1. Reference: https://www.deeplearning.ai/resources/natural-language-processing/
2. Sub Fields
2.1. Natural Language Generation (NLG)
2.2. Natural Language Understanding (NLU)
3. Use Cases
3.1. Sentiment Analysis
3.2. Toxicity Analysis
3.3. Machine Translation
3.4. Named Entity Recognition
3.5. Spam Detection
3.6. Grammatical Error Correction
3.7. Topic Modeling
3.8. Text Generation
3.8.1. Auto Complete
3.8.2. ChatBots
3.8.2.1. Database Query
3.8.2.2. Conversation Generation
3.9. Information Retrieval
3.10. Summarization
3.10.1. Extractive Summarization
3.10.2. Abstractive Summarization
3.11. Question Answering
3.11.1. Multiple Choice
3.11.2. Open Domain
4. How?
4.1. Data PreProcessing
4.1.1. Stemming & lemmatization
4.1.1.1. NLTK
4.1.1.2. spaCy
4.1.2. Sentence Segmentation
4.1.3. Stop Word Removal
4.1.4. Tokenization
4.2. Feature Exctraction
4.2.1. Bag-Of-Words
4.2.2. TF-IDF
4.2.2.1. Term Frequency
4.2.2.2. Inverse-Document Frequency
4.2.3. Word2Vec
4.2.4. GLoVE
4.3. Modeling
4.3.1. Logistic Regression, Naive Bayes, Decision Trees, Gradient Boosted Trees
4.3.2. Deep Neural Networks
4.3.3. Language Models
5. Techniques
5.1. Traditional Machine Learning
5.1.1. Latent Dirichlet Allocation (LDA)
5.1.2. Naive Bayes
5.1.3. Decision Trees
5.1.4. Logisitic Regression
5.1.5. Hidden Markov Models
5.2. Deep Learning
5.2.1. Convolutional Neural Network (CNN)
5.2.2. Recurrent Neural Network (RNN)
5.2.2.1. Architectures
5.2.2.1.1. Long Short Term Memory (LTSM)
5.2.2.1.2. Gated Recurrent Unit (GRU)
5.2.3. AutoEncoders
5.2.4. Encoder-Decoder Sequence to Sequence
5.2.5. Transformers
5.2.5.1. Parallelizable