Abstract
Though impressive results have been achieved in visual captioning, the task of generating abstract stories from photo streams is still a little-tapped problem. Different from captions, stories have more expressive language styles and contain many imaginary concepts that do not appear in the images. Thus it poses challenges to behavioral cloning algorithms. Furthermore, due to the limitations of automatic metrics on evaluating story quality, reinforcement learning methods with hand-crafted rewards also face difficulties in gaining an overall performance boost. Therefore, we propose an Adversarial REward Learning (AREL) framework to learn an implicit reward function from human demonstrations, and then optimize policy search with the learned reward function. Though automatic evaluation indicates slight performance boost over state-of-the-art (SOTA) methods in cloning expert behaviors, human evaluation shows that our approach achieves significant improvement in generating more human-like stories than SOTA systems.- Anthology ID:
- P18-1083
- Volume:
- Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2018
- Address:
- Melbourne, Australia
- Editors:
- Iryna Gurevych, Yusuke Miyao
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 899–909
- Language:
- URL:
- https://aclanthology.org/P18-1083
- DOI:
- 10.18653/v1/P18-1083
- Cite (ACL):
- Xin Wang, Wenhu Chen, Yuan-Fang Wang, and William Yang Wang. 2018. No Metrics Are Perfect: Adversarial Reward Learning for Visual Storytelling. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 899–909, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- No Metrics Are Perfect: Adversarial Reward Learning for Visual Storytelling (Wang et al., ACL 2018)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/P18-1083.pdf
- Code
- littlekobe/AREL + additional community code
- Data
- VIST