Keynote Speakers of the LWA 2013
Sung-Pil Choi: Systematic Approach to the Knowledge Extraction and Structuring for Scientific Big Data Analytics
About the speaker
Sung-Pil Choi works as senior researcher and the team leader of Infrastructure Development Group in Software Research Center at Korea Institute of Science and Technology Information (KISTI), Korea. He is also an associate professor of Department of Big Data Science at University of Science and Technology (UST) in Korea. He received his M.S. degree in Computer Science from PNU (Pusan National University), Korea. He obtained his Ph.D. in Information and Commmunications Engineering from KAIST (Korea Advanced Institute of Science and Technology), Korea. His current research areas are Big-Data based Text Analytics, Machine Learning, Information Retrieval and Statistical Natural Language Processing (SNLP).
About the talk
In this presentation, we introduce a methodical model for constructing and operating the software system of scientific big data analytics in order to support various R&D activities which are being performed by scientists and engineers for their research. The model includes two important technical aspects: information extraction model for extracting useful technological knowledge from scientific documents such as papers and patents; parallel execution model for maximizing the speed and volume of the information extraction model. We will explain each building block of the entire proposed system in detail while introducing a series of evaluation criteria for the components. Furthermore, the presentation will also cover some interesting research topics that will be necessary for us to enhance the introduced knowledge processing model in terms of performance as well as its functional completeness such as Textual Entailment Analysis, Advanced Information Retrieval using Paraphrases and Patent Analytics.
Klaus-Dieter Althoff: Collaborative Multi-Expert-Systems: towards more flexibly acquiring, integrating, and processing case-specific and (more) general knowledge
About the speaker
Klaus-Dieter Althoff is professor of Artificial Intelligence at the University of Hildesheim (UHI), Germany, and since May 2010 he is leading the Competence Center Case-Based Reasoning (CCCBR) at the German Research Center for Artificial Intelligence (DFKI) in Kaiserslautern based on a cooperation contract between DFKI and UHI. Klaus received a PhD on learning expert systems for technical diagnosis (1992) and a habilitation degree on evaluation of case-based reasoning (CBR) systems (1997) both from University of Kaiserslautern. Before entering UHI in 2004, he worked for the Fraunhofer Institute for Experimental Software Engineering since 1997, where he was responsible for experience management systems and processes. He was among others program co-chair of ECCBR’08, WM’05, LSO’01, and ICCBR’99 as well as local co-chair of LWA’06, EWCBR’93, and EKAW ‘92. He was/is team member and/or project leader of a number of projects on CBR and related research topics. The current research focus includes modeling expertise in its different facets, knowledge engineering and extraction for CBR, distributed architectures with CBR, integration of CBR with various semantic technologies, deep integration between CBR and explanation reasoning, and learning expert systems. At DFKI, CCCBR is responsible for the CBR tool myCBR, which is available as an open source project and further developed in the CBR-related projects at DFKI as well as in a joint project between DFKI and University of West London (Prof. Roth-Berghofer).
About the talk
Case-based reasoning (CBR) and expert systems have a long tradition in artificial intelligence: CBR since the late 1970s and expert systems since the late 1960s. While expert systems are based on expertise and expert reasoning capabilities for a specific area of responsibility, CBR is an approach for problem solving and learning of humans and computers. Starting from different research activities, CBR and expert systems have become overlapping research fields. In this talk the relationships between CBR and expert systems are analyzed from different perspectives like problem solving, learning, competence development, and knowledge types. As human case-based reasoners are quite successful in integrating problem-solving and learning, combining different problem solving strategies, utilizing different kinds of knowledge, and becoming experts for specific areas of responsibility, computer based expert systems do not have the reputation to be successful at these tasks. Based on this, the talk will discuss the learning ability of expert systems on different levels and the role CBR may play here. A research project is introduced that aims at, among others, improving the learning ability of expert systems by systematically considering multiple expert(s) (systems) as well as the wisdom of the crowd. The corresponding software architecture integrates concepts from software engineering (experience factory, software product lines) and artificial intelligence (multi-agent systems, CBR). In the scope of this research CBR is used in various ways: for representing and processing the experience part of expertise, for supporting continuous knowledge evolution and increasing knowledge formalization, as well as for providing an open framework for constructing learning expert systems. The current state of implementation is presented as along with open challenges and an outlook on future research.
Diedrich Wolter: Qualitative Representations of Space and Time: Lean Knowledge Representations for Efficient and Effective Reasoning
About the speaker
Diedrich Wolter is Junior-Professor for Applied Informatics with focus area smart environments at the University of Bamberg. He is also member of the Bremen-Freiburg based collaborative research center Spatial Cognition where he graduated in 2006 with his work on integrating vision- and robotics-based techniques for representation of spatial environments. His research interests are related to knowledge representation and all flavors of reasoning, particularly focusing on space, time, and events. Diedrich Wolter develops the qualitative reasoning toolbox SparQ which aims to link qualitative knowledge representations with applications.
About the talk
Qualitative representations have been introduced to reduce overly detailed and comprehensive amounts of data to knowledge representations of manageable size at an appropriate level of detail. The idea underlying qualitative approaches is to abstract from all pieces of information that are not relevant for a task at hand. Qualitative representations are discrete symbolic representations of continuous, often infinite domains. In particular spatial and temporal domains feature a domain structure that allows for semantically rich but compact representations. After about two decades of research in the area of spatio-temporal representations, there are now manifold approaches to tackle various applications. In this talk I aim to characterize some of the key ingredients of successful qualitative representations. Looking at selected application domains I give an overview of how qualitative reasoning can support a variety of tasks.
Thorsten Staake: Smart Grid Data Analytics to Promote Energy Efficiency
About the speaker
Thorsten Staake is full professor and chair of the Energy Efficient Systems group at the University of Bamberg. He is also lecturer at ETH Zurich and director of the Bits to Energy Lab, a joint research initiative of the University of Bamberg, ETH Zurich and the University of St. Gallen. His work is dedicated to bringing together Information and Communication Technologies with insights from behavioral science to build products that motivate and help consumers to conserve energy. Primary fields of application include end-user oriented Smart Metering systems and related feedback technologies. Prior to joining ETH, Thorsten worked at the Auto-ID Labs at the Massachusetts Institute of Technology, Infineon Technologies, and Clariant. He holds a PhD in business administration from the University of St. Gallen, a diploma in electrical engineering and information technology from TU Darmstadt and a M.Sc. degree from Worcester Polytechnic Institute, MA, USA. Thorsten is also co-founder of the two clean-tech startups Amphiro AG and BEN Energy AG.
About the talk
Increasing energy efficiency and reducing carbon emissions are foremost objectives of our society. Information Systems (IS) that offer feedback on personal energy consumption can contribute to achieving these objectives as they can help to discover fields of optimization and motivate actors to use resources in a sustainable way. The presentation provides examples of such systems and details current research results on techniques that utilize patterns in household electricity consumption profiles in order to provide targeted saving advice.