Scholarlink

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.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Natural Language Generation from Wikidata—Architecture, Scalability and Challenges

  • 章节

  • 发表日期：

    2026年

查看全文
  • Krasimir Angelov,
  • Andrea Carrión del Fresno,
  • Ekaterina Voloshina,
  • Aarne Ranta

摘要

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.