Published:
2020-06-02
Proceedings:
Proceedings of the AAAI Conference on Artificial Intelligence, 34
Volume
Issue:
Vol. 34 No. 05: AAAI-20 Technical Tracks 5
Track:
AAAI Technical Track: Natural Language Processing
Downloads:
Abstract:
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 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. We further propose a reinforcement learning framework, ReCo-RL, with reward functions designed to capture the essence of these quality criteria. Experiments on the Visual Storytelling Dataset (VIST) with both automatic and human evaluation demonstrate that our ReCo-RL model achieves better performance than state-of-the-art baselines on both traditional metrics and the proposed new criteria.
DOI:
10.1609/aaai.v34i05.6305
![](https://aaai.org/wp-content/uploads/2023/02/cover_issue_249_en_US.jpg)
AAAI
Vol. 34 No. 05: AAAI-20 Technical Tracks 5
ISSN 2374-3468 (Online) ISSN 2159-5399 (Print) ISBN 978-1-57735-835-0 (10 issue set)
Published by AAAI Press, Palo Alto, California USA Copyright © 2020, Association for the Advancement of Artificial Intelligence All Rights Reserved