The amateur’s guide to explore Natural Language Processing

How to contact me?

Please feel free to reach out to me if something is wrong in this doc or if it was helpful for you or you want to have a discussion on something.

email	nishantbaheti.it19@gmail.com
github	https://www.github.com/nishantbaheti
linkedin	https://www.linkedin.com/in/nishantbaheti/
instagram	@_cranky_panda_

• Natural Language Processing
• Corpus
  • Text Corpora /Text Corpus
    • Gutenberg Corpus
    • Brown
    • Inaugural
    • Popular Text Corpora
    • Text Corpus Structure
• Tokenization
  • sentence tokenizer
  • word tokenizer
  • Word Frequencies
  • Importing Items of book
    • find
    • word count
    • unique word count
    • transforming words
    • word coverage
    • filtering
• Stemming
• Co-occurance marix
  • Context words association matrix
  • Plotting word vectors
• Count Based Vectorizer
  • References
  • Count Vectorizer
  • Term Frequency Transformer
  • Inverse Document Frequency Transformer
  • TFIDF Vectorizer
• Word2Vec Algorithm
• Word2Vec Example (Amazon Products Reviews)
  • Loading data
  • Extract Reviews
  • Model Building
    • Continuous Bag of words model
    • Skip-grams model
  • Compare Models
• BERT Transformer
  • References
• BERT Demo
  • References
  • Loading Libraries
  • Loading Urls
  • Loading BERT Preprocessor
    • testing preprocessor
  • Loading Encoder
    • testing encoder
• BERT Example (Spam or Ham Classification)
  • Loading URLs
  • Loading data
  • Checking Class Count
  • Treating Imbalanced Class
  • Target Class 1 hot encoding
  • Loading BERT Preprocessor
  • Building Model
• Common frequency distribution methods
• Conditional Frequency
• PROJECT : Spam SMS Data Analytics
  • Loading NLTK (Natural Language Toolkit)
  • Tokenization
  • Lemmatization (convert a word into its base form)
  • Removing Stop Words
  • TFIDF Matrix
  • Stratified Shuffle Sampling
  • Models Pool

Indices and tables

• Index

• Module Index

• Search Page