Natural Language Processing: An Outline

Natural Language Procesing

This repository includes basic concepts of Natural Language Processing, textbooks and blogs of good reputation, popular papers and so on.

This is also the Natural Language Processing part of Machine Learning Resources created by a group of people including jindongwang.

Contributors are welcomed to work together and make it BETTER!

Resource of Textbooks and Lectures

Mathemetical and Statistical Foundation

• Linear Algebrap

  • 18.06 MIT(Gilbert Strang)[pdf][video]

• Matrix Analysis

• Convex Optimization

  • EE364A Stanford(Stephen Boyd)[pdf][website]
  • Introductory Lectures on Convex Programming(Yu.Nesterov)[pdf]

Machine Learning

• The Elements of Statistical Learning(ESL) - HTF

Deep Learning

• Deep Learning - Ian Goodfellow, Yoshua Bengio, Aaron Courville
• CS231n Convolutional Neural Networks for Visual Recognition - Stanford

Natural Language Processing

• Foundations of Statistical Natural Language Processing - Chris Manning
• Speech and Language Processing - Daniel Jurafsky and James H. Martin
• 统计学习方法 - 李航
• Advanced Natural Language Processing - MIT
• CS 224n Natural Language Processing with Deep Learning - Stanford
• Deep Learning for NLP at Oxford with Deepmind - Oxford
• Some Knowledge about Machine Learning

Models and Applications

• Hidden Markov Model
• Recurrent Neuron Network
  • Seq2Seq(Tensorflow Tutorial) - Machine Translation Tensorflow implement
  • LSTM
• Convolutional Neuron Network
• Attention Model
  • Overview(Chinese)
• Generative Adversial Network

Blog and Tutorials

• Tensorflow implement on RNN and undocumented features

Topics and Tasks

Category of areas is based on tracks in ACL 2018

Summerization

• Model
  • Extractive
  • Generative
• Dataset
  • CNN/DailyMail

Embedding

• Model
  • Word2Vec
• Pre-trained embedding
  • Glove
  • word2vec

Sentimental Analysis and Argument Mining

Name Entity Recognition

Tagging, Chunking, Syntax and Parsing

Machine Translation

Document Analysis

Sentence-level Semantics

Word-level Semantics

Information Extraction and Text Mining

• Tasks
  • Topic Extraction
  • Sentimental Extraction
  • Aspect Extraction

Machine Translation

• Attention is all you need - Google and University of Toronto

Text Generation

Text Classification

• Task
  • Spam Classification
• Model
• Dataset
  • Yelp Dataset
  • IMDB

Dialogue and Interactive Systems

Question Answering

• Task
• Model
• Dataset
  • CNN/DailyMail

Resources and Evaluation

Linguistic Theories and Cognitive Modeling

Multilinguality

• Task
  • Code-Switching
• Model
• Dataset
  • Linguistic Data Consortium [list] [ordered by year]
  • [List of Chinese Dataset]

Phonology, Morphology and Word Segmentation

Textual Inference

Vision, Robotics, Speech, Multimodal

Package

• Machine Learning package
  • sci-learn
  • Tensorflow
  • Caffe2
  • Pytorch
  • MXnet
• NLTK
• gensim
• jieba
• Stanford NLP