{"author":[{"full_name":"Vollmers, Daniel","last_name":"Vollmers","first_name":"Daniel"},{"first_name":"Nikit","last_name":"Srivastava","full_name":"Srivastava, Nikit","orcid":"0009-0004-5164-4911","id":"70066"},{"id":"72768","orcid":"0000-0003-0215-1278","full_name":"Zahera, Hamada Mohamed Abdelsamee","last_name":"Zahera","first_name":"Hamada Mohamed Abdelsamee"},{"full_name":"Moussallem, Diego","id":"71635","first_name":"Diego","last_name":"Moussallem"},{"id":"65716","full_name":"Ngonga Ngomo, Axel-Cyrille","last_name":"Ngonga Ngomo","first_name":"Axel-Cyrille"}],"status":"public","citation":{"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>.","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>","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>.","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} }","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.","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>","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>."},"date_created":"2024-11-22T12:56:54Z","page":"174–189","abstract":[{"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.","lang":"eng"}],"language":[{"iso":"eng"}],"publication_identifier":{"isbn":["978-3-031-77792-9"]},"user_id":"70066","publisher":"Springer Nature Switzerland","year":"2025","editor":[{"full_name":"Alam, Mehwish","last_name":"Alam","first_name":"Mehwish"},{"first_name":"Marco","last_name":"Rospocher","full_name":"Rospocher, Marco"},{"last_name":"van Erp","first_name":"Marieke","full_name":"van Erp, Marieke"},{"last_name":"Hollink","first_name":"Laura","full_name":"Hollink, Laura"},{"first_name":"Genet Asefa","last_name":"Gesese","full_name":"Gesese, Genet Asefa"}],"date_updated":"2024-11-22T12:58:59Z","doi":"https://doi.org/10.1007/978-3-031-77792-9_11","publication":"Knowledge Engineering and Knowledge Management","_id":"57324","type":"conference","title":"UniQ-Gen: Unified Query Generation Across Multiple Knowledge Graphs","place":"Cham"}