We present a data and error analysis for semantic role labelling. In a first experiment, we build a generic statistical model for semantic role assignment in the FrameNet paradigm...
The construction of personalised information systems is becoming more important as the quantity of information to be searched increases. The approach taken in this paper involves ...
In this paper we present some lessons learned from building vizsla, the keyword search and topic classification system used on the largest Hungarian portal, [origo.hu]. Based on ...
In [7], we reported on our experience in building Collaborative Mobile Virtual Communities (CMVC) on the Web. In [8], we proposed a finite state machine model and a new approach t...
We describe an agent architecture that integrates emotions, drives, and behaviors, and that focuses on modeling some of the aspects of emotions as fundamental components within th...