Date of Original Version
Proceedings of the Annual Meeting of the Association of Computational Linguistics (Short Papers)
Copyright 2014 Association for Computational Linguistics
Abstract or Description
To support empirical study of online privacy policies, as well as tools for users with privacy concerns, we consider the problem of aligning sections of a thousand policy documents, based on the issues they address. We apply an unsupervised HMM; in two new (and reusable) evaluations, we find the approach more effective than clustering and topic models.
Proceedings of the Annual Meeting of the Association of Computational Linguistics (Short Papers), 605-610.