Text representation is a central task for any approach to automatic learning from texts. It requires a format which allows to interrelate texts even if they do not share content w...
The implementation of collapsed Gibbs samplers for non-parametric Bayesian models is non-trivial, requiring considerable book-keeping. Goldwater et al. (2006a) presented an approx...
Phil Blunsom, Trevor Cohn, Sharon Goldwater, Mark ...
: We present in this paper a transformation model for structured documents. TransM is a new model that deals with specified documents, where the structure conforms to a predefined ...
Nouhad Amaneddine, Jean Paul Bahsoun, Jean-Paul Bo...
Background: To further understand the implementation of hyperparameters re-estimation technique in Bayesian hierarchical model, we added two more prior assumptions over the weight...
A new platform for reconfigurable computing has an object-based programming model, with architecture, silicon and tools designed to faithfully realize this model. The platform is ...