NLP - Tutorial

Repository to show how NLP can tacke real problem. Including the source code, dataset, state-of-the art in NLP

Text Augmentation

Section	Sub-Section	Research Lab	Story	Paper & Code
Augmentation	Data Augmentation in NLP		Medium
Augmentation	Data Augmentation library for text		Medium
Augmentation	Data Augmentation library for Speech Recognition		Medium
Augmentation	Data Augmentation library for Audio		Medium

Text Processing

Section	Sub-Section	Description	Link
Tokenization	Subword Tokenization		Medium
Tokenization	Word Tokenization		MediumGithub
Tokenization	Sentence Tokenization		MediumGithub
Part of Speech			MediumGithub
Lemmatization			MediumGithub
Stemming			MediumGithub
Stop Words			MediumGithub
Phrase Word Recognition
Spell Checking	Lexicon-based	Peter Norvig algorithm	MediumGithub
	Lexicon-based	Symspell	MediumGithub
	Machine Translation	Statistical Machine Translation	Medium
	Machine Translation	Attention	Medium
String Matching	Fuzzywuzzy		MediumGithub

Named Entity Recognition (NER)

Section	Sub-Section	Research Lab	Story	Paper & Code
Pattern-based Recognition			Medium
Lexicon-based Recognition			Medium
Pre-trained NER	Spacy		MediumGithub
	Custom NER

Optical Character Recognition (OCR)

Section	Sub-Section	Research Lab	Story	Paper & Code
Printed Text	Google Cloud Vision API	Google	Medium	Paper
Handwriting	LSTM	Google	Medium	Paper

Text Summarization

Section	Sub-Section	Description	Link
Extractive Approach			MediumGithub
Abstractive Approach

Distance Measurement

Section	Sub-Section	Description	Link	Paper
Euclidean Distance, Cosine Similarity and Jaccard Similarity			MediumGithub
Edit Distance	Levenshtein Distance		MediumGithub
Word Moving Distance (WMD)			MediumGithub
Supervised Word Moving Distance (S-WMD)			Medium
Manhattan LSTM			Medium	Paper

Text Representation

Section	Sub-Section	Research Lab	Story	Paper & Code
Traditional Method	Bag-of-words (BoW)		MediumGithub
	Latent Semantic Analysis (LSA) and Latent Dirichlet Allocation (LDA)		MediumGithub
Character Level	Character Embedding	New York University	MediumGithub	Paper
Word Level	Negative Sampling and Hierarchical Softmax		Medium
	Word2Vec, GloVe, fastText		MediumGithub
	Contextualized Word Vectors (CoVe)	Salesforce	MediumGithub	PaperCode
	Embeddings from Language Models (ELMo)	AI2	MediumGithub	PaperCode
	Generative Pre-Training (GPT)	OpenAI	Medium	PaperCode
	Contextual String Embeddings	Zalando Research	Medium	PaperCode
	Self-Governing Neural Networks (SGNN)	Google	Medium	Paper
	Multi-Task Deep Neural Networks (MT-DNN)	Microsoft	Medium	Paper
	Generative Pre-Training-2 (GPT-2)	OpenAI	Medium	PaperCode
	Universal Language Model Fine-tuning (ULMFiT)	OpenAI	Medium	PaperCode
Sentence Level	Skip-thoughts		MediumGithub	PaperCode
	InferSent		MediumGithub	PaperCode
	Quick-Thoughts	Google	Medium	PaperCode
	General Purpose Sentence (GenSen)		Medium	PaperCode
	Bidirectional Encoder Representations from Transformers (BERT)	Google	Medium	PaperCode
	BERT in Science Domain		Medium	SciBERT PaperBioBERT Paper
	BERT in Clinical Domain		Medium	Clincical BERT Embeddings PaperClinicalBert Paper
Document Level	lda2vec		Medium	Paper
	doc2vec	Google	MediumGithub	Paper

Model Interpretation

Section	Sub-Section	Description	Link
ELI5, LIME and Skater			MediumGithub
SHapley Additive exPlanations (SHAP)			MediumGithub
Anchors			MediumGithub

Myth

Section	Sub-Section	Description	Link
Using Deep Learning can resolve all problem?			MediumKaggle

Source Code

Section	Sub-Section	Description	Link
Spellcheck			Github
InferSent			Github