• Seq2Seq
• Michael Collins - one of the best NLP teachers. Check out the material on the courses he is teaching.
• Natural Language Processing in Action - A guide to creating machines that understand human language.
• Lecture Note

videos

• Intro to Natural Language Processing
• Intro to Artificial Intelligence
• Deep Learning for Natural Language Processing (2015 classes)
• Natural Language Processing - course on Coursera that was only done in 2013. The videos are not available at the moment. Also Mike Collins is a great professor and his notes and lectures are very good.
• Natural Language Processing SFU - Link is broken - course by [Prof Anoop Sarkar](https://www.cs.sfu.ca/~anoop/) on Natural Language Processing. Good notes and some good lectures on youtube about HMM.
• Natural Language Processing - Stanford - 462-spring-2013)
• Deep Learning for Natural Language Processing (2016 classes)

Implementations

• Dependency based word embeddings
• Word2vec
• HLBL language model
• Real-valued vector "embeddings"
• Improving Word Representations Via Global Context And Multiple Word Prototypes

Libraries

• TwitIE: An Open-Source Information Extraction Pipeline for Microblog Text
• Twitter-text - A JavaScript implementation of Twitter's text processing library
• Pattern - A web mining module for the Python programming language. It has tools for natural language processing, machine learning, among others.
• gensim - Python library to conduct unsupervised semantic modelling from plain text
• CRFsuite - CRFsuite is an implementation of Conditional Random Fields (CRFs) for labeling sequential data.
• Mecab (Korean)
• Practical Natural Language Processing done in Ruby

videos

• Stanford CS 224D: Deep Learning for NLP class
• Richard Socher
• A Primer on Neural Network Models for Natural Language Processing

Review Articles

• Deep Learning for Web Search and Natural Language Processing
• Probabilistic topic models
• A Critical Review of Recurrent Neural Networksfor Sequence Learning
• Deep parsing in Watson
• A unified architecture for natural language processing: Deep neural networks with multitask learning
• A unified architecture for natural language processing: Deep neural networks with multitask learning

Word Vectors

• Efficient Estimation of Word Representations in Vector Space
• Mikolov
• Word2Vec tutorial
• GloVe: Global vectors for word representation
• sense2vec - on word sense disambiguation
• Infinite Dimensional Word Embeddings - new
• Skip Thought Vectors - word representation method
• Adaptive skip-gram - similar approach, with adaptive properties
• Efficient Estimation of Word Representations in Vector Space

Thought Vectors

• Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
• Distributed Representations of Sentences and Documents
• Deep Recursive Neural Networks for Compositionality in Language
• Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks
• Semi-supervised Sequence Learning
• Semi-supervised Sequence Learning

Single Exchange Dialogs

• Le - respond-to-this-email.html)
• A Neural Network Approach toContext-Sensitive Generation of Conversational Responses
• Neural Responding Machine for Short-Text Conversation
• A Neural Conversation Model
• A Neural Conversation Model
• A Neural Network Approach toContext-Sensitive Generation of Conversational Responses
• Neural Responding Machine for Short-Text Conversation

Machine Translation

• Neural Machine Translation by jointly learning to align and translate
• English to French Demo
• Sequence to Sequence Learning with Neural Networks
• nips presentation
• seq2seq tutorial
• Cross-lingual Pseudo-Projected Expectation Regularization for Weakly Supervised Learning
• Generating Chinese Named Entity Data from a Parallel Corpus
• IXA pipeline: Efficient and Ready to Use Multilingual NLP tools
• Sequence to Sequence Learning with Neural Networks
• Cross-lingual Pseudo-Projected Expectation Regularization for Weakly Supervised Learning
• Neural Machine Translation by jointly learning to align and translate

Memory and Attention Models (from [DL4NLP](https://github.com/andrewt3000/DL4NLP))

• Reasoning, Attention and Memory RAM workshop at NIPS 2015. slides included
• End-To-End Memory Networks
• Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks
• Jason Weston lecture on MemNN
• Neural Turing Machines
• Inferring Algorithmic Patterns with Stack-Augmented Recurrent Nets
• Memory Networks
• End-To-End Memory Networks
• Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks
• Evaluating prerequisite qualities for learning end to end dialog systems
• Inferring Algorithmic Patterns with Stack-Augmented Recurrent Nets

General Natural Language Processing

• Neural autocoder for paragraphs and documents - LSTM representation
• LSTM over tree structures
• Teaching Machines to Read and Comprehend - DeepMind paper
• Improving distributional similarity with lessons learned from word embeddings
• Low-Dimensional Embeddings of Logic
• based on this paper
• Markov Logic Networks for Natural Language Question Answering
• Distant Supervision for Cancer Pathway Extraction From Text
• Template-Based Information Extraction without the Templates
• Retrofitting word vectors to semantic lexicons
• Unsupervised Learning of the Morphology of a Natural Language
• Learning the Structure of Biomedical Relation Extractions
• Relation extraction with matrix factorization and universal schemas
• Computational Grounded Cognition: a new alliance between grounded cognition and computational modelling
• Efficient Estimation of Word Representations in Vector Space
• Markov Logic Networks for Natural Language Question Answering
• Natural Language Processing (Almost) from Scratch

Named Entity Recognition

• A survey of named entity recognition and classification
• Benchmarking the extraction and disambiguation of named entities on the semantic web
• Knowledge base population: Successful approaches and challenges
• SpeedRead: A fast named entity recognition Pipeline
• A survey of named entity recognition and classification
• SpeedRead: A fast named entity recognition Pipeline

Neural Network

• Statistical Language Models based on Neural Networks
• Slides from Google Talk

Supplementary Materials

• Word2Vec
• Relation Extraction with Matrix Factorization and Universal Schemas
• Presentation slides for MLN tutorial
• Presentation slides for QA applications of MLNs
• Presentation slides
• Knowledge-Based Weak Supervision for Information Extraction of Overlapping Relations

Supplementary Materials

• NLP Tutorial
• Understand & Implement Natural Language Processing
• Deep Learning, NLP, and Representations

Supplementary Materials

• nlp-reading-group
• awesome-spanish-nlp
• jjangsangy's awesome-nlp
• awesome-machine-learning