/MLP-89

NLP concepts and algorithms

Primary LanguageJupyter NotebookApache License 2.0Apache-2.0

MLP-89

NLP concepts and algorithms

  • Regex
  • NLP pipeline
  • Tokenization
  • Stemming & Lemmentation
  • Parts of Speech POS tagging
  • Name Enitity Recognition (NER)
  • Text representation
    • Label
    • One-hot encoding
    • Bag of Words (BOW)
    • Bag of ngrams
    • TF-IDF
    • Word-embeddings
  • Stop words
  • Word vectors - WORD2Vec (text classfication) - Genshim (text classfication) - fastText (text classfication)
  • fastText
  • chatbots