2021

Differentially Private n-gram Extraction

Kim, Kunho, Gopi, Sivakanth, Kulkarni, Janardhan et al.

Understand

We revisit the problem of $n$-gram extraction in the differential privacy setting.

  • In this problem, given a corpus of private text data, the goal is to release as many $n$-grams as possible while preserving user level privacy.
  • Extracting $n$-grams is a fundamental subroutine in many NLP applications such as sentence completion, response generation for emails etc.
  • The problem also arises in other applications such as sequence mining, and is a generalization of recently studied differentially private set union (DPSU).

Built on

  • Calibrating noise to sensitivity in private data analysis

    Cynthia Dwork, Frank McSherry, Kobbi Nissim, and Adam Smith · 2006

    Earlier work this paper cites.

  • Differentially private sequential data publication via variable-length n-grams

    Rui Chen, Gergely Acs, and Claude Castelluccia · 2012

    Earlier work this paper cites.

  • The algorithmic foundations of differential privacy

    Cynthia Dwork and Aaron Roth · 2014

    Earlier work this paper cites.

  • Convolutional neural network architectures for matching natural language sentences

    Baotian Hu, Zhengdong Lu, Hang Li, and Qingcai Chen · 2014

    Earlier work this paper cites.

  • Dpt: differentially private trajectory synthesis using hierarchical reference systems

    Xi He, Graham Cormode, Ashwin Machanavajjhala, Cecilia M Procopiuc, and Divesh Srivastava · 2015

    Earlier work this paper cites.

Similar

  • Differentially private frequent sequence mining via sampling-based candidate pruning

    Shengzhi Xu, Sen Su, Xiang Cheng, Zhengyi Li, and Li Xiong · 2015

    Cited alongside, same era.

  • Smart reply: Automated response suggestion for email

    Anjuli Kannan, Karol Kurach, Sujith Ravi, Tobias Kaufmann, Andrew Tomkins, Balint Miklos, Greg Corrado, Laszlo Lukacs, Marina Ganea, Peter Young, et al · 2016

    Cited alongside, same era.

  • Differentially private frequent sequence mining

    Shengzhi Xu, Xiang Cheng, Sen Su, Ke Xiao, and Li Xiong · 2016

    Cited alongside, same era.

  • Improving the gaussian mechanism for differential privacy: Analytical calibration and optimal denoising

    Borja Balle and Yu-Xiang Wang · 2018

    Cited alongside, same era.

  • Privtrie: Effective frequent term discovery under local differential privacy

    Ning Wang, Xiaokui Xiao, Yin Yang, Ta Duy Hoang, Hyejin Shin, Junbum Shin, and Ge Yu · 2018

    Cited alongside, same era.

  • The secret sharer: Evaluating and testing unintended memorization in neural networks

    Nicholas Carlini, Chang Liu, Úlfar Erlingsson, Jernej Kos, and Dawn Song

    Cited in the paper.

Then

  • Gmail smart compose: Real-time assisted writing

    Mia Xu Chen, Benjamin N. Lee, Gagan Bansal, Yuan Cao, Shuyuan Zhang, Justin Lu, Jackie Tsay, Yinan Wang, Andrew M. Dai, Zhifeng Chen, and et al · 2019

    Later among the works it cites.

  • Diversifying reply suggestions using a matching-conditional variational autoencoder

    Budhaditya Deb, Peter Bailey, and Milad Shokouhi · 2019

    Later among the works it cites.

  • Gaussian differential privacy

    Original

    Jinshuo Dong, Aaron Roth, and Weijie J Su · 2019

    Later among the works it cites.

  • Differentially private set union

    Sivakanth Gopi, Pankaj Gulhane, Janardhan Kulkarni, Judy Hanwen Shen, Milad Shokouhi, and Sergey Yekhanin · 2020

    Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…