How to approach deep learning CV/Resume parser using Convolutions?

Question

I'm currently looking to invest some time on how to make a resume parser using deep learning.

I need some initial ideas (or) approaches on how to put together things at first, where to start. If you have any good approaches on handling resume parsing for multiple type resume structures please let me know.

Also to start here's my approach I was thinking, do let me know if you think this works!

1) First I will take a 100 resume as a image(i.e., jpg) file.
2) I will create bounding box around projects/education area and create my training data.
3) After training I'll try to predict it on test data. 

Is this an ideal approach? Are there any good approaches you can suggest which works based on any paper?

Much appreciated. Thanks.

Answer 1

Typically, resumes are not images. Almost all resumes are Microsoft Word or pdf. Given those document formats, a deep learning parser should be sequence-based (e.g., Recurrent Neural Network (RNN) or Long Short Term Memory (LSTM)).

To apply Deep Learning, you'll need many thousands of examples with each section labeled. There is HR-XML (Human Resources - Extensible Markup Language) which are the industry standards for labels of resume sections.