Natural Language Processing

Language Preprocessing

Section	Sub-Section	Notebook	Paper Link
String Matching	Regular Expressions	Regex
Language Tokenization	Sub-Word Tokenization	WordPiece Tokenization	Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
	Word Tokenization	Word Tokenization
	Sentence Tokenization
Language Normalization	Lemmatization/Stemming	Lemmatization/Stemming

Language Representation

Section	Sub-Section	Notebook	Paper Link
Sparse Representation	Bag-of-Words	BOW
	TF-IDF	TF-IDF
Word-Level Dense Representation	Word2Vec	Word2Vec	Efficient Estimation of Word Representations
	GloVe	GloVe	GloVe: Global Vectors for Word Representation
	FastText	FastText	Enriching Word Vectors with Subword Information
Sentence-Level Dense Representation	Doc2Vec

Language Models

Section	Sub-Section	Notebook	Paper Link
N-Gram Models		Tri-Gram LM
Neural Architectures	RNNs/LSTMs/GRUs	RNNs
	Seq2Seq	Seq2Seq (With Attention)	Sequence to Sequence Learning with Neural Networks
	Transformers	Transformer	Attention Is All You Need
Pre-trained Models	BERT	BERT	BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Language Tasks

Section	Sub-Section	Notebook	Model Architecture
Classification	Language Identification	Language Identification	Embedding and Dense Layers
	Sentiment Analysis	IMDb NB	BoW Vectorization with Naive Bayes
Sequence Labelling	Parts-of-Speech Tagging	POS Tagging	Stacked Bidirectional LSTM
	Named-Entity Recognition	NER Tagging	BERT Transformer
Machine Translation	English-Italian Translation	EN-IT MT	Seq2Seq LSTM
Question Answering	Extractive QA
	Abstractive QA	Abstractive QA on CoQA	Encoder-Decoder Transformer
Summarization	Extractive Summarization
	Abstractive Summarization
	Hybrid Summarization
Conditional Generation	Clickbait Content Spoiling	Clickbait Content Spoiling	FLAN-T5
Image Classification		Music Genre Classifier	ViT

🤗Hugging Face

Section	Notebook
Basic Pipeline	0. 🤗Hugging Face Pipeline
Fine-Tuning	1. Fine-tuning a Pretrained 🤗Hugging Face Model
Token Classification	2. Fine-tuning BERT on NER Tagging
Question Answering
Translation
Summarization