Unsupervised Hierarchical Story Infilling
Daphne Ippolito, David Grangier, Chris Callison-Burch, Douglas Eck
Abstract
Story infilling involves predicting words to go into a missing span from a story. This challenging task has the potential to transform interactive tools for creative writing. However, state-of-the-art conditional language models have trouble balancing fluency and coherence with novelty and diversity. We address this limitation with a hierarchical model which first selects a set of rare words and then generates text conditioned on that set. By relegating the high entropy task of picking rare words to a word-sampling model, the second-stage model conditioned on those words can achieve high fluency and coherence by searching for likely sentences, without sacrificing diversity.- Anthology ID:
- W19-2405
- Volume:
- Proceedings of the First Workshop on Narrative Understanding
- Month:
- June
- Year:
- 2019
- Address:
- Minneapolis, Minnesota
- Editors:
- David Bamman, Snigdha Chaturvedi, Elizabeth Clark, Madalina Fiterau, Mohit Iyyer
- Venue:
- WNU
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 37–43
- Language:
- URL:
- https://aclanthology.org/W19-2405
- DOI:
- 10.18653/v1/W19-2405
- Cite (ACL):
- Daphne Ippolito, David Grangier, Chris Callison-Burch, and Douglas Eck. 2019. Unsupervised Hierarchical Story Infilling. In Proceedings of the First Workshop on Narrative Understanding, pages 37–43, Minneapolis, Minnesota. Association for Computational Linguistics.
- Cite (Informal):
- Unsupervised Hierarchical Story Infilling (Ippolito et al., WNU 2019)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/W19-2405.pdf