Go Back in Time: Generating Flashbacks in Stories with Event Temporal Prompts

Rujun Han, Hong Chen, Yufei Tian, Nanyun Peng


Abstract
Stories or narratives are comprised of a sequence of events. To compose interesting stories, professional writers often leverage a creative writing technique called flashback that inserts past events into current storylines as we commonly observe in novels and plays. However, it is challenging for machines to generate flashback as it requires a solid understanding of event temporal order (e.g. feeling hungry before eat, not vice versa), and the creativity to arrange storylines so that earlier events do not always appear first in narrative order. Two major issues in existing systems that exacerbate the challenges: 1) temporal bias in pertaining and story datasets that leads to monotonic event temporal orders; 2) lack of explicit guidance that helps machines decide where to insert flashbacks. We propose to address these issues using structured storylines to encode events and their pair-wise temporal relations (before, after and vague) as temporal prompts that guide how stories should unfold temporally. We leverage a Plan-and-Write framework enhanced by reinforcement learning to generate storylines and stories end-to-end. Evaluation results show that the proposed method can generate more interesting stories with flashbacks while maintaining textual diversity, fluency, and temporal coherence.
Anthology ID:
2022.naacl-main.104
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1450–1470
Language:
URL:
https://preview.aclanthology.org/ingest-nlpsi/2022.naacl-main.104/
DOI:
10.18653/v1/2022.naacl-main.104
Bibkey:
Cite (ACL):
Rujun Han, Hong Chen, Yufei Tian, and Nanyun Peng. 2022. Go Back in Time: Generating Flashbacks in Stories with Event Temporal Prompts. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1450–1470, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Go Back in Time: Generating Flashbacks in Stories with Event Temporal Prompts (Han et al., NAACL 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-nlpsi/2022.naacl-main.104.pdf
Software:
 2022.naacl-main.104.software.zip
Video:
 https://preview.aclanthology.org/ingest-nlpsi/2022.naacl-main.104.mp4