We argue that groups of unannotated texts with overlapping and non-contradictory semantics represent a valuable source of information for learning semantic representations. A simp...
: The generic problem of estimation and inference given a sequence of i.i.d. samples has been extensively studied in the statistics, property testing, and learning communities. A n...
Representing lexicons and sentences with the subsymbolic approach (using techniques such as Self Organizing Map (SOM) or Artificial Neural Network (ANN)) is a relatively new but i...
Abstract. This paper introduces Higher-Order Bayesian Networks, a probabilistic reasoning formalism which combines the efficient reasoning mechanisms of Bayesian Networks with the...
Lifting can greatly reduce the cost of inference on firstorder probabilistic graphical models, but constructing the lifted network can itself be quite costly. In online applicatio...