Josep Ricci


pdf bib
A Pipeline for Extracting Abstract Dependency Templates for Data-to-Text Natural Language Generation
Simon Mille | Josep Ricci | Alexander Shvets | Anya Belz
Proceedings of the Seventh International Conference on Dependency Linguistics (Depling, GURT/SyntaxFest 2023)

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.