PhD student Mireille Makary presents at ICDIM

Following the successful earlier conferences at Bangalore (2006), Lyon (2007), London (2008), Michigan (2009) , Thunder Bay (2010), Melbourne (2011), Macau (2012), Islamabad (2013), Thailand (2014) and Republic of Korea (South Korea); the eleventh ICDIM event was held in Porto, Portugal. The International Conference on Digital Information Management is a multidisciplinary conference on digital information management, science and technology. The principal aim of this conference is to bring people in academia, research laboratories and industry together, and offer a collaborative platform to address the emerging issues and solutions in digital information science and technology.

Digital Information technologies are gaining maturity and rapid momentum in adoption across disciplines. The digital community is producing new ways of using digital information technologies for integrating and making sense out of various data ranging from real/live streams and simulations to analytics data analysis, in support of mining of knowledge. The conference will feature original research and industrial papers on the theory, design and implementation of digital information systems, as well as demonstrations, tutorials, workshops and industrial presentations.

The Eleventh International Conference on Digital Information Management was held during September 19-21, 2016 in Porto, Portugal.

RGCL PhD student Mireille Makary presented ‘Towards automatic generation of relevance judgments for a test collection’. An abstract can be found below.

Abstract: this paper represents a new technique for building a relevance judgment list for information retrieval test collections without any human intervention. It is based on the number of occurrences of the documents in runs retrieved from several information retrieval systems and a distance based measure between the documents. The effectiveness of the technique is evaluated by computing the correlation between the ranking of the TREC systems using the original relevance judgment list (qrels) built by human assessors and the ranking obtained by using the newly generated qrels and by computing the precision and recall for the newly generated qrels as opposed to previous techniques.