{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:41:10Z","timestamp":1760244070524,"version":"build-2065373602"},"reference-count":44,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2022,11,15]],"date-time":"2022-11-15T00:00:00Z","timestamp":1668470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006595","name":"Ministry of Research, Innovation and Digitization","doi-asserted-by":"publisher","award":["PN-III-P2-2.1-SOL-2021-2-0223"],"award-info":[{"award-number":["PN-III-P2-2.1-SOL-2021-2-0223"]}],"id":[{"id":"10.13039\/501100006595","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>We live in an era where time is a scarce resource and people enjoy the benefits of technological innovations to ensure prompt and smooth access to information required for our daily activities. In this context, conversational agents start to play a remarkable role by mediating the interaction between humans and computers in specific contexts. However, they turn out to be laborious for cross-domain use cases or when they are expected to automatically adapt throughout user dialogues. This paper introduces a method to plug in multiple domains of knowledge for a conversational agent localized in Romanian in order to facilitate the extension of the agent\u2019s area of expertise. Furthermore, the agent is intended to become more domain-aware and learn new information dynamically from user conversations by means of a knowledge graph acting as a network of facts and information. We ensure high capabilities for natural language understanding by proposing a novel architecture that takes into account RoBERT-contextualized embeddings alongside syntactic features. Our approach leads to improved intent classification performance (F1 score = 82.6) when compared with a basic pipeline relying only on features extracted from the agent\u2019s training data. Moreover, the proposed RDF knowledge representation is confirmed to provide flexibility in storing and retrieving natural language entities, values, and factoid relations between them in the context of each microworld.<\/jats:p>","DOI":"10.3390\/info13110539","type":"journal-article","created":{"date-parts":[[2022,11,15]],"date-time":"2022-11-15T02:32:16Z","timestamp":1668479536000},"page":"539","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Microworld Conversational Agent with RDF Knowledge Graph Integration"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8473-8456","authenticated-orcid":false,"given":"Gabriel","family":"Boroghina","sequence":"first","affiliation":[{"name":"Computer Science & Engineering Department, University Politehnica of Bucharest, 313 Splaiul Independentei, 060042 Bucharest, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7994-9950","authenticated-orcid":false,"given":"Dragos Georgian","family":"Corlatescu","sequence":"additional","affiliation":[{"name":"Computer Science & Engineering Department, University Politehnica of Bucharest, 313 Splaiul Independentei, 060042 Bucharest, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4815-9227","authenticated-orcid":false,"given":"Mihai","family":"Dascalu","sequence":"additional","affiliation":[{"name":"Computer Science & Engineering Department, University Politehnica of Bucharest, 313 Splaiul Independentei, 060042 Bucharest, Romania"},{"name":"Academy of Romanian Scientists, Str. Ilfov, Nr. 3, 050044 Bucharest, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,11,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.eswa.2019.03.054","article-title":"Survey of conversational agents in health","volume":"129","author":"Montenegro","year":"2019","journal-title":"Expert Syst. Appl."},{"key":"ref_2","unstructured":"Boroghina, G., Corlatescu, D.G., and Dascalu, M. (2020, January 22\u201323). Conversational Agent in Romanian for Storing User Information in a Knowledge Graph. Proceedings of the 17th International Conference on Human-Computer Interaction, RoCHI 2020, Sibiu (Virtual), Romania."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Adewumi, T., Liwicki, F., and Liwicki, M. (2022). State-of-the-Art in Open-Domain Conversational AI: A Survey. Information, 13.","DOI":"10.20944\/preprints202205.0016.v1"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Caldarini, G., Jaf, S., and McGarry, K. (2022). A Literature Survey of Recent Advances in Chatbots. Information, 13.","DOI":"10.3390\/info13010041"},{"key":"ref_5","first-page":"1","article-title":"RDF\/XML syntax specification (revised)","volume":"10","author":"Beckett","year":"2004","journal-title":"W3C Recomm."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"149220","DOI":"10.1109\/ACCESS.2020.3016142","article-title":"KBot: A Knowledge graph based chatBot for natural language understanding over linked data","volume":"8","author":"Jiang","year":"2020","journal-title":"IEEE Access"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Gerontas, A., Zeginis, D., Promikyridis, R., Andro\u0161, M., Tambouris, E., Cipan, V., and Tarabanis, K. (2022). Enhancing Core Public Service Vocabulary to Enable Public Service Personalization. Information, 13.","DOI":"10.3390\/info13050225"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Promikyridis, R., and Tambouris, E. (2022, January 15\u201317). Using Knowledge Graphs to provide public service information. Proceedings of the DG. O 2022: The 23rd Annual International Conference on Digital Government Research, Virtual.","DOI":"10.1145\/3543434.3543585"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Bao, Q., Ni, L., and Liu, J. (2020, January 3\u20137). HHH: An Online Medical Chatbot System based on Knowledge Graph and Hierarchical Bi-Directional Attention. Proceedings of the Australasian Computer Science Week, ACSW 2020, Melbourne, VIC, Australia.","DOI":"10.1145\/3373017.3373049"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Ni, P., Okhrati, R., Guan, S., and Chang, V. (2022). Knowledge Graph and Deep Learning-based Text-to-GraphQL Model for Intelligent Medical Consultation Chatbot. Inf. Syst. Front., 1\u201320.","DOI":"10.1007\/s10796-022-10295-0"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"715","DOI":"10.1016\/j.future.2021.06.001","article-title":"Representing emotions with knowledge graphs for movie recommendations","volume":"125","author":"Breitfuss","year":"2021","journal-title":"Future Gener. Comput. Syst."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Varitimiadis, S., Kotis, K., Pittou, D., and Konstantakis, G. (2021). Graph-Based Conversational AI: Towards a Distributed and Collaborative Multi-Chatbot Approach for Museums. Appl. Sci., 11.","DOI":"10.3390\/app11199160"},{"key":"ref_13","first-page":"281","article-title":"\u201cTalking\u201d Triples to Museum Chatbots","volume":"Volume 12215","author":"Rauterberg","year":"2020","journal-title":"Proceedings of the Culture and Computing\u20148th International Conference, C&C 2020, Held as Part of the 22nd HCI International Conference, HCII 2020"},{"key":"ref_14","unstructured":"Github (2022, May 02). Conversational Agent Project. Available online: https:\/\/github.com\/readerbench\/conversational-agent."},{"key":"ref_15","unstructured":"HuggingFace (2022, February 01). HuggingFace. Available online: https:\/\/huggingface.co\/."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Hardalov, M., Koychev, I., and Nakov, P. (2019). Machine Reading Comprehension for Answer Re-Ranking in Customer Support Chatbots. Information, 10.","DOI":"10.3390\/info10030082"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"da Silva, D.A., Louro, H.D.B., Goncalves, G.S., Marques, J.C., Dias, L.A.V., da Cunha, A.M., and Tasinaffo, P.M. (2021). Could a Conversational AI Identify Offensive Language?. Information, 12.","DOI":"10.3390\/info12100418"},{"key":"ref_18","unstructured":"Bocklisch, T., Faulkner, J., Pawlowski, N., and Nichol, A. (2017). Rasa: Open source language understanding and dialogue management. arXiv."},{"key":"ref_19","unstructured":"(2022, March 01). Wit.ai. Wit.ai. Available online: https:\/\/wit.ai\/."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Mikolov, T., Karafi\u00e1t, M., Burget, L., \u010cernock\u00fd, J., and Khudanpur, S. (2010, January 26\u201330). Recurrent neural network based language model. Proceedings of the Eleventh Annual Conference of the International Speech Communication Association, Makuhari, Japan.","DOI":"10.21437\/Interspeech.2010-343"},{"key":"ref_21","unstructured":"Sutskever, I., Vinyals, O., and Le, Q.V. (2014, January 8\u201313). Sequence to sequence learning with neural networks. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada."},{"key":"ref_22","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2017, January 4\u20139). Attention is all you need. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_23","unstructured":"Bunk, T., Varshneya, D., Vlasov, V., and Nichol, A. (2020). DIET: Lightweight Language Understanding for Dialogue Systems. arXiv."},{"key":"ref_24","unstructured":"Lafferty, J., McCallum, A., and Pereira, F.C. (July, January 8). Conditional random fields: Probabilistic models for segmenting and labeling sequence data. Proceedings of the ICML, Williamstown, MA, USA."},{"key":"ref_25","unstructured":"Devlin, J., Chang, M.W., Lee, K., and Toutanova, K. (2019, January 2\u20137). BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Minneapolis, MA, USA."},{"key":"ref_26","first-page":"411","article-title":"spacy 2: Natural language understanding with bloom embeddings","volume":"7","author":"Honnibal","year":"2017","journal-title":"Convolutional Neural Netw. Increm. Parsing"},{"key":"ref_27","first-page":"20","article-title":"SQL and NoSQL databases","volume":"2","author":"Sharma","year":"2012","journal-title":"Int. J. Adv. Res. Comput. Sci. Softw. Eng."},{"key":"ref_28","first-page":"29","article-title":"Knowledge graphs: New directions for knowledge representation on the semantic web (dagstuhl seminar 18371)","volume":"8","author":"Bonatti","year":"2019","journal-title":"Dagstuhl Rep."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1038\/scientificamerican0501-34","article-title":"The semantic web","volume":"284","author":"Hendler","year":"2001","journal-title":"Sci. Am."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Horrocks, I., and Patel-Schneider, P.F. (2011). Knowledge representation and reasoning on the semantic web: Owl. Handbook of Semantic Web Technologies, Springer. Chapter 9.","DOI":"10.1007\/978-3-540-92913-0_9"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Smith, E.M., Williamson, M., Shuster, K., Weston, J., and Boureau, Y.L. (2020, January 5\u201310). Can you put it all together: Evaluating conversational agents\u2019 ability to blend skills. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020). Association for Computational Linguistics, Seattle, WA, USA (Virtual).","DOI":"10.18653\/v1\/2020.acl-main.183"},{"key":"ref_32","unstructured":"Nenciu, B., Corlatescu, D.G., and Dascalu, M. (2020, January 22\u201323). RASA Conversational Agent in Romanian for Predefined Microworlds. Proceedings of the RoCHI-International Conference On Human-Computer Interaction, Sibiu, Romania (Virtual)."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1145\/2629489","article-title":"Wikidata: A free collaborative knowledgebase","volume":"57","year":"2014","journal-title":"Commun. ACM"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Auer, S., Bizer, C., Kobilarov, G., Lehmann, J., Cyganiak, R., and Ives, Z. (2007). Dbpedia: A nucleus for a web of open data. The Semantic Web, Springer.","DOI":"10.1007\/978-3-540-76298-0_52"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1620585.1620589","article-title":"Semantics and complexity of SPARQL","volume":"34","author":"Arenas","year":"2009","journal-title":"Acm Trans. Database Syst. (TODS)"},{"key":"ref_36","unstructured":"(2022, February 20). Explosion. spaCy Romanian Models. Available online: https:\/\/spacy.io\/models\/ro."},{"key":"ref_37","unstructured":"Barbu Mititelu, V., Ion, R., Simionescu, R., Irimia, E., and Perez, C.A. (October, January 29). The romanian treebank annotated according to universal dependencies. Proceedings of the Tenth International Conference on Natural Language Processing (hrtal2016), Dubrovnik, Croatia."},{"key":"ref_38","unstructured":"Contributors, U.D. (2021, July 14). Universal Dependencies Corpora. 2014\u20132021. Available online: http:\/\/universaldependencies.org\/u\/dep\/all.html."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Masala, M., Ruseti, S., and Dascalu, M. (2020, January 8\u201313). RoBERT\u2014A Romanian BERT Model. Proceedings of the 28th International Committee on Computational Linguistics (COLING), Barcelona, Spain.","DOI":"10.18653\/v1\/2020.coling-main.581"},{"key":"ref_40","unstructured":"Avram, A.M., Catrina, D., Cercel, D.C., Dasc\u0103lu, M., Rebedea, T., P\u0103i\u015f, V., and Tufi\u015f, D. (2021). Distilling the Knowledge of Romanian BERTs Using Multiple Teachers. arXiv."},{"key":"ref_41","unstructured":"B\u0103rbu\u021b\u0103, I., Cical\u0103, A., Constantinovici, E., Cotelnic, T., and D\u00eerul, A. (2000). Gramatica Uzual\u0103 a Limbii Rom\u00e2ne, Litera."},{"key":"ref_42","unstructured":"G\u00fcting, R.H. (1994, January 12\u201315). GraphDB: Modeling and querying graphs in databases. Proceedings of the VLDB, Citeseer, Santiago de Chile, Chile."},{"key":"ref_43","unstructured":"(2022, May 01). Eclipse Foundation. RDF4J. Available online: https:\/\/rdf4j.org\/."},{"key":"ref_44","unstructured":"Ontotext (2022, May 02).  LoadRDF. Available online: https:\/\/www.graphdb.ontotext.com\/documentation\/7.2\/standard\/loadrdf-tool.html."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/13\/11\/539\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:18:11Z","timestamp":1760145491000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/13\/11\/539"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,15]]},"references-count":44,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2022,11]]}},"alternative-id":["info13110539"],"URL":"https:\/\/doi.org\/10.3390\/info13110539","relation":{},"ISSN":["2078-2489"],"issn-type":[{"type":"electronic","value":"2078-2489"}],"subject":[],"published":{"date-parts":[[2022,11,15]]}}}