[{"status":"public","date_created":"2023-08-16T08:57:11Z","publication_status":"published","publication_identifier":{"issn":["0302-9743","1611-3349"],"isbn":["9783031353192","9783031353208"]},"author":[{"full_name":"Ahmed, Abdullah Fathi Ahmed","first_name":"Abdullah Fathi Ahmed","id":"29670","last_name":"Ahmed"},{"last_name":"Firmansyah","id":"76787","first_name":"Asep Fajar","full_name":"Firmansyah, Asep Fajar"},{"orcid":"https://orcid.org/0000-0002-9927-2203","full_name":"Sherif, Mohamed","first_name":"Mohamed","id":"67234","last_name":"Sherif"},{"full_name":"Moussallem, Diego","first_name":"Diego","id":"71635","last_name":"Moussallem"},{"first_name":"Axel-Cyrille","full_name":"Ngonga Ngomo, Axel-Cyrille","last_name":"Ngonga Ngomo","id":"65716"}],"publisher":"Springer Nature Switzerland","department":[{"_id":"34"}],"publication":"Natural Language Processing and Information Systems","user_id":"67234","title":"Explainable Integration of Knowledge Graphs Using Large Language Models","place":"Cham","abstract":[{"text":"Linked knowledge graphs build the backbone of many data-driven applications such as search engines, conversational agents and e-commerce solutions. Declarative link discovery frameworks use complex link specifications to express the conditions under which a link between two resources can be deemed to exist. However, understanding such complex link specifications is a challenging task for non-expert users of link discovery frameworks. In this paper, we address this drawback by devising NMV-LS, a language model-based verbalization approach for translating complex link specifications into natural language. NMV-LS relies on the results of rule-based link specification verbalization to apply continuous training on T5, a large language model based on the Transformerarchitecture. We evaluated NMV-LS on English and German datasets using well-known machine translation metrics such as BLUE, METEOR, ChrF++ and TER. Our results suggest that our approach achieves a verbalization performance close to that of humans and outperforms state of the art approaches. Our source code and datasets are publicly available at https://github.com/dice-group/NMV-LS.","lang":"eng"}],"language":[{"iso":"eng"}],"citation":{"ieee":"A. F. A. Ahmed, A. F. Firmansyah, M. Sherif, D. Moussallem, and A.-C. Ngonga Ngomo, “Explainable Integration of Knowledge Graphs Using Large Language Models,” in Natural Language Processing and Information Systems, Cham: Springer Nature Switzerland, 2023.","short":"A.F.A. Ahmed, A.F. Firmansyah, M. Sherif, D. Moussallem, A.-C. Ngonga Ngomo, in: Natural Language Processing and Information Systems, Springer Nature Switzerland, Cham, 2023.","bibtex":"@inbook{Ahmed_Firmansyah_Sherif_Moussallem_Ngonga Ngomo_2023, place={Cham}, title={Explainable Integration of Knowledge Graphs Using Large Language Models}, DOI={10.1007/978-3-031-35320-8_9}, booktitle={Natural Language Processing and Information Systems}, publisher={Springer Nature Switzerland}, author={Ahmed, Abdullah Fathi Ahmed and Firmansyah, Asep Fajar and Sherif, Mohamed and Moussallem, Diego and Ngonga Ngomo, Axel-Cyrille}, year={2023} }","mla":"Ahmed, Abdullah Fathi Ahmed, et al. “Explainable Integration of Knowledge Graphs Using Large Language Models.” Natural Language Processing and Information Systems, Springer Nature Switzerland, 2023, doi:10.1007/978-3-031-35320-8_9.","apa":"Ahmed, A. F. A., Firmansyah, A. F., Sherif, M., Moussallem, D., & Ngonga Ngomo, A.-C. (2023). Explainable Integration of Knowledge Graphs Using Large Language Models. In Natural Language Processing and Information Systems. Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-35320-8_9","ama":"Ahmed AFA, Firmansyah AF, Sherif M, Moussallem D, Ngonga Ngomo A-C. Explainable Integration of Knowledge Graphs Using Large Language Models. In: Natural Language Processing and Information Systems. Springer Nature Switzerland; 2023. doi:10.1007/978-3-031-35320-8_9","chicago":"Ahmed, Abdullah Fathi Ahmed, Asep Fajar Firmansyah, Mohamed Sherif, Diego Moussallem, and Axel-Cyrille Ngonga Ngomo. “Explainable Integration of Knowledge Graphs Using Large Language Models.” In Natural Language Processing and Information Systems. Cham: Springer Nature Switzerland, 2023. https://doi.org/10.1007/978-3-031-35320-8_9."},"type":"book_chapter","year":"2023","doi":"10.1007/978-3-031-35320-8_9","date_updated":"2023-08-16T09:15:42Z","_id":"46516"},{"language":[{"iso":"eng"}],"type":"conference","year":"2021","citation":{"short":"A.F. Firmansyah, D. Moussallem, A.-C. Ngonga Ngomo, in: Proceedings of the 11th on Knowledge Capture Conference, ACM, Virtual Event, USA, 2021, pp. 73–80.","ieee":"A. F. Firmansyah, D. Moussallem, and A.-C. Ngonga Ngomo, “GATES: Using Graph Attention Networks for Entity Summarization,” in Proceedings of the 11th on Knowledge Capture Conference, 2021, pp. 73–80, doi: 10.1145/3460210.3493574.","ama":"Firmansyah AF, Moussallem D, Ngonga Ngomo A-C. GATES: Using Graph Attention Networks for Entity Summarization. In: Proceedings of the 11th on Knowledge Capture Conference. ACM; 2021:73–80. doi:10.1145/3460210.3493574","apa":"Firmansyah, A. F., Moussallem, D., & Ngonga Ngomo, A.-C. (2021). GATES: Using Graph Attention Networks for Entity Summarization. Proceedings of the 11th on Knowledge Capture Conference, 73–80. https://doi.org/10.1145/3460210.3493574","chicago":"Firmansyah, Asep Fajar, Diego Moussallem, and Axel-Cyrille Ngonga Ngomo. “GATES: Using Graph Attention Networks for Entity Summarization.” In Proceedings of the 11th on Knowledge Capture Conference, 73–80. Virtual Event, USA: ACM, 2021. https://doi.org/10.1145/3460210.3493574.","bibtex":"@inproceedings{Firmansyah_Moussallem_Ngonga Ngomo_2021, place={Virtual Event, USA}, title={GATES: Using Graph Attention Networks for Entity Summarization}, DOI={10.1145/3460210.3493574}, booktitle={Proceedings of the 11th on Knowledge Capture Conference}, publisher={ACM}, author={Firmansyah, Asep Fajar and Moussallem, Diego and Ngonga Ngomo, Axel-Cyrille}, year={2021}, pages={73–80} }","mla":"Firmansyah, Asep Fajar, et al. “GATES: Using Graph Attention Networks for Entity Summarization.” Proceedings of the 11th on Knowledge Capture Conference, ACM, 2021, pp. 73–80, doi:10.1145/3460210.3493574."},"page":"73–80","doi":"10.1145/3460210.3493574","_id":"29486","date_updated":"2022-01-20T09:03:38Z","status":"public","date_created":"2022-01-20T08:37:12Z","publication_status":"published","publication_identifier":{"isbn":["978-1-4503-8457-5"]},"publisher":"ACM","author":[{"last_name":"Firmansyah","id":"76787","first_name":"Asep Fajar","full_name":"Firmansyah, Asep Fajar"},{"id":"71635","last_name":"Moussallem","full_name":"Moussallem, Diego","first_name":"Diego"},{"full_name":"Ngonga Ngomo, Axel-Cyrille","first_name":"Axel-Cyrille","id":"65716","last_name":"Ngonga Ngomo"}],"department":[{"_id":"574"}],"publication":"Proceedings of the 11th on Knowledge Capture Conference","user_id":"76787","title":"GATES: Using Graph Attention Networks for Entity Summarization","place":"Virtual Event, USA"}]