Natural Language Generation from Wikidata—Architecture, Scalability and Challenges
Book chapter, 2026
We present an architecture for generation of Wikipedia articles in several languages from Wikidata. The articles cover the topics of countries, cities, people, universities and professions, and vary in size depending on the amount of available information. The architecture is based on the Grammatical Framework, but we made significant extensions to the framework in order to scale it up to the size of Wikidata. We describe the different scalability issues, and we discuss challenges arising from the current Wikidata structure.
Author
Krasimir Angelov
Chalmers, Computer Science and Engineering (Chalmers), Functional Programming
University of Gothenburg
Andrea Carrion del Fresno
Chalmers, Computer Science and Engineering (Chalmers), Functional Programming
University of Gothenburg
Ekaterina Voloshina
Chalmers, Computer Science and Engineering (Chalmers), Functional Programming
University of Gothenburg
Aarne Ranta
Chalmers, Computer Science and Engineering (Chalmers), Computing Science
University of Gothenburg
Computational Linguistics, Information, Reasoning, and AI 2024
Vol. 1280 1-23
978-3-032-21143-9 (ISBN)
Subject Categories (SSIF 2025)
Natural Language Processing
Computer Sciences
DOI
10.1007/978-3-032-21143-9_1