1. Learn
    2. /
  2. Courses
    3. /
  3. Deep Learning for Text with PyTorch

Exercise

Shakespearean language preprocessing pipeline

Over at PyBooks, the team wants to transform a vast library of Shakespearean text data for further analysis. The most efficient way to do this is with a text processing pipeline, starting with the preprocessing steps.

The following have been loaded for you: torch, nltk, stopwords, PorterStemmer, get_tokenizer.

The Shakespearean text data is saved as shakespeare and the sentences have already been extracted.

Instructions 1/3

undefined XP
    1
    2
    3
  • Create a list of unique English stopwords, saving to them to stop_words.