NLP using DRL
Various of NLP tasks using Deep Reinforcement Learning
- Deep Reinforcement Learning for Mention-Ranking Coreference Models
- Deep Reinforcement Learning for Dialogue Generation
- A Deep Reinforced Model for Abstractive Summarization
- Learning through Dialogue Interactions by Asking Questions
- Deal or No Deal? End-to-End Learning for Negotiation Dialogues
- Teaching Machines to Describe Images via Natural Language Feedback
- Task-Oriented Query Reformulation with Reinforcement Learning
- DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning
- Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access
Dialogue Policy Optimization
- End-to-End Task-Completion Neural Dialogue Systems
- Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning
- PERSONALIZING DIALOGUE AGENTS:I HAVE A DOG, DO YOU HAVE PETS TOO?
Representation Learning for NLP
- GloVe: Global Vectors for Word Representation
- Skip-Thought Vectors
- Supervised Learning of Universal Sentence Representations from Natural Language Inference Data
- Mapping Unseen Words to Task-Trained Embedding Spaces
- A Structured Self-attentive Sentence Embedding
- Bag of Tricks for Efficient Text Classification
- Enriching Word Vectors with Subword Information
- Neural Embeddings of Graphs in Hyperbolic Space
- Poincaré Embeddings for Learning Hierarchical Representations
- Learned in Translation: Contextualized Word Vectors
- Exploiting Similarities among Languages for Machine Translation
- Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints
- Mixing Dirichlet Topic Models and Word Embeddings to Make lda2vec
- AN EFFICIENT FRAMEWORK FOR LEARNING SENTENCE REPRESENTATIONS
NLP
- Regularizing and Optimizing LSTM Language Models
- Layer Normalization
- POINTER SENTINEL MIXTURE MODELS
- Training RNNs as Fast as CNNs
- Beam Search Strategies for Neural Machine Translation
- Position-aware Attention and Supervised Data Improve Slot Filling
- Pointing the Unknown Words
- Dilated Recurrent Neural Networks
- FRATERNAL DROPOUT
- BREAKING THE SOFTMAX BOTTLENECK:A HIGH-RANK RNN LANGUAGE MODEL
- VARIATIONAL BI-LSTMS
- END-TO-END JOINT LEARNING OF NATURAL LANGUAGE UNDERSTANDING AND DIALOGUE MANAGER
- SVD-Softmax: Fast Softmax Approximation on Large Vocabulary Neural Networks
- Natural Language Does Not Emerge ‘Naturally’ in Multi-Agent Dialog
- Learning to Generate Reviews and Discovering Sentiment
- MinimalRNN: Toward More Interpretable and Trainable Recurrent Neural Networks
- Sequence-to-Sequence Learning as Beam-Search Optimization
Machine Reading Comprehension
- Bidirectional Attention Flow for Machine Comprehension
- DCN+: Mixed Objective and Deep Residual Coattention for Question Answering
- FUSIONNET: FUSING VIA FULLY-AWARE ATTENTION WITH APPLICATION TO MACHINE COMPREHENSION
- Fast and Accurate Reading Comprehension by Combining Self-Attention and Convolution
Speech Recognition
- Listen, Attend and Spell
- Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
- State-of-the-art Speech Recognition With Sequence-to-Sequence Models
Neural Machine Translation
- Attention Is All You Need
- Unsupervised Machine Translation Using Monolingual Corpora Only
- Incorporating Copying Mechanism in Sequence-to-Sequence Learning
- Training Tips for the Transformer Model
Reinforcement Learning
- Guiding Reinforcement Learning Exploration Using Natural Language
- Learning from Demonstrations for Real World Reinforcement Learning
- A Distributional Perspective on Reinforcement Learning
- Evolution Strategies as a Scalable Alternative to Reinforcement Learning
- Parameter Space Noise for Exploration
- Learning with Opponent-Learning Awareness
- Curiosity-driven Exploration by Self-supervised Prediction
- META LEARNING SHARED HIERARCHIES
- Proximal Policy Optimization Algorithms
- CATEGORICAL REPARAMETERIZATION WITH GUMBEL-SOFTMAX
- Rainbow: Combining Improvements in Deep Reinforcement Learning