Tutorial 1: Virtual Knowledge Graphs
Abstract: Recently, semantic technologies have been successfully deployed to overcome the typical difficulties in accessing and integrating data stored in different kinds of legacy sources. In particular, knowledge graphs are being used as a mechanism to provide a uniform representation of heterogeneous information. Such graphs represent data in the RDF format, which is complemented by an ontology and can be queried using the standard SPARQL language. The RDF graph is often obtained by materializing source data, following the traditional extract-transform-load workflow. Alternatively, the sources are declaratively mapped to the ontology, and the RDF graph is maintained virtual. In such an approach, usually called Virtual Knowledge Graphs (VKG), query answering is based on sophisticated query transformation techniques. In this workshop: (i) we provide a general introduction to relevant semantic technologies; (ii) we illustrate the principles underlying the VKG approach, providing insights into its theoretical foundations, and describing well-established algorithms, techniques, and tools; (iii) we discuss relevant use-cases using VKGs.
Bio: Diego Calvanese is a full professor at the Research Centre for Knowledge and Data (KRDB), Faculty of Computer Science, Free University of Bozen-Bolzano, where he teaches graduate and undergraduate courses on knowledge bases and databases, ontologies, theory of computing, and formal languages. He received a PhD from Sapienza University of Rome in 1996. His research interests include formalisms for knowledge representation and reasoning, ontology based data access and integration, description logics, Semantic Web, graph data management, data-aware process verification, and service modeling and synthesis. He has been actively involved in several national and international research projects in the above areas (including FP6-7603 TONES, FP7-257593 ACSI, FP7-318338 Optique). He is the author of more than 350 refereed publications, including ones in the most prestigious international journals and conferences in Databases and Artificial Intelligence, with almost 30000 citations and an h-index of 68, according to Google Scholar. He is one of the editors of the Description Logic Handbook. He has served in around 150 organization and program committee roles for international events, and he is an associate editor of Artificial Intelligence, JAIR, and a member of the editorial board of the Journal of Automated Reasoning. In 2012-2013 he has been a visiting researcher at the Technical University of Vienna as Pauli Fellow of the “Wolfgang Pauli Institute”. He has been the program chair of the 34th ACM Symposium on Principles of Database Systems (PODS 2015), the program co-chair of the 28th Description Logic Workshop (DL 2015), and the general chair of the 28th European Summer School in Logic, Language and Information (ESSLLI 2016). He has been nominated Fellow of the European Association for Artificial Intelligence (EurAI, formerly ECCAI) in 2015. Diego is one of the inventors of VKG approach and the initiator of Ontop. He is a Co-Founder and the president of the Ontopic startup.
Bio: Guohui Xiao is an assistant professor at the KRDB Research Centre for Knowledge and Data, Faculty of Computer Science, Free University of Bozen-Bolzano. He received his Bachelor and Master degrees from Peking University, respectively in 2007 and 2010, and his PhD degree in computer science from Vienna University of Technology, Austria, in 2014. His main research interests include knowledge representation, description logics, semantic Web, database theory and virtual knowledge graphs. In these areas, he authored more than 90 publications, including top-tier international journals and conferences, such as JAIR, SWJ, JWS, IJCAI, AAAI, KR, ICDT, EDBT, ISWC, CIKM, and ECAI, with almost 1600 citations and an h-index of 20. He received the Semantic Web Journal 2016 Outstanding Paper Award for the work of Ontop, the Best In-Use Paper in The 16th International Semantic Web Conference (ISWC’17), and the Best Paper in he 17th Int. Conf. of the Italian Association for Artificial Intelligence (AIxIA 2018). He is currently leading the development of the Ontop Virtual Knowledge Graph platform. He is a Co-Founder and Chief Scientist of the Ontopic startup.
Tutorial 2: Building the Medical Knowledge Graph for Smart Clinical Decision Support
Abstract: Doctors need to make clinical decisions during their daily work. The clinical decision making scenario could be divided into the following two: (1) during their point-of-care, doctors have to determine the potential diagnosis and give the treatment given the symptom description from the patient; (2) for the complicated cases, doctors have to search the l iterations to help the decision. In addition, doctors may need to survey the literatures to identify the research topic. It requires the medical knowledge to make the above decision. However, Healthcare area has huge amount of knowledge，and it has to be updated periodically. Therefore, the intelligent clinical decision support tool is indispensable. Medical knowledge graph is the foundation of the smart tool. The medical knowledge graph helps to represent the unstructured medical knowledge into the format that could be used by machines to reason on it. In this talk, I will share how we build the medical knowledge graph in PingAn. Then, I will introduce how we use the medical knowledge graph to support the intelligent tools.
Bio: Yuan Ni, Ph.D. Head of Medical Natural Language Processing Department, PingAn Health Tech. Dr Ni got her bachelor degree from Computer science department, Fudan University at 2003 and her Ph.D. degree from National University of Singapore, School of Computing at 2007. Before joining PingAn Health Tech, she was the a senior research staff member in IBM Research, China. Her research expertise includes natural language processing, machine learning and semantic technology areas. In IBM, she has taken part in the Watson for Jeopardy! Project and Debater Project from 2008 to 2013. After that, she has worked on applying the technologies into the Healthcare industry. Dr Ni has published more than 20 papers in the top conferences including SIGMOD, ICDE, ISWC, WSDM, CIKM, MEDINFO, MIE and etc., and she has worked as the program committee for top conferences such as CIKM, ISWC, CSWC, APWeb and etc.
Tutorial 3: The Construction of Open-domain Knowledge Graph
Abstract: In order to effectively store and make use of knowledge, lots of open-domain and closed-domain knowledge bases are constructed by means of expert annotation and automatic machine annotation, such as Wikidata, Freebase, DBpedia, YAGO, and WordNet. The knowledge bases represent concrete objects and abstract concepts in world as entities, and represent the connections among entities as relationships. Recently, classic knowledge bases often adopt triples to store the relationships among entities. In general, the key topics involved in the research about construction of knowledge graph are named entity recognition and relationship mining. Recently, the segmentation of domain and the diversity of user needs provide an urgent need on automatically building knowledge graph for specific domain. However, due to the diversity of relationship types, it is difficult to manually annotate sufficient corpus to mine entities and relationships to build knowledge graph. Therefore, the construction of open-domain knowledge graph has become a hot research issue. This talk just gives the recent research trend about the construction of open-domain knowledge graph.
Bio: Ming Liu, Associate Professor/Ph.D Supervisor, in Harbin institute of Technology, School of Computer Science and Technology. He is PI of many projects, including NSFC, NSFC of Heilongjiang Province, Specialized Research Fund for the Doctoral Program of Higher Education, China Postdoctoral Science Foundation, CCF-Tencent Open Fund, MSRA Collaborative Fund. He has been awarded the First Prize of Science and Technology of Heilongjiang Province, and a Scientific Achievement of Harbin City. He has published over 20 papers in the first author, including TKDE、TOIS、KAIS、IJCAI、ACL, and translated an English book. He has long-term cooperation with MSRA, Tencent, Baidu, Huawei, and other companies.