This paper presents a machine learning approach to question classification. We have defined a kernel function based on latent semantic information acquired from unlabeled data. This kernel allows including external semantic knowledge into the supervised learning process. We have combined this knowledge with a bag-of-words approach by means of composite kernels to obtain state-of-the-art results...

Model updating concerns the modification of an existing but inaccurate model with measured data. For models characterized by quadratic pencils, themeasured data usually involve incomplete knowledge of natural frequencies, mode shapes, or other spectral information. In conducting the updating, it is often desirable tomatch only the part of observed data without tampering with the other part of u...

This paper describes a system for lexical knowledge representation and retrieval in interpersonal communication aids, developed in the context of an innovative modular architecture for the design and development of functionally adaptable interpersonal communicators. This module supports user language adaptability, and communication between users of different languages.

. This paper gives an overview of my PhD study into the persuasiveness of (legal) knowledge-based systems. The results of three experiments show the possible problems that may arise when computerised legal decision aids are put into practice. The users in the experiments had great difficulties with judging the limitations of the legal knowledge-based systems they were using. For the average law...