Skip to content

Text Classification of documents in business categories #11656

Discussion options

You must be logged in to vote

We don't provide a pretrained model for this, no. Our recommendation is that you build your own set of training data, built to your specifications and definitions of categories, and use that to train a model.

I believe there are commercial APIs that provide services like this, but because you're stuck with their definitions you'll spend time figuring out where your definitions don't match up, and troubleshooting will be difficult.

You can also use so-called "zero shot" classification methods, where you just give a set of labels and classify items into them, but again you don't have much control compared to building your own set of examples.

Replies: 1 comment

Comment options

You must be logged in to vote
0 replies
Answer selected by adrianeboyd
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
feat / textcat Feature: Text Classifier
2 participants