A Pipeline for Extracting Abstract Dependency Templates for Data-to-Text Natural Language Generation
Abstract
We present work in progress that aims to address the coverage issue faced by rule-based text generators. We propose a pipeline for extracting abstract dependency template (predicate-argument structures) from Wikipedia text to be used as input for generating text from structured data with the FORGe system. The pipeline comprises three main components: (i) candidate sentence retrieval, (ii) clause extraction, ranking and selection, and (iii) conversion to predicate-argument form. We present an approach and preliminary evaluation for the ranking and selection module.- Anthology ID:
- 2023.depling-1.9
- Volume:
- Proceedings of the Seventh International Conference on Dependency Linguistics (Depling, GURT/SyntaxFest 2023)
- Month:
- March
- Year:
- 2023
- Address:
- Washington, D.C.
- Editors:
- Owen Rambow, François Lareau
- Venues:
- DepLing | SyntaxFest
- SIG:
- SIGPARSE
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 91–101
- Language:
- URL:
- https://aclanthology.org/2023.depling-1.9
- DOI:
- Cite (ACL):
- Simon Mille, Josep Ricci, Alexander Shvets, and Anya Belz. 2023. A Pipeline for Extracting Abstract Dependency Templates for Data-to-Text Natural Language Generation. In Proceedings of the Seventh International Conference on Dependency Linguistics (Depling, GURT/SyntaxFest 2023), pages 91–101, Washington, D.C.. Association for Computational Linguistics.
- Cite (Informal):
- A Pipeline for Extracting Abstract Dependency Templates for Data-to-Text Natural Language Generation (Mille et al., DepLing-SyntaxFest 2023)
- PDF:
- https://preview.aclanthology.org/naacl-24-ws-corrections/2023.depling-1.9.pdf