Named Entity Recognition (NER) is the information extraction task of identifying and classifying mentions of locations, quantities, monetary values, organizations, people, and other named entities within a text.
To identify sensitive NER for document redaction which includes Social Security Numbers (Aadhaar Number), Bank account numbers and related sensitive information, Name, Place, Organization. (Vary from organization to organization for data anonymity objective)
- Transfer learning on Spacy
- Using RNN and BiLSTM
- Using Pytorch and BERT
[1] Neural Architectures for Named Entity Recognition - published on arxiv.org