WriterForcing: Generating more interesting story endings
Prakhar Gupta, Vinayshekhar Bannihatti Kumar, Mukul Bhutani, Alan W Black
Abstract
We study the problem of generating interesting endings for stories. Neural generative models have shown promising results for various text generation problems. Sequence to Sequence (Seq2Seq) models are typically trained to generate a single output sequence for a given input sequence. However, in the context of a story, multiple endings are possible. Seq2Seq models tend to ignore the context and generate generic and dull responses. Very few works have studied generating diverse and interesting story endings for the same story context. In this paper, we propose models which generate more diverse and interesting outputs by 1) training models to focus attention on important keyphrases of the story, and 2) promoting generating nongeneric words. We show that the combination of the two leads to more interesting endings.- Anthology ID:
- W19-3413
- Volume:
- Proceedings of the Second Workshop on Storytelling
- Month:
- August
- Year:
- 2019
- Address:
- Florence, Italy
- Editors:
- Francis Ferraro, Ting-Hao ‘Kenneth’ Huang, Stephanie M. Lukin, Margaret Mitchell
- Venue:
- Story-NLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 117–126
- Language:
- URL:
- https://aclanthology.org/W19-3413
- DOI:
- 10.18653/v1/W19-3413
- Cite (ACL):
- Prakhar Gupta, Vinayshekhar Bannihatti Kumar, Mukul Bhutani, and Alan W Black. 2019. WriterForcing: Generating more interesting story endings. In Proceedings of the Second Workshop on Storytelling, pages 117–126, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- WriterForcing: Generating more interesting story endings (Gupta et al., Story-NLP 2019)
- PDF:
- https://preview.aclanthology.org/corrections-2024-07/W19-3413.pdf
- Code
- witerforcing/WriterForcing + additional community code