Paper ID: 2409.18969

Integrating SPARQL and LLMs for Question Answering over Scholarly Data Sources

Fomubad Borista Fondi, Azanzi Jiomekong Fidel

The Scholarly Hybrid Question Answering over Linked Data (QALD) Challenge at International Semantic Web Conference (ISWC) 2024 focuses on Question Answering (QA) over diverse scholarly sources: DBLP, SemOpenAlex, and Wikipedia-based texts. This paper describes a methodology that combines SPARQL queries, divide and conquer algorithms, and BERT-based-case-SQuad2 predictions. It starts with SPARQL queries to gather data, then applies divide and conquer to manage various question types and sources, and uses BERT to handle personal author questions. The approach, evaluated with Exact Match and F-score metrics, shows promise for improving QA accuracy and efficiency in scholarly contexts.

Submitted: Sep 11, 2024