Data Sense is a piece of software to find, classify and relative sensitive data using Natural Language Processing and Machine Learning techniques.
- Find all sensitive data inside documents (Word, Excel, PowerPoint, Text based) and databases (Oracle, SQLServer, MySQL, etc) in Portuguese Language
- Classify and and represent sensitive data relationships between unstructured data
- Named-Entity recognition (NER), Dictionary Based Search, Automatic Relation Extraction and other Natural Language Processing techniques are used
- Allow human-feedback to improve NLP models using a simple interface
- Developed with GDPR in mind
For now, the language that is supported is Portuguese (Portugal). It is expected to support English.