SIRKM'22

SEMINAR ON INFORMATION RETRIEVAL AND KNOWLEDGE MANAGEMENT 2022

INVITED SPEAKER

  • Riichiro Mizoguchi
    Japan Advanced Institute of Science and Technology
  • TITLE: Ontology Engineering and 15 Tips for Good Research Life

    ABSTRACT : In my talk, I discuss ontology engineering and its applications. After a brief introduction of ontology in the context of the Semantic Web, I explain what ontology is, followed by two achievements of ontology engineering. Next, I discuss how the research on ontology is fun using familiar examples because I believe it contributes to training your capability for conducting research. Finally, I would like to share 15 tips with you for realizing a joyful and fruitful research life.

    KEYNOTE 1


    Riichiro MIZOGUCHI received Ph.D. degree from Osaka University in 1977. He had been a full professor of the Institute of Scientific and Industrial Research, Osaka University from 1990 to 2012 and a research professor of Research Center for Service Science, Japan Advanced Institute of Science and Technology (JAIST) from October, 2012 to March, 2019. He is currently a Fellow of JAIST and Associate researcher, ISTC-CNR Laboratory for Applied Ontology, Trento, Italy. His research interests include Non-parametric data analyses, Knowledge-based systems, Ontology engineering and intelligent learning support systems. He received honorable mention for the Pattern Recognition Society Award in 1985, Best paper award of the Institute of Electronics, Information and Communication Engineers in 1988, 10th Anniversary Memorial Paper Award of JSAI in 1996, Best paper award of ICCE99 and ICCE2006, Best paper award of JSAI in 2006 and 2012, and Best paper award of Japan Society for Information and Systems in Education in 2010 and 2019. Dr. Mizoguchi was President of the International AI in Education Society, and of Asia-Pacific Society for Computers in Education from 2001 to 2003, He was President of Japanese Society for Artificial Intelligence (JSAI) from 2005-2007. He was Vice-President of SWSA (Semantic Web Science Association) and Co-Editor-in-Chief of J. of Web Semantics from 2005 to 2009 and from 2008 to 2011, respectively. He is currently an editorial board member of Applied Ontology. His Google Scholar Citations are found at: https://scholar.google.com/citations?hl=en&user=8vYF2UIAAAAJ&view_op=list_works


  • Shahrul Azman Mohd Noah
    Universiti Kebangsaan Malaysia

  • TITLE: LOD-ENABLED RECOMMENDER SYSTEMS

    ABSTRACT : Recent advances in the Semantic Web community have resulted in novel data representation strategies that may improve the current state of the art in recommender systems, paving the way for a new generation of systems that fully comprehend user preferences (tastes, interests, and goals), item features (e.g., domain attributes, categories, and related concepts), and contextual signals (e.g., time, location, mood, and social company) they deal with. Today, the Web of Data encompasses both sedimentary (encyclopaedic, cultural, linguistic, common-sense) and real-time (news, data streams, etc.) types of knowledge recorded in a homogenous form. This knowledge could be used to connect disparate pieces of information about users, items, and their relationships, as well as add reasoning techniques to aid and improve the recommendation process. In this talk, the application of Linked Open Data (LOD) to the task of recommendations will be introduced and discussed, primarily focusing on group recommendations.

    KEYNOTE 2


    Shahrul Azman Mohd Noah received the BSc with honors in Mathematics from the Universiti Kebangsaan Malaysia in 1992, MSc and PhD degrees in Information Studies from the University of Sheffield, UK, in 1994 and 1998, respectively. He is a professor in the Center for Artificial Intelligence Technology, Universiti Kebangsaan Malaysia and currently heads the Knowledge Technology research group. His research interests include information retrieval and ontology with special emphasis on semantic search and recommender systems. He has published more than 200 research articles in these areas. Prof. Shahrul Azman was also elected as a research fellow at the Institute for Pure and Applied Mathematics (IPAM), UCLA for its Program on Mathematics of Knowledge and Search Engines. He also serves as technical expert assessor for various research grants such as the Multimedia Development Corporation (MDeC) IGS, MSC Multimedia Super Corridor R&D (MGS) and MOSTI Technofund grant schemes. Prof. Shahrul Azman is currently the deputy dean of academic at the Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, members of the International Association for Ontology and its Applications (IAOA) and IEEE Computer Science Society associations.


  • Alan Smeaton
    Dublin City University
  • TITLE: Why has search not changed in more than 25 years?

    ABSTRACT : Information retrieval (IR) research continues to attract much attention from our research communities, with contributions from computing, information science, engineering, and AI/machine learning. Over the last 50 years of research into IR, the topics have naturally evolved and still, our IR conferences and journals are packed each year with new innovations, big developments in the algorithms we might use, and lots of work reporting testing and evaluation. While we may see our searches running on larger collections of information, most of the developments result in changes that we do not see, they are under the hood and hidden from us. What we do see is the search engine interface, both out input and out output and for the most part this has not changed much, in decades. In this talk, I will pick out some of the most significant developments in IR research in recent years, and that will include variants on the search interfaces that are offered to us. I will then point to the fact that the delivery of search to us as users, covering both internet and enterprise search, through the homogenisation of the search interface, has been bad for us. While some of the developments like knowledge graphs are visible to us, we do search in our own filter bubbles, we have become accustomed to having low levels of expectation and acceptance of search service, and there is low support for the variety of information-seeking behaviours and the variation among us as searchers. I will finish by pointing to features of search such as unified search and searching personal search spaces which could be made available to us and should be, in order to make the search engine industry sustainable.
    Keywords: Search, affordance, information retrieval

    KEYNOTE 3


    Alan Smeaton has been Professor of Computing at DCU since 1997. He is an IEEE Fellow and Principal Fellow of the AdvanceHE as well as a member of the Royal Irish Academy and Academy Gold Medal Winner. He is the Chair of ACM SIGMM (SIG Multimedia), former Chair of Academy Engineering and Computer Sciences Committee former member of the inaugural Scientific Committee for COST | European Cooperation in Science and Technology and former Board member of the Irish Research Council (2011-2018). Previously Deputy Director of CLARITY: Centre for Sensor Web Technologies, an SFI-funded CSET, 2008-2013 and before that Head of School of Computing from 1999 to 2002 and Dean of the Faculty of Engineering and Computing from 2002 to 2004. In 2001 he co-founded TRECVid, the annual benchmarking activity for content-based analysis, retrieval and summarisation of digital video and he has guided this annually since then. TRECVid has involved 1,955 researchers, drawn from 270 unique institutions including CMU, IBM, Beijing University of Posts and Telegraphs, Fudan University and the Chinese Academy of Sciences.

    His specialties are information management, specifically the management of unstructured information. Earlier in his career, this was applied to text, then image, and now video, and more recently unstructured data derived from sensor networks, in both the physical and virtual worlds. He has a particular focus on lifelogging, recording information about yourself for your own purposes, and cross-correlating information from diverse sources, now known as "big data" and data analytics. He has a broad range of research interests, mostly around helping people to find information and helping information to find people.