t-Plausibility: Semantic Preserving Text Sanitization

Text documents play significant roles in decision making and scientific research. Under federal regulations, documents (e.g., pathology records) containing personally identifiable information cannot be shared freely, unless properly sani-tized. Generally speaking, document sanitization consists of finding and hiding personally identifiable information. The first task has received much attention from the research community, but the main strategy for the second task has been to simply remove personal identifiers. It is not hard to see that if important information (e.g., diagnoses and per-sonal medical histories) is completely removed from pathol-ogy records, these records are no longer readable, and even worse, they no longer contain sufficient information for re-search purposes