps for Learning More: Handling the Concealed Entity Problem for Class-incremental NER


Oct 10, 2022
Ruotian Ma, Xuanting Chen, Lin Zhang, Tao Gui, Qi Zhang, Xuanjing Huang

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
4
5
6
7
>>