---
_id: '57324'
abstract:
- lang: eng
  text: Generating SPARQL queries is crucial for extracting relevant information from
    diverse knowledge graphs. However, the structural and semantic differences among
    these graphs necessitate training or fine-tuning a tailored model for each one.
    In this paper, we propose UniQ-Gen, a unified query generation approach to generate
    SPARQL queries across various knowledge graphs. UniQ-Gen integrates entity recognition,
    disambiguation, and linking through a BERT-NER model and employs cross-encoder
    ranking to align questions with the Freebase ontology. We conducted several experiments
    on different benchmark datasets such as LC-QuAD 2.0, GrailQA, and QALD-10. The
    evaluation results demonstrate that our approach achieves performance equivalent
    to or better than models fine-tuned for individual knowledge graphs. This finding
    suggests that fine-tuning a unified model on a heterogeneous dataset of SPARQL
    queries across different knowledge graphs eliminates the need for separate models
    for each graph, thereby reducing resource requirements.
author:
- first_name: Daniel
  full_name: Vollmers, Daniel
  last_name: Vollmers
- first_name: Nikit
  full_name: Srivastava, Nikit
  id: '70066'
  last_name: Srivastava
  orcid: 0009-0004-5164-4911
- first_name: Hamada Mohamed Abdelsamee
  full_name: Zahera, Hamada Mohamed Abdelsamee
  id: '72768'
  last_name: Zahera
  orcid: 0000-0003-0215-1278
- first_name: Diego
  full_name: Moussallem, Diego
  id: '71635'
  last_name: Moussallem
- first_name: Axel-Cyrille
  full_name: Ngonga Ngomo, Axel-Cyrille
  id: '65716'
  last_name: Ngonga Ngomo
citation:
  ama: 'Vollmers D, Srivastava N, Zahera HMA, Moussallem D, Ngonga Ngomo A-C. UniQ-Gen:
    Unified Query Generation Across Multiple Knowledge Graphs. In: Alam M, Rospocher
    M, van Erp M, Hollink L, Gesese GA, eds. <i>Knowledge Engineering and Knowledge
    Management</i>. Springer Nature Switzerland; 2025:174–189. doi:<a href="https://doi.org/10.1007/978-3-031-77792-9_11">https://doi.org/10.1007/978-3-031-77792-9_11</a>'
  apa: 'Vollmers, D., Srivastava, N., Zahera, H. M. A., Moussallem, D., &#38; Ngonga
    Ngomo, A.-C. (2025). UniQ-Gen: Unified Query Generation Across Multiple Knowledge
    Graphs. In M. Alam, M. Rospocher, M. van Erp, L. Hollink, &#38; G. A. Gesese (Eds.),
    <i>Knowledge Engineering and Knowledge Management</i> (pp. 174–189). Springer
    Nature Switzerland. <a href="https://doi.org/10.1007/978-3-031-77792-9_11">https://doi.org/10.1007/978-3-031-77792-9_11</a>'
  bibtex: '@inproceedings{Vollmers_Srivastava_Zahera_Moussallem_Ngonga Ngomo_2025,
    place={Cham}, title={UniQ-Gen: Unified Query Generation Across Multiple Knowledge
    Graphs}, DOI={<a href="https://doi.org/10.1007/978-3-031-77792-9_11">https://doi.org/10.1007/978-3-031-77792-9_11</a>},
    booktitle={Knowledge Engineering and Knowledge Management}, publisher={Springer
    Nature Switzerland}, author={Vollmers, Daniel and Srivastava, Nikit and Zahera,
    Hamada Mohamed Abdelsamee and Moussallem, Diego and Ngonga Ngomo, Axel-Cyrille},
    editor={Alam, Mehwish and Rospocher, Marco and van Erp, Marieke and Hollink, Laura
    and Gesese, Genet Asefa}, year={2025}, pages={174–189} }'
  chicago: 'Vollmers, Daniel, Nikit Srivastava, Hamada Mohamed Abdelsamee Zahera,
    Diego Moussallem, and Axel-Cyrille Ngonga Ngomo. “UniQ-Gen: Unified Query Generation
    Across Multiple Knowledge Graphs.” In <i>Knowledge Engineering and Knowledge Management</i>,
    edited by Mehwish Alam, Marco Rospocher, Marieke van Erp, Laura Hollink, and Genet
    Asefa Gesese, 174–189. Cham: Springer Nature Switzerland, 2025. <a href="https://doi.org/10.1007/978-3-031-77792-9_11">https://doi.org/10.1007/978-3-031-77792-9_11</a>.'
  ieee: 'D. Vollmers, N. Srivastava, H. M. A. Zahera, D. Moussallem, and A.-C. Ngonga
    Ngomo, “UniQ-Gen: Unified Query Generation Across Multiple Knowledge Graphs,”
    in <i>Knowledge Engineering and Knowledge Management</i>, 2025, pp. 174–189, doi:
    <a href="https://doi.org/10.1007/978-3-031-77792-9_11">https://doi.org/10.1007/978-3-031-77792-9_11</a>.'
  mla: 'Vollmers, Daniel, et al. “UniQ-Gen: Unified Query Generation Across Multiple
    Knowledge Graphs.” <i>Knowledge Engineering and Knowledge Management</i>, edited
    by Mehwish Alam et al., Springer Nature Switzerland, 2025, pp. 174–189, doi:<a
    href="https://doi.org/10.1007/978-3-031-77792-9_11">https://doi.org/10.1007/978-3-031-77792-9_11</a>.'
  short: 'D. Vollmers, N. Srivastava, H.M.A. Zahera, D. Moussallem, A.-C. Ngonga Ngomo,
    in: M. Alam, M. Rospocher, M. van Erp, L. Hollink, G.A. Gesese (Eds.), Knowledge
    Engineering and Knowledge Management, Springer Nature Switzerland, Cham, 2025,
    pp. 174–189.'
date_created: 2024-11-22T12:56:54Z
date_updated: 2024-11-22T12:58:59Z
doi: https://doi.org/10.1007/978-3-031-77792-9_11
editor:
- first_name: Mehwish
  full_name: Alam, Mehwish
  last_name: Alam
- first_name: Marco
  full_name: Rospocher, Marco
  last_name: Rospocher
- first_name: Marieke
  full_name: van Erp, Marieke
  last_name: van Erp
- first_name: Laura
  full_name: Hollink, Laura
  last_name: Hollink
- first_name: Genet Asefa
  full_name: Gesese, Genet Asefa
  last_name: Gesese
language:
- iso: eng
page: 174–189
place: Cham
publication: Knowledge Engineering and Knowledge Management
publication_identifier:
  isbn:
  - 978-3-031-77792-9
publisher: Springer Nature Switzerland
status: public
title: 'UniQ-Gen: Unified Query Generation Across Multiple Knowledge Graphs'
type: conference
user_id: '70066'
year: '2025'
...