DBLP QuAD 2.0: Scholarly Natural Questions from SPARQL
Publikation: Beiträge in Sammelwerken › Aufsätze in Konferenzbänden › Forschung › begutachtet
Standard
K-CAP '25: Proceedings of the 13th Knowledge Capture Conference 2025. 2025.
Publikation: Beiträge in Sammelwerken › Aufsätze in Konferenzbänden › Forschung › begutachtet
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - CHAP
T1 - DBLP QuAD 2.0: Scholarly Natural Questions from SPARQL
AU - Taffa, Tilahun
AU - Neises, Patrick
AU - Ollinger, Stefan
AU - Westphal, Patrick
AU - Ackermann, Marcel R.
AU - Banerjee, Debayan
AU - Usbeck, Ricardo
PY - 2025/12/9
Y1 - 2025/12/9
N2 - We present DBLP-QuAD 2.0, designed to evaluate Scholarly Knowledge Graph Question Answering (KGQA) over DBLP. Recent updates in the underlying DBLP KG, including new entities and relationships such as venues, research streams, and citation links, have necessitated a corresponding update to existing KG QA benchmarking resources. While the DBLP-QuAD dataset focused on author and publication-centered queries, DBLP-QuAD 2.0 broadens the coverage to reflect the enriched structure of the updated KG. Specifically, the questions in our dataset are formulated from SPARQL query logs that cover a wide range of entities involving authors, publications, venues, research streams, and citation relationships. DBLP-QuAD 2.0 thus provides a more comprehensive benchmark for evaluating KGQA systems with a baseline.
AB - We present DBLP-QuAD 2.0, designed to evaluate Scholarly Knowledge Graph Question Answering (KGQA) over DBLP. Recent updates in the underlying DBLP KG, including new entities and relationships such as venues, research streams, and citation links, have necessitated a corresponding update to existing KG QA benchmarking resources. While the DBLP-QuAD dataset focused on author and publication-centered queries, DBLP-QuAD 2.0 broadens the coverage to reflect the enriched structure of the updated KG. Specifically, the questions in our dataset are formulated from SPARQL query logs that cover a wide range of entities involving authors, publications, venues, research streams, and citation relationships. DBLP-QuAD 2.0 thus provides a more comprehensive benchmark for evaluating KGQA systems with a baseline.
U2 - 10.1145/3731443.3771376
DO - 10.1145/3731443.3771376
M3 - Article in conference proceedings
BT - K-CAP '25: Proceedings of the 13th Knowledge Capture Conference 2025
ER -