/text_it_is

here we are going to learn and apply DL on texts

Primary LanguagePython

text_it_is

here we are going to learn and apply DL on texts

  1. data: download data from https://www.kaggle.com/utathya/imdb-review-dataset and put it in the 'data' directory.

  2. run: python preprocess_data.py to get the reviews. Add preprocessing steps and clean these reviews, tokenize them, making them ready to train the word embeddings.