I am working on a resume parser project. Currently, I am using rule-based regex to extract features like University, Experience, Large Companies, etc.
So basically I have a set of universities' names in a CSV, and if the resume contains one of them then I am extracting that as University Name. In the same way I have a list of Large Companies in CSV and if the resume contains any of them then I flag it as Yes.
So these are rule-based logic and can never be fool-proof considering different countries have different resume formats. Is there any other way of doing it to improve the accuracy and make it a global solution?