Abstract
This work introduces an original and practical paradigm for narrative comprehension, stemming from the characteristics that individual passages within narratives tend to be more cohesively related than isolated.Complementary to the common end-to-end paradigm, we propose a fine-grained modeling of narrative context, by formulating a graph dubbed NarCo, which explicitly depicts task-agnostic coherence dependencies that are ready to be consumed by various downstream tasks. In particular, edges in NarCo encompass free-form retrospective questions between context snippets, inspired by human cognitive perception that constantly reinstates relevant events from prior context. Importantly, our graph formalism is practically instantiated by LLMs without human annotations, through our designed two-stage prompting scheme.To examine the graph properties and its utility, we conduct three studies in narratives, each from a unique angle: edge relation efficacy, local context enrichment, and broader application in QA. All tasks could benefit from the explicit coherence captured by NarCo.- Anthology ID:
- 2024.acl-long.317
- Volume:
- Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand
- Editors:
- Lun-Wei Ku, Andre Martins, Vivek Srikumar
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5822–5838
- Language:
- URL:
- https://aclanthology.org/2024.acl-long.317
- DOI:
- 10.18653/v1/2024.acl-long.317
- Cite (ACL):
- Liyan Xu, Jiangnan Li, Mo Yu, and Jie Zhou. 2024. Fine-Grained Modeling of Narrative Context: A Coherence Perspective via Retrospective Questions. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5822–5838, Bangkok, Thailand. Association for Computational Linguistics.
- Cite (Informal):
- Fine-Grained Modeling of Narrative Context: A Coherence Perspective via Retrospective Questions (Xu et al., ACL 2024)
- PDF:
- https://preview.aclanthology.org/autopr/2024.acl-long.317.pdf