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 Fatemehsadat Mireshghallah

Fatemehsadat Mireshghallah

Privacy-Preserving Domain Adaptation of Semantic Parsers


Dec 20, 2022
Fatemehsadat Mireshghallah, Richard Shin, Yu Su, Tatsunori Hashimoto, Jason Eisner

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

Non-Parametric Temporal Adaptation for Social Media Topic Classification


Sep 13, 2022
Fatemehsadat Mireshghallah, Nikolai Vogler, Junxian He, Omar Florez, Ahmed El-Kishky, Taylor Berg-Kirkpatrick

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

Differentially Private Model Compression


Jun 03, 2022
Fatemehsadat Mireshghallah, Arturs Backurs, Huseyin A Inan, Lukas Wutschitz, Janardhan Kulkarni

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

Memorization in NLP Fine-tuning Methods


May 25, 2022
Fatemehsadat Mireshghallah, Archit Uniyal, Tianhao Wang, David Evans, Taylor Berg-Kirkpatrick

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

Mix and Match: Learning-free Controllable Text Generation using Energy Language Models


Apr 04, 2022
Fatemehsadat Mireshghallah, Kartik Goyal, Taylor Berg-Kirkpatrick

Add code

* Camera ready--ACL 2022 (minor edits) 

   Access Paper or Ask Questions

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

Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks


Mar 08, 2022
Fatemehsadat Mireshghallah, Kartik Goyal, Archit Uniyal, Taylor Berg-Kirkpatrick, Reza Shokri

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

What Does it Mean for a Language Model to Preserve Privacy?


Feb 14, 2022
Hannah Brown, Katherine Lee, Fatemehsadat Mireshghallah, Reza Shokri, Florian Tramèr

Add code

* 21 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

UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment Analysis


Oct 01, 2021
Fatemehsadat Mireshghallah, Vaishnavi Shrivastava, Milad Shokouhi, Taylor Berg-Kirkpatrick, Robert Sim, Dimitrios Dimitriadis

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

Style Pooling: Automatic Text Style Obfuscation for Improved Classification Fairness


Sep 10, 2021
Fatemehsadat Mireshghallah, Taylor Berg-Kirkpatrick

Add code

* EMNLP 2021 

   Access Paper or Ask Questions

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

Efficient Hyperparameter Optimization for Differentially Private Deep Learning


Aug 09, 2021
Aman Priyanshu, Rakshit Naidu, Fatemehsadat Mireshghallah, Mohammad Malekzadeh

Add code

* 4+1 pages, 4 figures, 1 table 

   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
>>