State-of-the-art pronoun interpretation systems rely predominantly on morphosyntactic contextual features. While the use of deep knowledge and inference to improve these models wo...
Andrew Kehler, Douglas E. Appelt, Lara Taylor, Ale...
We present a novel method for approximate inference in Bayesian models and regularized risk functionals. It is based on the propagation of mean and variance derived from the Lapla...
Alexander J. Smola, Vishy Vishwanathan, Eleazar Es...
This paper introduces YAYA1, a Description Logic system focused towards learning complex interrelations among objects. YAYA Concept Language (YCL) is quite restricted; although it...
: This paper presents the design criteria for an Intelligent User Interface to a search engine of an on-line document data base. The Interface is aimed at users that have little or...
Real-valued random hidden variables can be useful for modelling latent structure that explains correlations among observed variables. I propose a simple unit that adds zero-mean G...