Colloquium Henrik Leopold (Humboldt University Berlin)

EVENT details

My name is Henrik Leopold and I am a research fellow with the Institute of Information Systems at the Humboldt University Berlin, Germany. I received a PhD degree (Dr. rer. pol.) as well as a master degree in information systems from the Humboldt University Berlin and a bachelor degree in information systems from the Berlin School of Economics. Before my graduation I worked for several departments of the pharmaceutical division of Bayer in Germany and the USA. In July 2013, I completed my doctoral thesis on Natural Language in Business Process Models. My current research interests are business process modelling, natural language processing, and process architectures. The results of my research have been published, among others, in Decision Support Systems and Information Systems. I have been a visiting researcher at the Eindhoven University of Technology (April-July 2010) and the Universidade Federal do Estado do Rio de Janeiro (March-April 2012, funded by DAAD). Since 2011 I am also a board member of the Berlin BPM Community of Practice (

Title: Natural language analysis in process models

Abstract: Natural language is one of the most important means of human communication. It enables us to express our will, to exchange thoughts, and to document our knowledge in written sources. Owing to its substantial role in many facets of human life, technology for automatically analyzing and processing natural language has recently become increasingly important. The goal of this presentation is to give an overview of how natural language processing can be applied in the context of business process modeling. Therefore, it first introduces how the automatic analysis of natural language in process models can be accomplished. Then, it discusses three popular application scenarios of natural language analysis in process models: the automated recognition of naming convention violations, the automated generation of natural language texts from process models, and the automated assessment of process model granularity.  

Colloquium IE&IS/IS Feb 7, 2014

Rui De Almeida

Event Details

Conditional density approximation using fuzzy and probabilistic representations of uncertainty

This presentation will focus on conditional density approximation using fuzzy and probabilistic representations of uncertainty. Fuzzy systems are typically used for approximating deterministic functions, in which case the stochastic uncertainty is ignored. I will present two different systems that combine the fuzzy and probabilistic nature of uncertainty. The obtained semi-parametric models make very few assumptions regarding the functional form of the estimated density or changes across the input variables space. These models possess sufficient generalization power to approximate a non-standard density and ability to describe the underlying process using simple linguistic descriptors despite the complexity and possible non-linearity of these processes. The additional information and process understanding provided by these models are illustrated using a real world example of conditional volatility estimation for the S&P500 index.