Learning Semantic-based Structures from Textual Sources
Marco Gori, Universita degli Studi di Siena, Italy
Five Challenges to the Web Information Systems Field
Christoph Rosenkranz, University of Cologne, Germany
From Web Data to Information that Makes Sense
Geert-Jan Houben, Delft University of Technology, Netherlands
Learning Semantic-based Structures from Textual Sources
Marco Gori
Universita degli Studi di Siena
Italy
Brief Bio
Marco Gori received the Ph.D. degree in 1990 from Università di Bologna, Italy. From October 1988 to June 1989 he was a visiting student at the School of Computer Science (McGill University, Montreal). In 1992, he became an Associate Professor of Computer Science at Università di Firenze and, in November 1995, he joined the Università di Siena, where he is currently full professor of computer science. His main interests are in machine learning, with applications to pattern recognition, Web mining, and game playing. He is especially interested in the formulation of relational machine learning schemes in the continuum setting. He is the leader of the WebCrow project for automatic solving of crosswords that has recently outperformed human competitors in an official competition taken place within the ECAI-06 conference. He is co-author of the book "Web Dragons: Inside the myths of search engines technologies," Morgan Kauffman (Elsevier), 2006. Dr. Gori serves (has served) as an Associate Editor of a number of technical journals related to his areas of expertise, including IEEE Transaction on Neural Networks, Pattern Recognition, Neural Networks, Neurocomputing, Pattern Analysis and Application, the International Journal of Document Analysis and Recognition, and the International Journal on Pattern Recognition and Artificial Intelligence. He has been the recipient of best paper awards and keynote speakers in a number of international conferences. He was the Chairman of the Italian Chapter of the IEEE Computational Intelligence Society and the President of the Italian Society for Artificial Intelligence. He is a fellow of the ECCAI and of the IEEE.
Abstract
In this talk, I introduce the theory of learning from constraints as a general framework to attacking problems of text processing which involve semantics. I give the foundations of the theory which incorporates logic formalisms and unstructured information. This is made possible by the unification of continuous and discrete computational mechanisms in the same functional framework, so as any stimulus, like supervised examples and logic predicates, are translated into constraints. Finally, it is shown how deep neural networks can be trained in this more general semantic-based framework. The emergence of semantics is presented in a number of problems that involve text processing. In addition to classic
problems, like text categorization, it is shown that we can carry out constraint satisfaction, so as the proposed intelligent agents can drive conclusions that involve semantics.
Five Challenges to the Web Information Systems Field
Christoph Rosenkranz
University of Cologne
Germany
Brief Bio
Christoph Rosenkranz is a Professor of Integrated Information Systems at the University of Cologne. He joined the University of Cologne in 2014. His research interests focus on designing, building, and managing integrated information systems, on business process management, on systems development, and on online communities, with an interest on the general question of how organizations can design, build, and manage integrated information systems. His work has been published in leading academic journals such as the Journal of Information Technology, Information Systems Journal, Business & Information Systems Engineering, Journal of Database Management, Supply Chain Management, and Journal of the Association for Information Systems. Prof. Dr. Rosenkranz holds a diploma degree from the University of Münster, Germany. He received his doctoral degree and his habilitation from Goethe University of Frankfurt, Germany. He has collaborated and worked with leading organizations such as SEB, zeb, Woolworth’s, Lufthansa, e-Spirit, and SAP.
Abstract
Information systems using web-based technologies have evolved over the years to cover almost every enterprise or private aspect of life. Due to their now ubiquitous nature and overall intertwining with many aspects of life and society in general, it is time to look at what "grand" challenges the discipline is facing. Five challenges are proposed that researchers and practitioners need to overcome in order to move forward - integration, security, radical technology shifts, monopolies, and the “human component”. These range from very technical to very social aspects. Not all of them are new or astounding, and almost all of them are wicked problems without any easy solution at hand. It is the intention to put them in the spotlight, focusing emphasis on and awareness of them, and to suggest some potential avenues for addressing them.
From Web Data to Information that Makes Sense
Geert-Jan Houben
Delft University of Technology
Netherlands
Brief Bio
Abstract
In this talk, we consider state of the art research into the capability of web information systems to cater for their users, by means of user models that represent relevant properties of the system's users in order to deliver them relevant and personalised information. By illustrating the research in SocialGlass and LambdaLab, we show how data-driven approaches to large-scale user modeling and sense making help to meet the challenges from domains such as urban analytics, enterprise analytics, or learning analytics.