Natural Language Generation from Wikidata—Architecture, Scalability and Challenges

Artikel i vetenskaplig tidskrift, 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.