Skip to content

Old NLP

NLP methods before transformers and basic building blocks of nlp

Concepts:

  • 0.Preprocessing
  • 1.Encodings
  • 2.Tokenizers
  • 3.One-gram/Bi-gram/N-gram
  • 4.BOW/Word2vec/tf-idf
  • 5.Embeddings
  • 6.Distances/similarity
  • 7.Text Decoding
  • 8.POS/NER

Usecases:

  • 1.Document similarity
  • 2.Document clustering/Topic Modelling
  • 3.NER

Will add more...

<!--https://www.analyticsvidhya.com/blog/2020/01/3-important-nlp-libraries-indian-languages-python/ https://indicnlp.ai4bharat.org/pages/indicnlp-resources/ https://www.newscatcherapi.com/blog/ultimate-guide-to-text-similarity-with-python https://copyprogramming.com/howto/python-find-similar-words-from-a-list-python