Enhancing factualness and controllability of Data-to-Text Generation via data Views and constraints
Craig Thomson, Clement Rebuffel, Ehud Reiter, Laure Soulier, Somayajulu Sripada, Patrick Gallinari
Abstract
Neural data-to-text systems lack the control and factual accuracy required to generate useful and insightful summaries of multidimensional data. We propose a solution in the form of data views, where each view describes an entity and its attributes along specific dimensions. A sequence of views can then be used as a high-level schema for document planning, with the neural model handling the complexities of micro-planning and surface realization. We show that our view-based system retains factual accuracy while offering high-level control of output that can be tailored based on user preference or other norms within the domain.- Anthology ID:
- 2023.inlg-main.16
- Volume:
- Proceedings of the 16th International Natural Language Generation Conference
- Month:
- September
- Year:
- 2023
- Address:
- Prague, Czechia
- Editors:
- C. Maria Keet, Hung-Yi Lee, Sina Zarrieß
- Venues:
- INLG | SIGDIAL
- SIG:
- SIGGEN
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 221–236
- Language:
- URL:
- https://aclanthology.org/2023.inlg-main.16
- DOI:
- 10.18653/v1/2023.inlg-main.16
- Cite (ACL):
- Craig Thomson, Clement Rebuffel, Ehud Reiter, Laure Soulier, Somayajulu Sripada, and Patrick Gallinari. 2023. Enhancing factualness and controllability of Data-to-Text Generation via data Views and constraints. In Proceedings of the 16th International Natural Language Generation Conference, pages 221–236, Prague, Czechia. Association for Computational Linguistics.
- Cite (Informal):
- Enhancing factualness and controllability of Data-to-Text Generation via data Views and constraints (Thomson et al., INLG-SIGDIAL 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-3/2023.inlg-main.16.pdf