My research is focussed on developing probabilistic models of vagueness (fuzziness) and applying them across a number of application domains in Artificial Intelligence. Underpinning my approach is the identification of vagueness or fuzziness with linguistic (semantic) uncertainty. The latter corresponds to uncertainty about the correct interpretation of a given predicate, which I have argued is epistemic in nature and therefore should be treated probabilistically.
Recently I have become convinced of the need to extend this probabilistic model so as to incorporate truth-gaps i.e. explicitly borderline cases. This has motivated my most recent work in which I have looked at combining probabilities and three valued truth models. This approach allows for a much more flexible representation framework in which both propositions and valuations can be ordered in terms of their relative vagueness, and in which we can capture both stronger and weaker versions of an assertion e.g. absolutely short, quite short etc. This opens the possibility of developing choice models of assertion in which there is a clear rational for choosing a vague statement over a (more) crisp one in the presence of uncertainty.
During the last few years I have also been investigating the modelling of vagueness and uncertainty in multi-agent systems and distributed decision making through simulations and robot systems experiments.
Recently I have become convinced of the need to extend this probabilistic model so as to incorporate truth-gaps i.e. explicitly borderline cases. This has motivated my most recent work in which I have looked at combining probabilities and three valued truth models. This approach allows for a much more flexible representation framework in which both propositions and valuations can be ordered in terms of their relative vagueness, and in which we can capture both stronger and weaker versions of an assertion e.g. absolutely short, quite short etc. This opens the possibility of developing choice models of assertion in which there is a clear rational for choosing a vague statement over a (more) crisp one in the presence of uncertainty.
During the last few years I have also been investigating the modelling of vagueness and uncertainty in multi-agent systems and distributed decision making through simulations and robot systems experiments.