I am trying to test my model on the benchmark text classification dataset "Bibtex". The Bibtex dataset is available in tf-idf vectors but LSTM works on sequences. Bag of Words is a vectorized representation of text as a vector of counts. Therefore, it is no longer a sequence of words. RNN takes sequences as an input.

How can I download the raw data of Bibtex for custom feature extraction?


Your Answer

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

Browse other questions tagged or ask your own question.