Natural Language Processing - Resources

Basic Definitions

• Named Entity Recognition
• Part of Speech
• Syntactic Parser
• • Constituency Parser
• • Dependency Parser
• Semantic Parser
• • Semantic Role Labeling
• Lemmatization and Stemming
• Coreference Resolution
• Stop words
• Tokenization

Data Cleaning and Preprocessing

• Ultimate guide to deal with Text Data (using Python) – for Data Scientists & Engineers http://bit.ly/2SAeBTt
• NLP: Text Data Cleaning and Preprocessing http://bit.ly/2SCeZR4+
• Cleaning and pre-processing textual data http://bit.ly/2SxwPVr
• Text Data Preprocessing: A Walkthrough in Python http://bit.ly/2SAgyyX

Topic Modelling

• Topic Modelling in Python with NLTK and Gensim http://bit.ly/2SAyda0
• Topic Modeling and Latent Dirichlet Allocation (LDA) in Python http://bit.ly/2SDmPdB
• Combing LDA and Word Embeddings for topic modeling http://bit.ly/2SBnjRs
• Topic modelling with PLSA http://bit.ly/2Sy1xOh
• NLP For Topic Modeling & Summarization Of Legal Documents http://bit.ly/2Sx3bzI
• NLP: Extracting the main topics from your dataset using LDA in minutes http://bit.ly/2SyziPu

Vectorizers

• Hacking Scikit-Learn’s Vectorizers http://bit.ly/2SA9RNm
• Mapping Word Embeddings with Word2vec http://bit.ly/2SCPhfF

Word2Vec

• Introducción a Word2vec (skip gram model) http://bit.ly/2SzAdzm
• Light on Math Machine Learning: Intuitive Guide to Understanding Word2vec http://bit.ly/2SCgi2q
• A Beginner's Quide to Word2Vec and Neural Word Embeddings http://bit.ly/2SuLVem
• Word2Vec and FastText Word Embedding with Gensim http://bit.ly/2SyNmZp
• Multi-Class Text Classification with Doc2Vec & Logistic Regression http://bit.ly/2SuNvwO
• Duplicate question detection using Word2Vec, XGBoost and Autoencoders http://bit.ly/2SuQLs2

Bag-of-Words

• An Introduction to Bag-of-Words in NLP http://bit.ly/2Sy36f6
• Text Processing 1 — Old Fashioned Methods (Bag of Words and

xIDF) http://bit.ly/2SF0f4e

• Beyond bag of words: Using PyTextRank to find Phrases and Summarize text http://bit.ly/2SxNEj0
• Beyond Word Embeddings Part 2- Word Vectors and NLP Modeling from BoW to BERT http://bit.ly/2SAkujx
• Finding Similar Quora Questions with BOW, TFIDF and Xgboost http://bit.ly/2SyRBnN

Twitter Sentiment Analysis Project

• Another Twitter sentiment analysis with Python — Part 1 http://bit.ly/2zhVHI6
• Another Twitter sentiment analysis with Python - Part 2 http://bit.ly/2zeaPGm
• Another Twitter sentiment analysis with Python — Part 3 (Zipf’s Law, data visualisation) http://bit.ly/2zlu4O7
• Another Twitter sentiment analysis with Python — Part 4 (Count vectorizer, confusion matrix) http://bit.ly/2zdoywY
• Another Twitter sentiment analysis with Python — Part 5 (Tfidf vectorizer, model comparison, lexical approach) http://bit.ly/2zhglbc
• Another Twitter sentiment analysis with Python — Part 6 (Doc2Vec) http://bit.ly/2zdoD3K
• Another Twitter sentiment analysis with Python — Part 7 (Phrase modeling + Doc2Vec) http://bit.ly/2zhYcKu
• Another Twitter sentiment analysis with Python — Part 8 (Dimensionality reduction: Chi2, PCA) http://bit.ly/2zhXOM2
• Another Twitter sentiment analysis with Python — Part 9 (Neural Networks with Tfidf vectors using Keras) http://bit.ly/2zhYyRk
• Another Twitter sentiment analysis with Python — Part 10 (Neural Network with Doc2Vec/Word2Vec/GloVe) http://bit.ly/2zhgueK
• Another Twitter sentiment analysis with Python — Part 11 (CNN + Word2Vec) http://bit.ly/2zhZOnw
• Yet Another Twitter Sentiment Analysis Part 1 — tackling class imbalance http://bit.ly/2zi8nP9

Deep Learning

• Deep Learning for NLP (video) http://bit.ly/2St1L9v slides http://bit.ly/2SwxPJH
• Deep Learning for NLP: An Overview of Recent Trends http://bit.ly/2SF4iNY
• A Light Introduction to Transfer Learning for NLP http://bit.ly/2SxzFd7
• Deep Learning, NLP, and Representations http://bit.ly/2QQSZAS
• Modern Deep Learning Techniques Applied to Natural Language Processing http://bit.ly/2zh6Xoc
• Deep Learning for NLP: PyTorch vs Tensorflow – Elvis Saravia – PyCon Taiwan 2018 (video) http://bit.ly/2zhdkYq
• Introducing state of the art text classification with universal language models http://bit.ly/2zltFLY
• Autoencoders and Word Embeddings http://bit.ly/2ziiwvj

Transfer Learning

• NLP's ImageNet moment has arrived http://bit.ly/2zoLhpZ
• How NLP Cracked Transfer Learning https://thegradient.pub/nlp-imagenet/

Gaussian Mixture Models

• Gaussian mixture models http://bit.ly/2QQTbjA

University Courses

• Deep Learning for NLP Stanford University [video] http://bit.ly/2zjzuJP [syllabus] https://stanford.io/2SE22GN
• Deep Learning for NLP at Oxford with DeepMind [video] http://bit.ly/2zlsBaz [resources] http://bit.ly/2SH54Kb

MOOCs

Foundations

• Natural Language Processing Intel AI Academy https://intel.ly/2TiRnRY
• Natural Language Processing With Python and NLTK [video] http://bit.ly/2StmQ3D
• Natural Language Processing [video] http://bit.ly/2SAdFOQ

Recurrent Neural Networks - Deep Learning Specialization

• Sequence Models Andrew Ng Course [video] http://bit.ly/2zfIEa5

arXiv Publications

• Notes on Deep Learning for NLP http://bit.ly/2zmyhkG
• Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling https://arxiv.org/pdf/1703.04826.pdf
• Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering https://arxiv.org/pdf/1606.09375.pdf
• Deep Convolutional Networks on Graph-Structured Data http://bit.ly/2zkQ0Jc