A template-based approach for question answering over knowledge bases

• DOI: 10.1007/s10115-023-01966-8
• Publication Date: 2023-09-02T12:01:27Z
• Authors: Anna Formica; Ida Mele; Francesco Taglino
• Keywords: Template

Abstract In this paper, we address the problem of answering complex questions formulated by users in natural language. Since traditional information retrieval systems are not suitable for questions, these usually run over knowledge bases, such as Wikidata or DBpedia. We propose a semi-automatic approach transforming language question into SPARQL query that can be easily processed base. The applies classification techniques to associate with proper template from set predefined templates. nature our is templates manually written human assessors, who experts whereas and processing steps completely automatic. Our experiments on large-scale CSQA dataset question-answering corroborate effectiveness approach.