Poziv na predavanje: Domain-specific Search: What do doctors and patent searchers have in common?

Abstract

Information Retrieval (IR) on the World Wide Web functions very effectively and efficiently. These search tools are specifically designed as multi-purpose tools, applicable in as wide an array of situations as possible. Nevertheless, there are areas for which these tools are conceived too broadly to be useful: health or biomedical information, intellectual property information, social science publications, blogs, legal domain (laws, court decisions, ...), chemistry domain, press photographs, etc. A search in one of these domains is called a domain-specific search.

This talk discusses a model of domain-specific search, to assist researchers, systems designers and system beneficiaries in the analysis of their own domain. The use of the domain-specific search model in the patent search and medical information search domains is presented. However, it is also important to know how well a domain-specific search system functions, and both empirical and user-centred evaluation of domain-specific search systems is discussed, with a number of current challenges being highlighted. In particular, potential solutions for the abstraction of domain-specific evaluation results to multiple domains are presented.

Biography

Allan Hanbury is Senior Researcher and Privatdozent at the Vienna University of Technology, Austria. He is scientific coordinator of the EU-funded KHRESMOI Integrated Project on medical and health information search and analysis, coordinator of the EU-funded VISCERAL project on evaluation of algorithms on big data, and coordinator of the CHIST-ERA project MUCKE on credibility of and search in multimodal data and social networks. He was leader of the Evaluation, Integration and Standards work package of the MUSCLE EU Network of Excellence, and has led a number of Austrian national projects. His research interests include information retrieval, multimodal information retrieval, and the evaluation of information retrieval systems and algorithms. He is author or co-author of over 100 publications in refereed journals and refereed international conferences.