0
$\begingroup$

I have questions of users and I want to classify them automatically without manually labelling them. What deep learning method would be good for text classification just from text (so unsupervised).

Does those algorithms have to rely on word embedding?

$\endgroup$

1 Answer 1

2
$\begingroup$

Since you are specifically asking about deep learning techniques, nothing strikes me out of the bat other than Autoencoders.

You can try using autoencoders for clustering, basically, you need to stick with clustering. Since you don't have the labels.

To answer your question whether they rely on embeddings that are out there, it depends on your data, if you have a domain-specific data or you have the data in a weird language then you should go for creating your own embeddings.

I found this article really helpful, though it has been done on images, you can try it on text, using Conv1D. Also yes, you can try out word embeddings like word2vec or fasttext. There is this good article where they use gensim for doing attaching the embeddings, in case your data is just plain ordinary English.

there's also this article from keras blog where the author uses pre-trained GloVe embeddings.

Hope this helps.

$\endgroup$
1
  • $\begingroup$ Thanks! FastText sounds very intersting. But I still want to get basic knowledge about the types of algorithms to do text classification.I think the deep learning algos for unsupervised classification are based on word vectors, right? Do you know how fasttext performs text classifications? Can you elaborate more how to use autoencoders for text classification? So, the basis of all text classifications are the word vectors? I think you missed to link the article you mentioned in your post. Thanks $\endgroup$
    – Tido
    Jul 5, 2018 at 17:08

Your Answer

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

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