Abstract
We present a general framework of analyzing existing story corpora to generate controllable and creative new stories. The proposed framework needs little manual annotation to achieve controllable story generation. It creates a new interface for humans to interact with computers to generate personalized stories. We apply the framework to build recurrent neural network (RNN)-based generation models to control story ending valence and storyline. Experiments show that our methods successfully achieve the control and enhance the coherence of stories through introducing storylines. with additional control factors, the generation model gets lower perplexity, and yields more coherent stories that are faithful to the control factors according to human evaluation.- Anthology ID:
- W18-1505
- Volume:
- Proceedings of the First Workshop on Storytelling
- Month:
- June
- Year:
- 2018
- Address:
- New Orleans, Louisiana
- Editors:
- Margaret Mitchell, Ting-Hao ‘Kenneth’ Huang, Francis Ferraro, Ishan Misra
- Venue:
- Story-NLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 43–49
- Language:
- URL:
- https://aclanthology.org/W18-1505
- DOI:
- 10.18653/v1/W18-1505
- Cite (ACL):
- Nanyun Peng, Marjan Ghazvininejad, Jonathan May, and Kevin Knight. 2018. Towards Controllable Story Generation. In Proceedings of the First Workshop on Storytelling, pages 43–49, New Orleans, Louisiana. Association for Computational Linguistics.
- Cite (Informal):
- Towards Controllable Story Generation (Peng et al., Story-NLP 2018)
- PDF:
- https://preview.aclanthology.org/teach-a-man-to-fish/W18-1505.pdf
- Data
- ROCStories