Protecting Sensitive Topics in Text Documents with PROTEXTOR

Abstract

This is a demonstration of a system for protecting sensitive topics present in text documents. Our system works in a privacy framework where the topic is characterized as a multiclass classification problem in a generative setting. We show how our system helps a user redact a document in a business setting to obscure what company the text pertains to, and show some experimental results on redacting the topic for a standard text classification data set.

Cite

Text

Cumby. "Protecting Sensitive Topics in Text Documents with PROTEXTOR." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2009. doi:10.1007/978-3-642-04174-7_47

Markdown

[Cumby. "Protecting Sensitive Topics in Text Documents with PROTEXTOR." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2009.](https://mlanthology.org/ecmlpkdd/2009/cumby2009ecmlpkdd-protecting/) doi:10.1007/978-3-642-04174-7_47

BibTeX

@inproceedings{cumby2009ecmlpkdd-protecting,
  title     = {{Protecting Sensitive Topics in Text Documents with PROTEXTOR}},
  author    = {Cumby, Chad M.},
  booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
  year      = {2009},
  pages     = {714-717},
  doi       = {10.1007/978-3-642-04174-7_47},
  url       = {https://mlanthology.org/ecmlpkdd/2009/cumby2009ecmlpkdd-protecting/}
}