Blog Posts

• Understanding Gradient Rollback

• Interpretability and Analysis of Models for NLP

• Attending to Future Tokens for Bidirectional Sequence Generation

• Response-Based and Counterfactual Learning for Sequence-to-Sequence Tasks in NLP: An Overview

• Counterfactual Learning of Semantic Parsers When Even Gold Answers Are Unattainable

• Taming Wild Reward Functions: The Score Function Gradient Estimator Trick