Abstract
Research on summarization has mainly been driven by empirical approaches, crafting systems to perform well on standard datasets with the notion of information Importance remaining latent. We argue that establishing theoretical models of Importance will advance our understanding of the task and help to further improve summarization systems. To this end, we propose simple but rigorous definitions of several concepts that were previously used only intuitively in summarization: Redundancy, Relevance, and Informativeness. Importance arises as a single quantity naturally unifying these concepts. Additionally, we provide intuitions to interpret the proposed quantities and experiments to demonstrate the potential of the framework to inform and guide subsequent works.- Anthology ID:
- P19-1101
- Volume:
- Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2019
- Address:
- Florence, Italy
- Editors:
- Anna Korhonen, David Traum, Lluís Màrquez
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1059–1073
- Language:
- URL:
- https://aclanthology.org/P19-1101
- DOI:
- 10.18653/v1/P19-1101
- Award:
- Outstanding Paper
- Cite (ACL):
- Maxime Peyrard. 2019. A Simple Theoretical Model of Importance for Summarization. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1059–1073, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- A Simple Theoretical Model of Importance for Summarization (Peyrard, ACL 2019)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/P19-1101.pdf