vitojph / kschool-nlp-19

This repo contains the NLP materials for the 19th edition of the Master on Data Science held at KSchool

Natural Language Processing (Master on Data Science, KSchool)

This repo contains the NLP materials for the 19th edition of the Data Science Master held at KSchool Madrid.

Topics

• Introduction to NLP

• Unix Command Line Tools to Process Text

• NLTK: Access to Corpora and Linguistic Resources

• NLTK: Part-of-Speech Tagging

• NLTK: Parsing

• TextBlob: NLP

• spaCy: NLP

• flair: NLP

• Space Vector Models

• Word Embeddings

MOOCs, Courses and Other Materials

• Dragomir Radev's Introduction to Natural Language Processing is no longer on Coursera. But here there are some materials.

• Some years ago, Manning & Jurafsky organized a course on NLP at Coursera. There are some slides and videos.

• Stanford NLP (materiales)

• Natural Language Processing, Johns Hopkins University

• Programming for Linguists (and fellow travelers) (materiales)

• Oxford Deep NLP

Books and Further Readings

• Dan Jurafsky and James H. Martin. Speech and Language Processing

• Chris Manning and Hinrich Schütze, Foundations of Statistical Natural Language Processing

• Emily Bender. Linguistic Fundamentals for Natural Language Processing: 100 Essentials from Morphology and Syntax

• Jacob Einstein. Natural Language Processing

• Steven Bird, Ewan Klein, and Edward Loper. Natural Language Processing with Python

• Jacob Perkins. Python 3 Text Processing with NLTK 3 Cookbook

• The Stupidity of Computers

• NLP (almost) from scratch

• The Two Paths from NLP to AI

• Natural Language Processing Key Terms, Explained

• 4 Approaches to NLP

Resources

• NLP Progress

• Papers with Code: NLP

• the Beyond Word Embeddings series, especially its Part 2

• The Big Bad NLP Database

• Awesome NLP

• Awesome Spanish NLP

• Awesome Data Science

• WordNet

• Multilingual Central Repository (Spanish WordNet)

• SentiWordNet

• BERT pre-trained vectors for Tensorflow

• PyTorch pre-trained vectors: BERT & OpenAI's GPT Models

• Pre-trained word vectors by fastText

• TurorialBank: Learning NLP Made Easier

Other NLProc APIs

• Cloud Natural Language API

• IBM's Watson API

• MeaningCloud API

• MonkeyLearn

• Mashape's Market on Natural Language

Readings on Neural Networks and Deep Learning

• Christopher Olah's blog on Neural Networks , specially the post on Deep Learning, NLP, and Representations

• Hacker's guide to Neural Networks

• The Unreasonable Effectiveness of Recurrent Neural Networks (code repo)

• CS224d: Deep Learning for Natural Language Processing

• Understanding Natural Language with Deep Neural Networks Using Torch

• Deep Learning for NLP (without magic)