NLP using DRL

Various of NLP tasks using Deep Reinforcement Learning

1. Deep Reinforcement Learning for Mention-Ranking Coreference Models
2. Deep Reinforcement Learning for Dialogue Generation
3. A Deep Reinforced Model for Abstractive Summarization
4. Learning through Dialogue Interactions by Asking Questions
5. Deal or No Deal? End-to-End Learning for Negotiation Dialogues
6. Teaching Machines to Describe Images via Natural Language Feedback
7. Task-Oriented Query Reformulation with Reinforcement Learning
8. DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning
9. Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access

Dialogue Policy Optimization

1. End-to-End Task-Completion Neural Dialogue Systems
2. Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning
3. PERSONALIZING DIALOGUE AGENTS:I HAVE A DOG, DO YOU HAVE PETS TOO?

Representation Learning for NLP

1. GloVe: Global Vectors for Word Representation
2. Skip-Thought Vectors
3. Supervised Learning of Universal Sentence Representations from Natural Language Inference Data
4. Mapping Unseen Words to Task-Trained Embedding Spaces
5. A Structured Self-attentive Sentence Embedding
6. Bag of Tricks for Efficient Text Classification
7. Enriching Word Vectors with Subword Information
8. Neural Embeddings of Graphs in Hyperbolic Space
9. Poincaré Embeddings for Learning Hierarchical Representations
10. Learned in Translation: Contextualized Word Vectors
11. Exploiting Similarities among Languages for Machine Translation
12. Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints
13. Mixing Dirichlet Topic Models and Word Embeddings to Make lda2vec
14. AN EFFICIENT FRAMEWORK FOR LEARNING SENTENCE REPRESENTATIONS

NLP

1. Regularizing and Optimizing LSTM Language Models
2. Layer Normalization
3. POINTER SENTINEL MIXTURE MODELS
4. Training RNNs as Fast as CNNs
5. Beam Search Strategies for Neural Machine Translation
6. Position-aware Attention and Supervised Data Improve Slot Filling
7. Pointing the Unknown Words
8. Dilated Recurrent Neural Networks
9. FRATERNAL DROPOUT
10. BREAKING THE SOFTMAX BOTTLENECK:A HIGH-RANK RNN LANGUAGE MODEL
11. VARIATIONAL BI-LSTMS
12. END-TO-END JOINT LEARNING OF NATURAL LANGUAGE UNDERSTANDING AND DIALOGUE MANAGER
13. SVD-Softmax: Fast Softmax Approximation on Large Vocabulary Neural Networks
14. Natural Language Does Not Emerge ‘Naturally’ in Multi-Agent Dialog
15. Learning to Generate Reviews and Discovering Sentiment
16. MinimalRNN: Toward More Interpretable and Trainable Recurrent Neural Networks
17. Sequence-to-Sequence Learning as Beam-Search Optimization

Machine Reading Comprehension

1. Bidirectional Attention Flow for Machine Comprehension
2. DCN+: Mixed Objective and Deep Residual Coattention for Question Answering
3. FUSIONNET: FUSING VIA FULLY-AWARE ATTENTION WITH APPLICATION TO MACHINE COMPREHENSION
4. Fast and Accurate Reading Comprehension by Combining Self-Attention and Convolution

Speech Recognition

1. Listen, Attend and Spell
2. Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
3. State-of-the-art Speech Recognition With Sequence-to-Sequence Models

Neural Machine Translation

1. Attention Is All You Need
2. Unsupervised Machine Translation Using Monolingual Corpora Only
3. Incorporating Copying Mechanism in Sequence-to-Sequence Learning
4. Training Tips for the Transformer Model

Reinforcement Learning

1. Guiding Reinforcement Learning Exploration Using Natural Language
2. Learning from Demonstrations for Real World Reinforcement Learning
3. A Distributional Perspective on Reinforcement Learning
4. Evolution Strategies as a Scalable Alternative to Reinforcement Learning
5. Parameter Space Noise for Exploration
6. Learning with Opponent-Learning Awareness
7. Curiosity-driven Exploration by Self-supervised Prediction
8. META LEARNING SHARED HIERARCHIES
9. Proximal Policy Optimization Algorithms
10. CATEGORICAL REPARAMETERIZATION WITH GUMBEL-SOFTMAX
11. Rainbow: Combining Improvements in Deep Reinforcement Learning