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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Rebuild and Ensemble: Exploring Defense Against Text Adversaries


Mar 27, 2022
Linyang Li , Demin Song , Jiehang Zeng , Ruotian Ma , Xipeng Qiu

* work in progress 

   Access Paper or Ask Questions

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

MarkBERT: Marking Word Boundaries Improves Chinese BERT


Mar 12, 2022
Linyang Li , Yong Dai , Duyu Tang , Zhangyin Feng , Cong Zhou , Xipeng Qiu , Zenglin Xu , Shuming Shi

* Work in progress 

   Access Paper or Ask Questions

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

"Is Whole Word Masking Always Better for Chinese BERT?": Probing on Chinese Grammatical Error Correction


Mar 02, 2022
Yong Dai , Linyang Li , Cong Zhou , Zhangyin Feng , Enbo Zhao , Xipeng Qiu , Piji Li , Duyu Tang

* Short paper in Findings of ACL 2022 

   Access Paper or Ask Questions

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

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


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

* preprint 

   Access Paper or Ask Questions

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

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

* Accepted by EMNLP2021 main conference 

   Access Paper or Ask Questions

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

Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitution


Aug 29, 2021
Zongyi Li , Jianhan Xu , Jiehang Zeng , Linyang Li , Xiaoqing Zheng , Qi Zhang , Kai-Wei Chang , Cho-Jui Hsieh

* Accepted by EMNLP2021 main conference 

   Access Paper or Ask Questions

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

SENT: Sentence-level Distant Relation Extraction via Negative Training


Jun 22, 2021
Ruotian Ma , Tao Gui , Linyang Li , Qi Zhang , Yaqian Zhou , Xuanjing Huang

* Accepted by ACL 2021 

   Access Paper or Ask Questions

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

Certified Robustness to Text Adversarial Attacks by Randomized [MASK]


May 08, 2021
Jiehang Zeng , Xiaoqing Zheng , Jianhan Xu , Linyang Li , Liping Yuan , Xuanjing Huang

* Accepted by Findings of ACL 2021, Long Paper 

   Access Paper or Ask Questions

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

Generating Adversarial Examples in Chinese Texts Using Sentence-Pieces


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

* pre-print 

   Access Paper or Ask Questions

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

TextAT: Adversarial Training for Natural Language Understanding with Token-Level Perturbation


Apr 30, 2020
Linyang Li , Xipeng Qiu

* 8 pages, 3 figures 

   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
>>