3
$\begingroup$

As many people, I've been following Andrew NG's course and I'd like now to work on a multilabel (short) text classifier with Keras/TensorFlow/Scikit learn.

I'm new to this and I know this is not exactly the kind of questions that we're supposed to ask here but where can I find a small full example (data + implementation) of a multilabel text classifier that I could run out of the box?

I've been looking all over the internet and couldn't find something like this. I need a first example to modify, change features etc to fully understand how it should work.

Improve this question
$\endgroup$

1 Answer 1

Reset to default
2
$\begingroup$

A shameless plug over here. Feel free to check Magpie, a framework for multi-label text classification that builds on word2vec and neural network technologies. It should run out-of-the-box if you have a good dataset and it builds on the technologies that you mentioned (keras, TF and scikit-learn).

I managed to run it for classifying texts with up to 10k labels with reasonable performance. Thanks to word2vec it should also be able to work for an arbitrary language.

Improve this answer
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.