0
$\begingroup$

I'm looking for proper method of document embeddings. I know that doc2vec will give me the vector representations for given corpus, but how do I embed new documents? I need to train neural network that will classify text, but I have no idea how new documents should be embedded properly.

$\endgroup$
0
$\begingroup$

Not necessarily. Documents embeddings are constructions from (sub)word embeddings. Nowadays, you should always start from a pre-trained model. Please check tensorflow Hub or Hugging Face. Even without retraining, as long as your text is not too specific, the pre-trained encoder should capture enough relations.

$\endgroup$
1
  • $\begingroup$ Thank you, that is saving me! $\endgroup$ – Mikołaj Wróblewski Nov 24 '20 at 7:10

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

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