NLP

• Tutorials
• Neural Models
• Sequence to Sequence Learning
• Translation
• Summarization
• Question Answering
• Alignment
• Resources

Tutorials

Neural Models

Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models

• paper: http://arxiv.org/abs/1411.2539
• results: http://www.cs.toronto.edu/~rkiros/lstm_scnlm.html
• demo: http://deeplearning.cs.toronto.edu/i2t
• github: https://github.com/ryankiros/visual-semantic-embedding

Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks

• arXiv: http://arxiv.org/abs/1503.00075
• github: https://github.com/stanfordnlp/treelstm

Visualizing and Understanding Neural Models in NLP

• arXiv: http://arxiv.org/abs/1506.01066

Character-Aware Neural Language Models

• paper: http://arxiv.org/abs/1508.06615
• github: https://github.com/yoonkim/lstm-char-cnn

Skip-Thought Vectors

• paper: http://arxiv.org/abs/1506.06726
• github: https://github.com/ryankiros/skip-thoughts

A Primer on Neural Network Models for Natural Language Processing

• arXiv: http://arxiv.org/abs/1510.00726

Character-aware Neural Language Models

• arxiv: http://arxiv.org/abs/1508.06615

Sequence to Sequence Learning

Generating Text with Deep Reinforcement Learning(NIPS 2015)

• arXiv: http://arxiv.org/abs/1510.09202

MUSIO: A Deep Learning based Chatbot Getting Smarter

• homepage: http://ec2-204-236-149-143.us-west-1.compute.amazonaws.com:9000/
• github(Torch7): https://github.com/deepcoord/seq2seq

Translation

Learning phrase representations using rnn encoder-decoder for statistical machine translation

• arXiv: http://arxiv.org/abs/1406.1078

Neural Machine Translation by Jointly Learning to Align and Translate

• arXiv: http://arxiv.org/abs/1409.0473
• github: https://github.com/lisa-groundhog/GroundHog

Multi-Source Neural Translation

• intro: “report up to +4.8 Bleu increases on top of a very strong attention-based neural translation model.”
• arxiv: Multi-Source Neural Translation
• github(Zoph_RNN): https://github.com/isi-nlp/Zoph_RNN
• video: http://research.microsoft.com/apps/video/default.aspx?id=260336

Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanism

• arxiv: http://arxiv.org/abs/1601.01073

Summarization

A Neural Attention Model for Abstractive Sentence Summarization(EMNLP 2015. Facebook AI Research)

• arXiv: http://arxiv.org/abs/1509.00685
• github: https://github.com/facebook/NAMAS

Question Answering

Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks(Facebook AI Research)

• arXiv: http://arxiv.org/abs/1502.05698v1
• github: https://github.com/facebook/bAbI-tasks

VQA: Visual Question Answering

• arxiv: http://arxiv.org/abs/1505.00468
• homepage: http://visualqa.org/

Ask Your Neurons: A Neural-based Approach to Answering Questions about Images

• arxiv: http://arxiv.org/abs/1505.01121

Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question Answering

• arxiv: http://arxiv.org/abs/1505.05612

Teaching Machines to Read and Comprehend(Google DeepMind)

• arXiv: http://arxiv.org/abs/1506.03340
• github: https://github.com/deepmind/rc-data
• github(Theano/Blocks): https://github.com/thomasmesnard/DeepMind-Teaching-Machines-to-Read-and-Comprehend
• github(Tensorflow): https://github.com/carpedm20/attentive-reader-tensorflow

Image Question Answering using Convolutional Neural Network with Dynamic Parameter Prediction

• arxiv: http://arxiv.org/abs/1511.05756
• github: https://github.com/HyeonwooNoh/DPPnet
• project page: http://cvlab.postech.ac.kr/research/dppnet/

Neural Generative Question Answering

• arXiv: http://arxiv.org/abs/1512.01337

Simple Baseline for Visual Question Answering (Facebook AI Research. Bag-of-word)

• arXiv: http://arxiv.org/abs/1512.02167
• github: https://github.com/metalbubble/VQAbaseline
• demo: http://visualqa.csail.mit.edu/

MovieQA: Understanding Stories in Movies through Question-Answering

• arxiv: http://arxiv.org/abs/1512.02902
• homepage: http://movieqa.cs.toronto.edu/home/

Deeper LSTM+ normalized CNN for Visual Question Answering

• intro: “This current code can get 58.16 on Open-Ended and 63.09 on Multiple-Choice on test-standard split”
• github: https://github.com/VT-vision-lab/VQA_LSTM_CNN

A Neural Network for Factoid Question Answering over Paragraphs

• project page: http://cs.umd.edu/~miyyer/qblearn/
• paper: https://cs.umd.edu/~miyyer/pubs/2014_qb_rnn.pdf
• code+data: https://cs.umd.edu/~miyyer/qblearn/qanta.tar.gz

Generating Natural Questions About an Image

• arxiv: http://arxiv.org/abs/1603.06059

Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus

• arxiv: http://arxiv.org/abs/1603.06807

Alignment

Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books

• arXiv: http://arxiv.org/abs/1506.06724
• github: https://github.com/ryankiros/neural-storyteller

Resources

So, you need to understand language data? Open-source NLP software can help!

• blog: http://entopix.com/so-you-need-to-understand-language-data-open-source-nlp-software-can-help.html