I have to build a Entity extractor in C# which would do following things:
- read a file(.doc, docx).
- scan the doc for following entities:
- Name(forename, surname).
- Location( includes building, apartment, street names, state, town cities etc.)
- Zip code.
- Vehicle Identification number
- Social security.
- Phone num.
- Basically all personal identification entities.
Once these entities are found, remove it, and save the rest of the data.
I have tried Stanford.NER but it only recognizes person, organization and place(only city names). I want street name building name also.