0
$\begingroup$

Does anyone know a content-based vectorization scheme can be used in Natural Language Processing to represent documents in vector space??

$\endgroup$
0
$\begingroup$

Definitely doc2vec is a way. You can also calculate doc vector from word vectors (embeddings) manually - averaging them, potentially weighted average with tf-idf of words as weights.

$\endgroup$

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.