We introduce a framework for syntactic parsing with latent variables based on a form of dynamic Sigmoid Belief Networks called Incremental Sigmoid Belief Networks. We demonstrate ...
We present a discriminative, latent variable approach to syntactic parsing in which rules exist at multiple scales of refinement. The model is formally a latent variable CRF gramm...
Abstract Subtyping relations for object-oriented formalisms describe relationships between super- and subclasses which satisfy the substitutability requirement imposed on types and...
We formalize a model for supervised learning of action strategies in dynamic stochastic domains and show that PAC-learning results on Occam algorithms hold in this model as well. W...
Subtyping relations for the -calculus are usually defined in a syntactic way, by means of structural rules. We propose a semantic characterisation of channel types and use it to d...
Giuseppe Castagna, Rocco De Nicola, Daniele Varacc...