Gianluca Demartini, Ph.D.
School of Information Technology and Electrical Engineering,
University of Queensland
QLD 4072 Australia
Office: +61 7 336 58325
Mobile: +39 349 5119466
Dr. Gianluca Demartini is a Senior Lecturer in Data Science at the University of Queensland, School of Information Technology and Electrical Engineering. His main research interests are Information Retrieval, Semantic Web, and Human Computation. His research has been supported by the UK Engineering and Physical Sciences Research Council (EPSRC) and by the EU H2020 framework program. He received Best Paper Awards at the AAAI Conference on Human Computation and Crowdsourcing (HCOMP) in 2018 and at the European Conference on Information Retrieval (ECIR) in 2016 and the Best Demo Award at the International Semantic Web Conference (ISWC) in 2011. He has published more than 80 peer-reviewed scientific publications (10 of which in venues with acceptance rate of 20% or lower) including papers at major venues such as WWW, ACM SIGIR, VLDBJ, ISWC, and ACM CHI. He has given several invited talks, tutorials, and keynotes at a number of academic conferences (e.g., ISWC, ICWSM, WebScience, and the RuSSIR Summer School), companies (e.g., Facebook), and Dagstuhl seminars. He is an ACM Distinguished Speaker since 2015. He serves as area editor for the Journal of Web Semantics, editorial board member for the Information Retrieval journal, as Crowdsourcing and Human Computation Track co-Chair at WWW 2018, and as Student Coordinator at ISWC 2017. He has been Senior Program Committee member for the AAAI Conference on Human Computation and Crowdsourcing (HCOMP), the International Conference on Web Engineering (ICWE), and the ACM International Conference on Information and Knowledge Management (CIKM). He is Program Committee member for several conferences including WWW, SIGIR, KDD, IJCAI, ISWC, and ICWSM. He was co-chair for the Human Computation and Crowdsourcing Track at ESWC 2015. He co-organized the Entity Ranking Track at the Initiative for the Evaluation of XML Retrieval in 2008 and 2009. Before joining the University of Queensland, he was Lecturer at the University of Sheffield in UK, post-doctoral researcher at the eXascale Infolab at the University of Fribourg in Switzerland, visiting researcher at UC Berkeley, junior researcher at the L3S Research Center in Germany, and intern at Yahoo! Research in Spain. In 2011, he obtained a Ph.D. in Computer Science at the Leibniz University of Hanover focusing on Semantic Search.
From People to Entities: Typed Search in the Enterprise and the Web
Gianluca Demartini, Ph.D. on April 6th 2011
The full Ph.D. thesis is available for download here. (downloaded 5761 times since April 2011)
The slides presented during the Ph.D. defense are available for download here. (downloaded 2471 times since April 2011)
The exponential growth of digital information available in Enterprises and on the Web creates the need for search tools that can respond to the most sophisticated informational needs. Retrieving relevant documents is not enough anymore and finding entities rather than just textual resources provides great support to the final user both on the Web and in Enterprises. Many user tasks would be simplified if Search Engines would support typed search, and return entities instead of just Web pages. For example, an executive who tries to solve a problem needs to find people in the company who are knowledgeable about a certain topic. Aggregation of information spread over different documents is a key aspect in this process. Finding experts is a problem mostly considered in the Enterprise setting where teams for new projects need to be built and problems need to be solved by the right persons. In the first part of the thesis, we propose a model for expert finding based on the well consolidated vector space model for Information Retrieval and investigate its effectiveness. We can define Entity Retrieval by generalizing the expert finding problem to any entity. In Entity Retrieval the goal is to rank entities according to their relevance to a query (e.g., "Countries where I can pay in Euro"); the set of entities to be ranked is assumed to be loosely defined by a generic category, given in the query itself (e.g., countries), or by some example entities (e.g., Italy, Germany, France). In the second part of the thesis, we investigate different methods based on Semantic Web and Natural Language Processing techniques for solving these tasks both in Wikipedia and, generally, on the Web. Evaluation is a critical aspect of Information Retrieval. We contributed to the field of Information Retrieval evaluation by organizing an evaluation initiative for Entity Retrieval. Opinions and other relevant information about entities can be provided by different sources in different contexts. News articles report about events where entities are involved. In such setting the temporal dimension is critical as news stories develop over time and new entities appear in the story and others are not relevant anymore. In the third part of this thesis, we study the problem of Entity Retrieval for news applications and the importance of the news trail history (i.e., past related articles) to determine the relevant entities in current articles. We also study opinion evolution about entities. In the last years, the blogosphere has become a vital part of the Web, covering a variety of different points of view and opinions on political and event-related topics such as immigration, election campaigns, or economic developments. We propose a method for automatically extracting public opinion about specific entities from the blogosphere. In summary, we develop methods to find entities that satisfy the user's need aggregating knowledge from different sources and we study how entity relevance and opinions evolve over time.
© 2011 - Contact: Gianluca Demartini