Naive Bayesian classi ers utilise a simple mathematical model for induction. While it is known that the assumptions on which this model is based are frequently violated, the predic...
We argue that multilingual parallel data provides a valuable source of indirect supervision for induction of shallow semantic representations. Specifically, we consider unsupervi...
Most statistical parsers have used the grammar induction approach, in which a stochastic grammar is induced from a treebank. An alternative approach is to induce a controller for ...
We lay down plans to study how Inductive Reasoning Ability (IRA) affects the analyzing and understanding of Program Visualization (PV) systems. Current PV systems do not take int...
We revisit the roots of Genetic Programming (i.e. Natural Evolution), and conclude that the mechanisms of the process of evolution (i.e. selection, inheritance and variation) are ...