Transfer Reward Learning for Policy Gradient-Based Text Generation

Understand

Task-specific scores are often used to optimize for and evaluate the performance of conditional text generation systems.

• However, such scores are non-differentiable and cannot be used in the standard supervised learning paradigm.
• Hence, policy gradient methods are used since the gradient can be computed without requiring a differentiable objective.
• However, we argue that current n-gram overlap based measures that are used as rewards can be improved by using model-based rewards transferred from tasks that directly compare the similarity of sentence pairs.