Approaching (Almost) Any Natural Language Processing Problem

Contents:

• The obvious intro to NLP
• Bag of words
• TFIDF
• Hashing
• Cleaning text data (stemming, lemmatization)
• Tokenization of text data (from space-based to BPE and SentencePiece)
• Word embeddings
• Revisit LSTM, GRU, 1-D CNN, 2-D CNN
• Decomposition-SVD
• SVM, Logistic regression based models
• Topic modelling
• POS tagging, NER, entity detection/extraction using traditional approaches
• Attention is all you need
• Transformers
• BERT, RoBERTa, XLM, and other transformer based models
• Distillation of transformer based models
• Entity extraction using transformer based models
• Text summarization
• Various assignments and projects

Missing something? Have a wish? Create an issue and let me know :)