Planning a classifier to recognize specific documents based on text. Categories are mutually exclusive and include: job application resumes, paychecks, quarterly financial reports etc, and data is text extracted from doc, pdf, xls etc.
At the feature engineering stage, with questions in mind:
- One Multiclass classifier or a number of One vs. Rest (one per category)?
- Word embedding (Word2Vec/GloVe) - one embedding for all categories or a separate embedding for each category?
My tendency is towards a number of one vs. rest classifiers (to allow for dynamic use of just some of the categories), and one embedding for all categories (to save prediction time).
Project architecture: initially basic LogReg, but will soon develop to CNN / CNN+RNN.
- Training: a few hundreds per category
- Prediction: millions of files
Please feel free to share any insights or references, thank you