search

clutchkingasiimov / ABSA-

0 stars 1 forks source link

Preprocessing #3

Open celineyixinz opened 2 years ago

celineyixinz commented 2 years ago
  1. lower case
  2. remove stopwords
  3. remove special characters (#, %, @ ...)
  4. remove punctuation
  5. basic spell correction
  6. lemmatization
clutchkingasiimov commented 2 years ago

Steps implemented in text_processor.py:

  1. Lower case
  2. Stopword removal
  3. Special Character removal
  4. Punctuations (Will have to test more cases)
  5. Lemmatization

Spell correction left.