The need for robust and easily extensible systems for word sense disambiguation coupled with successes in training systems for a variety of tasks using large on-line corpora has led to extensive research into corpus-based statistical approaches to this problem. Promising…

This paper proposes three tests to determine whether a given nonlinear device noise model
is in agreement with accepted thermodynamic principles. These tests are applied to several
models. One conclusion is that every Gaussian noise model for any nonlinear device…

A key problem in model-based object recognition is selection, namely, the problem of isolating regions in an image that are likely to come from a single object. This isolation can be either based solely on image data (data-driven) or can…

This dissertation is a critical analysis of the transformations in the definition of a modem architectural artifact and the artifact's changing status in an institutional context. This work develops on a series of themes which proceed on the assumption that…

We report on a study of how people look for information within email, files, and the Web. When locating a document or searching for a specific answer, people relied on their contextual knowledge of their information target to help them…