DBLP QuAD 2.0: Scholarly Natural Questions from SPARQL

Tilahun Taffa; Patrick Neises; Stefan Ollinger; Patrick Westphal; Marcel R. Ackermann; Debayan Banerjee; Ricardo Usbeck

doi:10.1145/3731443.3771376

DBLP QuAD 2.0: Scholarly Natural Questions from SPARQL

Tilahun Taffa
, Patrick Neises
, Stefan Ollinger
, Patrick Westphal
, Marcel R. Ackermann
, Debayan Banerjee
, Ricardo Usbeck

Professorship of Information Systems, in particular Artificial Intelligence and Explainability

Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review

Abstract

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.

Original language	English
Title of host publication	K-CAP 2025 - Proceedings of the 13th Knowledge Capture Conference 2025
Editors	Cogan Shimizu, Sebastian Ferrada, Lalana Kagal
Number of pages	5
Publisher	Association for Computing Machinery, Inc
Publication date	09.12.2025
Pages	236-240
ISBN (Electronic)	979-8-4007-1867-0
DOIs	https://doi.org/10.1145/3731443.3771376
Publication status	Published - 09.12.2025
Event	K-CAP '25: Knowledge Capture Conference 2025 - Dayton, United States Duration: 10.12.2025 → 12.12.2025

Bibliographical note

Publisher Copyright:
© 2025 Copyright held by the owner/author(s).

Research areas and keywords

DBLP
Knowledge Graph Question Answering
Question Answering Dataset
SPARQL to Natural Questions

ASJC Scopus Subject Areas

Computational Theory and Mathematics
Computer Science Applications
Information Systems
Software

Access to Document

10.1145/3731443.3771376Licence: CC BY

Cite this

Taffa, T., Neises, P., Ollinger, S., Westphal, P., Ackermann, M. R., Banerjee, D., & Usbeck, R. (2025). DBLP QuAD 2.0: Scholarly Natural Questions from SPARQL. In C. Shimizu, S. Ferrada, & L. Kagal (Eds.), K-CAP 2025 - Proceedings of the 13th Knowledge Capture Conference 2025 (pp. 236-240). (K-CAP 2025 - Proceedings of the 13th Knowledge Capture Conference 2025). Association for Computing Machinery, Inc. https://doi.org/10.1145/3731443.3771376

Taffa, Tilahun ; Neises, Patrick ; Ollinger, Stefan et al. / DBLP QuAD 2.0: Scholarly Natural Questions from SPARQL. K-CAP 2025 - Proceedings of the 13th Knowledge Capture Conference 2025. editor / Cogan Shimizu ; Sebastian Ferrada ; Lalana Kagal. Association for Computing Machinery, Inc, 2025. pp. 236-240 (K-CAP 2025 - Proceedings of the 13th Knowledge Capture Conference 2025).

@inbook{8cc3fe105ae1493cbebd4afc297ff647,

title = "DBLP QuAD 2.0: Scholarly Natural Questions from SPARQL",

abstract = "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.",

keywords = "DBLP, Knowledge Graph Question Answering, Question Answering Dataset, SPARQL to Natural Questions",

author = "Tilahun Taffa and Patrick Neises and Stefan Ollinger and Patrick Westphal and Ackermann, \{Marcel R.\} and Debayan Banerjee and Ricardo Usbeck",

note = "Publisher Copyright: {\textcopyright} 2025 Copyright held by the owner/author(s).; K-CAP '25: Knowledge Capture Conference 2025 ; Conference date: 10-12-2025 Through 12-12-2025",

year = "2025",

month = dec,

day = "9",

doi = "10.1145/3731443.3771376",

language = "English",

series = "K-CAP 2025 - Proceedings of the 13th Knowledge Capture Conference 2025",

publisher = "Association for Computing Machinery, Inc",

pages = "236--240",

editor = "Cogan Shimizu and Sebastian Ferrada and Lalana Kagal",

booktitle = "K-CAP 2025 - Proceedings of the 13th Knowledge Capture Conference 2025",

address = "United States",

}

Taffa, T, Neises, P, Ollinger, S, Westphal, P, Ackermann, MR, Banerjee, D & Usbeck, R 2025, DBLP QuAD 2.0: Scholarly Natural Questions from SPARQL. in C Shimizu, S Ferrada & L Kagal (eds), K-CAP 2025 - Proceedings of the 13th Knowledge Capture Conference 2025. K-CAP 2025 - Proceedings of the 13th Knowledge Capture Conference 2025, Association for Computing Machinery, Inc, pp. 236-240, K-CAP '25: Knowledge Capture Conference 2025, Dayton, Ohio, United States, 10.12.25. https://doi.org/10.1145/3731443.3771376

DBLP QuAD 2.0: Scholarly Natural Questions from SPARQL. / Taffa, Tilahun; Neises, Patrick; Ollinger, Stefan et al.
K-CAP 2025 - Proceedings of the 13th Knowledge Capture Conference 2025. ed. / Cogan Shimizu; Sebastian Ferrada; Lalana Kagal. Association for Computing Machinery, Inc, 2025. p. 236-240 (K-CAP 2025 - Proceedings of the 13th Knowledge Capture Conference 2025).

Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review

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.

KW - DBLP

KW - Knowledge Graph Question Answering

KW - Question Answering Dataset

KW - SPARQL to Natural Questions

UR - https://www.scopus.com/pages/publications/105024936021

U2 - 10.1145/3731443.3771376

DO - 10.1145/3731443.3771376

M3 - Article in conference proceedings

T3 - K-CAP 2025 - Proceedings of the 13th Knowledge Capture Conference 2025

SP - 236

EP - 240

BT - K-CAP 2025 - Proceedings of the 13th Knowledge Capture Conference 2025

A2 - Shimizu, Cogan

A2 - Ferrada, Sebastian

A2 - Kagal, Lalana

PB - Association for Computing Machinery, Inc

T2 - K-CAP '25: Knowledge Capture Conference 2025

Y2 - 10 December 2025 through 12 December 2025

ER -

Taffa T, Neises P, Ollinger S, Westphal P, Ackermann MR, Banerjee D et al. DBLP QuAD 2.0: Scholarly Natural Questions from SPARQL. In Shimizu C, Ferrada S, Kagal L, editors, K-CAP 2025 - Proceedings of the 13th Knowledge Capture Conference 2025. Association for Computing Machinery, Inc. 2025. p. 236-240. (K-CAP 2025 - Proceedings of the 13th Knowledge Capture Conference 2025). doi: 10.1145/3731443.3771376

DBLP QuAD 2.0: Scholarly Natural Questions from SPARQL

Abstract

Bibliographical note

Research areas and keywords

ASJC Scopus Subject Areas

Access to Document

Fingerprint

Cite this