Workshops

She argued that this ingrained conversational collaboration should be exploited to design successful natural language interfaces. Paul McKevitt, New Mexico State University, described a Wizard of Oz experiment in which it was found that particular sequences of speech act types have implications for the structure of the ensuing dialogue and can be correlated with certain aspects of the user, such as his experience in the domain. McKevitt contended that such empirical data, rather than subjective decision-making, should be the basis for constructing user models and argued for the development of automatic techniques for deriving the models. The second workshop was as successful as the first, with all agreeing that subsequent workshops should be held more frequently than at four year intervals. Since the general trend has been for researchers in different areas of user modeling to operate in isolation, such workshops are particularly important as a means of increasing cooperation and cross-fertilization of ideas among the subdisciplines.