DBLP QuAD 2.0: Scholarly Natural Questions from SPARQL
Publikation: Beiträge in Sammelwerken › Aufsätze in Konferenzbänden › Forschung › begutachtet
Authors
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.
| Originalsprache | Englisch |
|---|---|
| Titel | K-CAP 2025 - Proceedings of the 13th Knowledge Capture Conference 2025 |
| Herausgeber | Cogan Shimizu, Sebastian Ferrada, Lalana Kagal |
| Anzahl der Seiten | 5 |
| Verlag | Association for Computing Machinery, Inc |
| Erscheinungsdatum | 09.12.2025 |
| Seiten | 236-240 |
| ISBN (elektronisch) | 979-8-4007-1867-0 |
| DOIs | |
| Publikationsstatus | Erschienen - 09.12.2025 |
| Veranstaltung | K-CAP '25: Knowledge Capture Conference 2025 - Dayton, USA / Vereinigte Staaten Dauer: 10.12.2025 → 12.12.2025 |
Bibliographische Notiz
Publisher Copyright:
© 2025 Copyright held by the owner/author(s).
- Theoretische Informatik und Mathematik
- Angewandte Informatik
- Information systems
- Software.
