{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:20:28Z","timestamp":1777890028420,"version":"3.51.4"},"reference-count":40,"publisher":"SAGE Publications","issue":"5","license":[{"start":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T00:00:00Z","timestamp":1728432000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["SW"],"published-print":{"date-parts":[[2024,10,9]]},"abstract":"<jats:p>There are two main limitations in most of the existing Knowledge Graph Question Answering (KGQA) algorithms. First, the approaches depend heavily on the structure and cannot be easily adapted to other KGs. Second, the availability and amount of additional domain-specific data in structured or unstructured formats has also proven to be critical in many of these systems. Such dependencies limit the applicability of KGQA systems and make their adoption difficult. A\u00a0novel algorithm is proposed, MuHeQA, that alleviates both limitations by retrieving the answer from textual content automatically generated from KGs instead of queries over them. This new approach (1) works on one or several KGs simultaneously, (2) does not require training data what makes it is domain-independent, (3) enables the combination of knowledge graphs with unstructured information sources to build the answer, and (4) reduces the dependency on the underlying schema since it does not navigate through structured content but only reads property values. MuHeQA extracts answers from textual summaries created by combining information related to the question from multiple knowledge bases, be them structured or not. Experiments over Wikidata and DBpedia show that our approach achieves comparable performance to other approaches in single-fact questions while being domain and KG independent. Results raise important questions for future work about how the textual content that can be created from knowledge graphs enables answer extraction.<\/jats:p>","DOI":"10.3233\/sw-233379","type":"journal-article","created":{"date-parts":[[2023,6,9]],"date-time":"2023-06-09T10:36:06Z","timestamp":1686306966000},"page":"1547-1561","source":"Crossref","is-referenced-by-count":2,"title":["MuHeQA: Zero-shot question answering over multiple and heterogeneous knowledge bases"],"prefix":"10.1177","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2753-9917","authenticated-orcid":false,"given":"Carlos","family":"Badenes-Olmedo","sequence":"first","affiliation":[{"name":"Ontology Engineering Group, Universidad Polit\u00e9cnica de Madrid, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9260-0753","authenticated-orcid":false,"given":"Oscar","family":"Corcho","sequence":"additional","affiliation":[{"name":"Ontology Engineering Group, Universidad Polit\u00e9cnica de Madrid, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"key":"10.3233\/SW-233379_ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052583"},{"key":"10.3233\/SW-233379_ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.278"},{"key":"10.3233\/SW-233379_ref3","unstructured":"A.\u00a0Akbik, D.\u00a0Blythe and R.\u00a0Vollgraf, Contextual string embeddings for sequence labeling, in: COLING 2018, 27th International Conference on Computational Linguistics, Association for Computational Linguistics, 2018, pp.\u00a01638\u20131649."},{"key":"10.3233\/SW-233379_ref4","unstructured":"M.\u00a0Azmy, P.\u00a0Shi, J.\u00a0Lin and I.\u00a0Ilyas, Farewell Freebase: Migrating the SimpleQuestions dataset to DBpedia, in: Proceedings of the 27th International Conference on Computational Linguistics, Association for Computational Linguistics, 2018, pp.\u00a02093\u20132103."},{"key":"10.3233\/SW-233379_ref5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2012.01953"},{"key":"10.3233\/SW-233379_ref6","unstructured":"J.\u00a0Berant, A.\u00a0Chou, R.\u00a0Frostig and P.\u00a0Liang, Semantic parsing on freebase from question-answer pairs, in: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, 2013, pp.\u00a01533\u20131544."},{"key":"10.3233\/SW-233379_ref7","unstructured":"A.\u00a0Bordes, N.\u00a0Usunier, S.\u00a0Chopra and J.\u00a0Weston, Large-scale simple question answering with memory networks, Computing Research Repository (2015)."},{"key":"10.3233\/SW-233379_ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"10.3233\/SW-233379_ref9","unstructured":"D.\u00a0Diefenbach, T.P.\u00a0Tanon, K.\u00a0Singh and P.\u00a0Maret, Question answering benchmarks for Wikidata, in: Proceedings of the ISWC 2017 Posters & Demonstrations and Industry Tracks Co-Located with 16th International Semantic Web Conference, 2017."},{"key":"10.3233\/SW-233379_ref10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2107.02865"},{"key":"10.3233\/SW-233379_ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30796-7_5"},{"key":"10.3233\/SW-233379_ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-49461-2_31"},{"key":"10.3233\/SW-233379_ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"10.3233\/SW-233379_ref14","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/611"},{"key":"10.3233\/SW-233379_ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.91"},{"key":"10.3233\/SW-233379_ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"10.3233\/SW-233379_ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1484"},{"key":"10.3233\/SW-233379_ref18","unstructured":"P.\u00a0Lewis, E.\u00a0Perez, A.\u00a0Piktus, F.\u00a0Petroni, V.\u00a0Karpukhin, N.\u00a0Goyal, H.\u00a0K\u00fcttler, M.\u00a0Lewis, W.-t.\u00a0Yih, T.\u00a0Rockt\u00e4schel, S.\u00a0Riedel and D.\u00a0Kiela, Retrieval-augmented generation for knowledge-intensive NLP tasks, in: Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS\u201920, Curran Associates Inc., 2020. ISBN 9781713829546."},{"key":"10.3233\/SW-233379_ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2063518.2063519"},{"key":"10.3233\/SW-233379_ref20","doi-asserted-by":"crossref","unstructured":"S.\u00a0Neelam, U.\u00a0Sharma, H.\u00a0Karanam, S.\u00a0Ikbal, P.\u00a0Kapanipathi, I.\u00a0Abdelaziz, N.\u00a0Mihindukulasooriya, Y.-S.\u00a0Lee, S.\u00a0Srivastava, C.\u00a0Pendus, S.\u00a0Dana, D.\u00a0Garg, A.\u00a0Fokoue, G.P.S.\u00a0Bhargav, D.\u00a0Khandelwal, S.\u00a0Ravishankar, S.\u00a0Gurajada, M.\u00a0Chang, R.\u00a0Uceda-Sosa, S.\u00a0Roukos, A.\u00a0Gray, G.\u00a0Lima, R.\u00a0Riegel, F.\u00a0Luus and L.V.\u00a0Subramaniam, SYGMA: A system for generalizable and modular question answering over knowledge bases, in: Findings of the Association for Computational Linguistics: EMNLP 2022, Association for Computational Linguistics, 2022, pp.\u00a03866\u20133879.","DOI":"10.18653\/v1\/2022.findings-emnlp.284"},{"key":"10.3233\/SW-233379_ref21","unstructured":"C.\u00a0Nikas, P.\u00a0Fafalios and Y.\u00a0Tzitzikas, Two-stage semantic answer type prediction for question answering using BERT and class-specificity rewarding, in: Proceedings of the SeMantic AnsweR Type Prediction Task (SMART) at ISWC 2020 Semantic Web Challenge Co-Located with the 19th International Semantic Web Conference (ISWC 2020), Virtual Conference, November 5th, 2020, CEUR Workshop Proceedings, CEUR-WS.org, 2020, pp.\u00a019\u201328."},{"key":"10.3233\/SW-233379_ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.115"},{"key":"10.3233\/SW-233379_ref23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1049\/sfw2.12028","article-title":"Systematic review of question answering over knowledge bases","author":"Pereira","year":"2022","journal-title":"IET Software"},{"key":"10.3233\/SW-233379_ref24","unstructured":"S.\u00a0Pramanik, J.\u00a0Alabi, R.S.\u00a0Roy and G.\u00a0Weikum, UNIQORN: Unified question answering over RDF knowledge graphs and natural language text, Computing Research Repository (2021)."},{"key":"10.3233\/SW-233379_ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"10.3233\/SW-233379_ref26","doi-asserted-by":"crossref","unstructured":"S.\u00a0Ravishankar, D.\u00a0Thai, I.\u00a0Abdelaziz, N.\u00a0Mihindukulasooriya, T.\u00a0Naseem, P.\u00a0Kapanipathi, G.\u00a0Rossiello and A.\u00a0Fokoue, A two-stage approach towards generalization in knowledge base question answering, in: Findings of the Association for Computational Linguistics: EMNLP 2022, Association for Computational Linguistics, 2022, pp.\u00a05571\u20135580.","DOI":"10.18653\/v1\/2022.findings-emnlp.408"},{"key":"10.3233\/SW-233379_ref27","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-022-04751-6"},{"key":"10.3233\/SW-233379_ref28","doi-asserted-by":"publisher","first-page":"3141","DOI":"10.1145\/3340531.3412777","article-title":"Falcon 2.0: An entity and relation linking tool over Wikidata","author":"Sakor","year":"2020","journal-title":"Association for Computing Machinery"},{"key":"10.3233\/SW-233379_ref29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2011.06993"},{"key":"10.3233\/SW-233379_ref30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/tacl_a_00530","article-title":"Improving the domain adaptation of retrieval augmented generation (RAG) models for open domain question answering","author":"Siriwardhana","year":"2023","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"10.3233\/SW-233379_ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1242"},{"key":"10.3233\/SW-233379_ref32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2106.00200"},{"key":"10.3233\/SW-233379_ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-2623"},{"key":"10.3233\/SW-233379_ref34","unstructured":"L.L.\u00a0Wang, K.\u00a0Lo, Y.\u00a0Chandrasekhar, R.\u00a0Reas, J.\u00a0Yang, D.\u00a0Burdick, D.\u00a0Eide, K.\u00a0Funk, Y.\u00a0Katsis, R.M.\u00a0Kinney, Y.\u00a0Li, Z.\u00a0Liu, W.\u00a0Merrill, P.\u00a0Mooney, D.A.\u00a0Murdick, D.\u00a0Rishi, J.\u00a0Sheehan, Z.\u00a0Shen, B.\u00a0Stilson, A.D.\u00a0Wade, K.\u00a0Wang, N.X.R.\u00a0Wang, C.\u00a0Wilhelm, B.\u00a0Xie, D.M.\u00a0Raymond, D.S.\u00a0Weld, O.\u00a0Etzioni and S.\u00a0Kohlmeier, CORD-19: The COVID-19 open research dataset, in: Proceedings of the 1st Workshop on NLP for COVID-19 at ACL 2020, Association for Computational Linguistics, 2020."},{"key":"10.3233\/SW-233379_ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.370"},{"key":"10.3233\/SW-233379_ref36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2009.12756"},{"key":"10.3233\/SW-233379_ref37","doi-asserted-by":"publisher","DOI":"10.3390\/info12070271"},{"key":"10.3233\/SW-233379_ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.465"},{"key":"10.3233\/SW-233379_ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331232"},{"key":"10.3233\/SW-233379_ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-84186-7_31"}],"container-title":["Semantic Web"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/SW-233379","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:27:01Z","timestamp":1777613221000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/SW-233379"}},"subtitle":[],"editor":[{"given":"Bo","family":"Fu","sequence":"additional","affiliation":[{"name":"California State University Long Beach, USA"}],"role":[{"role":"editor","vocabulary":"crossref"}]},{"given":"Patrick","family":"Lambrix","sequence":"additional","affiliation":[{"name":"Link\u00f6ping University and University of G\u00e4vle, Sweden"}],"role":[{"role":"editor","vocabulary":"crossref"}]},{"given":"Catia","family":"Pesquita","sequence":"additional","affiliation":[{"name":"LASIGE, Faculdade de Ci\u00eancias, Universidade de Lisboa, Portugal"}],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2024,10,9]]},"references-count":40,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.3233\/sw-233379","relation":{},"ISSN":["2210-4968","1570-0844"],"issn-type":[{"value":"2210-4968","type":"electronic"},{"value":"1570-0844","type":"print"}],"subject":[],"published":{"date-parts":[[2024,10,9]]}}}