RDF & Chatbots

The Inextricable Link Between RDF and Chatbots: How Resource Description Framework Empowers Conversational AI

RDF, or Resource Description Framework, is a standard for representing information about resources on the web in a structured way. It is based on the idea of representing data in the form of subject-predicate-object triples, where the subject represents the resource being described, the predicate represents the property or relationship being described, and the object represents the value of the property or the resource related to the subject.

RDF is commonly used as a key enabling technology in the development of chatbots. By providing a flexible yet structured format for representing knowledge, RDF empowers chatbots with several critical capabilities:

  1. Linking to Knowledge Graphs

One of the main advantages of RDF for chatbots is its ability to integrate data from diverse sources into unified knowledge graphs. Major knowledge bases like Wikidata and DBpedia publish their structured data as RDF, allowing this data to be queried and incorporated by RDF-based chatbots. Bringing in such broad background knowledge enables more intelligent and meaningful dialog.

  1. Reasoning Over Knowledge Bases

A key capability that RDF enables for chatbots is the ability to logically reason over knowledge bases to infer new information. Using ontology languages like RDFS and OWL layered over RDF data, chatbots can answer questions that are not directly asserted in their knowledge bases but derived through chains of reasoning. For instance, a tourism chatbot could use accommodation RDF data annotated with ontologies to recommend lodging options meeting logical constraints in visitor queries.

  1. Multi-Platform Data Integration

The flexibility of RDF as a data model facilitates aggregating diverse data under one roof for chatbots. RDF’s graph structure is amenable to integrating IoT sensor streams, database tables, spreadsheets, JSON objects, and more. Microsoft researchers demonstrated an RDF platform ingesting myriad transport data that intelligently plans multi-modal trips via conversational interaction. Such flexibility helps chatbots scale.

  1. Conversational Contextualization

A major limit of chatbots is their lack of understanding context. Labeling conversation data like user profiles and dialog sessions using semantic RDF can help chatbots track context. Software company Expert System introduced a RDF-based chatbot that represents contextual session data to have meaningful, personalized dialogs spanning multiple turns. Such context-awareness moves chatbots toward human-like conversation.

In summary, RDF provides the connective fabric allowing chatbots to interoperate with external knowledge, reason internally, unify decentralized data, and track contextual dialogue. While not sufficient by itself for conversational AI, RDF can be considered a foundational technology for enriching chatbots with capabilities such as contextual understanding that bring them closer to human-level intelligence. When woven together with other semantics-supplying technologies like ontologies and natural language processing, RDF delivers more capable conversational experiences




See also:

100 Best AI & NLP Resources: RDFSPARQL & Chatbots 2018

  • Achichi, M., Lisena, P., Todorov, K., Troncy, R., & others. (2018). DOREMUS: A graph of linked musical works. In International Semantic Web Conference. Springer.
  • Arkoudas, K., & Yahya, M. (2018). Auto-completion for Question Answering Systems at Bloomberg. In The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval. ACM.
  • Athreya, R. G. (2018). Template-Based Question Answering over Linked Data Using Recursive Neural Networks. ProQuest Dissertations Publishing.
  • Athreya, R. G., Ngonga Ngomo, A. C., & Usbeck, R. (2018). Enhancing community interactions with data-driven chatbots–The DBpedia chatbot. In Companion Proceedings of the Web Conference 2018 (pp. 943-949). International World Wide Web Conferences Steering Committee.
  • Augello, A., Pilato, G., Vassallo, G., & Gaglio, S. (2018). Sub-symbolic semantic layer in cyc for intuitive chat-bots. In International Conference on Human-Computer Interaction. Springer.
  • Augello, A., Pilato, G., Vassallo, G., Gaglio, S., & others. (2018). Interaction Capabilities of a Robotic Receptionist. In International Conference on Practical Applications of Agents and Multi-Agent Systems. Springer.
  • Bahrami, K., Daemi, B., & Abedi, M. (2018). Distributed E-learning Based on SOA. InTechOpen.
  • Balci, B. T., Simsek, U., Kärle, E., & Fensel, D. (2018). Analysis of Schema.org Usage in the Tourism Domain. arXiv preprint arXiv:1802.05948.
  • Barisevicius, G., Coste, M., Geleta, D., Juric, D., & others. (2018). Supporting Digital Healthcare Services Using Semantic Web Technologies. In International Semantic Web Conference. Springer
  • Beck, M., Dumpert, F., & Feuerhake, J. (2018). Machine Learning in Official Statistics. arXiv preprint arXiv:1812.10422.
  • Bhullar, R., Gibeau, E., Robertson, D., Zhan, M., & Zhang, W. (2018). Financial Literacy: The Future of Financial Wellness at UBC. University of British Columbia.
  • Bouziane, A., Bouchiha, D., Doumi, N., & Malki, M. (2018). Toward An Arabic Question Answering System Over Linked Data. ResearchGate.
  • Caldarola, E. G., Modoni, G. E., & Sacco, M. (2018). ManuLearning: A Knowledge-Based System to Enable the Continuous Training of Workers in the Manufacturing Field. International Association for the Development of the Information Society. ERIC.
  • Carignan, B. (2018). Improving Dialog Systems Using Knowledge Graph Embeddings. Carleton University.
  • Chorowski, J., Lancucki, A., Malik, S., & others. (2018). A Talker Ensemble: The University of Wroclaw’s Entry to the NIPS 2017 Conversational Intelligence Challenge. In The NIPS’17 Competition. Springer.
  • Ciolacu, M., Tehrani, A. F., Binder, L., & others. (2018). Education 4.0-Artificial Intelligence Assisted Higher Education: Early recognition System with Machine Learning to support Students’ Success. In 2018 IEEE 24th International Conference on Parallel and Distributed Systems. IEEE.
  • Clarizia, F., Colace, F., Lombardi, M., & others. (2018). A Context Aware Recommender System for Digital Storytelling. In 2018 IEEE 32nd International Conference on Advanced Information Networking and Applications. IEEE.
  • Cochez, M., Ristoski, P., Ponzetto, S. P., & Paulheim, H. (2018). Biased graph walks for RDF graph embeddings. In International Semantic Web Conference. Springer.
  • Coronado, M., Iglesias, C. A., Carrera, Á., & others. (2018). A cognitive assistant for learning java featuring social dialogue. International Journal of Human-Computer Studies.
  • Cunningham, A., James, A. D., Taylor, P., & others. (2018). Disruptive Technologies & Legal Service Provision in the UK: A Preliminary Study. SSRN.
  • de Araujo, D. A., Hentges, A. R., & Rigo, S. (2018). A Linguistic Approach to Short Query and Answer Systems. In Proceedings of the XIV Brazilian Symposium on Information Systems. ACM.
  • Diefenbach, D., Both, A., Singh, K., & Maret, P. (2018). Towards a question answering system over the Semantic Web. Semantic Web Journal.
  • Dragoni, M., Bailoni, T., Maimone, R., Guerini, M., & others. (2018). PerKApp: A general purpose persuasion architecture for healthy lifestyles. Journal of Biomedical Informatics.
  • El Kaed, C., Ponnouradjane, A., & others. (2018). A Semantic Based Multi-Platform IoT Integration Approach from Sensors to Chatbots. In 2018 Global Internet of Things Summit. IEEE.
  • Fan, Z., Wei, Z., Li, P., Lan, Y., & Huang, X. (2018). A Question Type Driven Framework to Diversify Visual Question Generation. In IJCAI.
  • Fulda, N., Etchart, T., Myers, W., Ricks, D., Brown, Z., & others. (2018). BYU-EVE: Mixed Initiative Dialog via Structured Knowledge Graph Traversal and Conversational Scaffolding. In Alexa Prize Proceedings.
  • Gapanyuk, Y., Chernobrovkin, S., Leontiev, A., Latkin, I., & others. (2018). The Hybrid Chatbot System Combining Q&A and Knowledgebase Approaches. ceur-ws.org.
  • Gkiokas, A., & Cristea, A. I. (2018). Cognitive agents and machine learning by example: Representation with conceptual graphs. Computational Intelligence.
  • Granell, C., Bhattacharya, D., & others. (2018). GEO-C: Enabling Open Cities And The Open City Toolkit. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences.
  • Huemer, C., Kleedorfer, F., Suda, F., & Stolze, M. (2018). Hailing a Taxi on the Web of Needs. In Proceedings of the Posters and Demos Track of the 14th International Conference on Semantic Systems. CEUR Workshop Proceedings.
  • Jokinen, K. (2018). Dialogue Models for Socially Intelligent Robots. In International Conference on Social Robotics. Springer.
  • Kärle, E., & Fensel, D. (2018). Heuristics for publishing dynamic content as structured data with schema.org. arXiv preprint arXiv:1808.06012.
  • Kärle, E., Simsek, U., Panasiuk, O., & Fensel, D. (2018). Building an ecosystem for the tyrolean tourism knowledge graph. In International Conference on Knowledge Engineering and Knowledge Management. Springer.
  • Kleedorfer, F., Suda, F., Stolze, M., & Huemer, C. (2018). Hailing a Taxi on the Web of Needs. In Proceedings of the Posters and Demos Track of the 14th International Conference on Semantic Systems. CEUR Workshop Proceedings.
  • Lafia, S., Turner, A., & Kuhn, W. (2018). Improving Discovery of Open Civic Data. In 10th International Conference on Geographic Information Science. Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik.
  • Li, Y., & Rafiei, D. (2018). Natural Language Data Management and Interfaces. Morgan & Claypool Publishers.
  • Maimone, R., Guerini, M., Dragoni, M., Bailoni, T., & others. (2018). PerKApp: A general purpose persuasion architecture for healthy lifestyles. Journal of Biomedical Informatics.
  • Maus, H., Jilek, C., & Schwarz, S. (2018). Remembering and forgetting for personal preservation. In Personal Multimedia Preservation. Springer.
  • Mensa, E., Porporato, A., & Radicioni, D. P. (2018). Grasping metaphors: Lexical semantics in metaphor analysis. In European Semantic Web Conference. Springer.
  • Modrzejewski, M., & Rokita, P. (2018). Critical Analysis of Conversational Agent Technology for Intelligent Customer Support and Proposition of a New Solution. In International Conference on Artificial Intelligence and Soft Computing. Springer.
  • Morisio, M., & Mensio, M. (2018). Deep Semantic Learning for Conversational Agents. Politecnico di Torino.
  • Neumann, A., Laranjeiro, N., & Madeira, H. (2018). An analysis of public rest web service APIs. IEEE Transactions on Services Computing.
  • Niebler, T. (2018). Extracting and Learning Semantics from Social Web Data. University of Würzburg.
  • Nuccio, C., Augello, A., Gaglio, S., & Pilato, G. (2018). Interaction Capabilities of a Robotic Receptionist. In International Conference on Human-Computer Interaction. Springer.
  • Okwunma, N. E. (2018). Automatic Comprehension of Customer Queries for Feedback Generation. University of the Witwatersrand.
  • Panesar, K. (2018). How can one evaluate a conversational software agent framework? York St John University.
  • Panesar, K. (2018). Motivating a linguistically orientated model for a conversational software agent. York St John University.
  • Papangelis, A., Papadakos, P., Stylianou, Y., & Karkaletsis, V. (2018). Spoken Dialogue for Information Navigation. In Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue. Association for Computational Linguistics.
  • Sangroya, A., Anantaram, C., Saini, P., & Rawat, M. (2018). Automatic Extraction of Domain Specific Latent Beliefs in Customer Complaints to Help Tailor Chatbots. In Workshops at the Thirty-Second AAAI Conference on Artificial Intelligence. Retrieved from aaai.org.
  • Sheth, A. P., Yip, H. Y., Jaimini, U., Kadariya, D., & others. (2018). Augmented personalized health: Using semantically integrated multimodal data for patient empowered health management strategies. Retrieved from corescholar.libraries.wright.edu.
  • Simsek, U., & Fensel, D. (2018). Now We Are Talking! Flexible and Open Goal-Oriented Dialogue Systems for Accessing Touristic Services. e-Review of Tourism Research, 9(2), 126-133.
  • Tambouris, E. (2018). Using Chatbots and Semantics to Exploit Public Sector Information. In EGOV-CeDEM-ePart 2018. Retrieved from books.google.com.
  • Tanon, T. P., de Assuncao, M. D., Caron, E., & others. (2018). Demoing platypus–A multilingual question answering platform for wikidata. In European Semantic Web Conference. Retrieved from Springer.
  • Vossen, P., Baez, S., Bajcetic, L., & others. (2018). Leolani: a reference machine with a theory of mind for social communication. In International Conference on Text, Speech, and Dialogue. Retrieved from Springer.