What Makes A Good Story? Designing Composite Rewards for Visual Storytelling

Understand

Previous storytelling approaches mostly focused on optimizing traditional metrics such as BLEU, ROUGE and CIDEr.

• In this paper, we re-examine this problem from a different angle, by looking deep into what defines a realistically-natural and topically-coherent story.
• To this end, we propose three assessment criteria: relevance, coherence and expressiveness, which we observe through empirical analysis could constitute a "high-quality" story to the human eye.
• Following this quality guideline, we propose a reinforcement learning framework, ReCo-RL, with reward functions designed to capture the essence of these quality criteria.