Rule induction through integrated symbolic and subsymbolic processing
We describe a neural network, called RuleNet, that learns explicit,
symbolic condition-action rules in a formal string manipulation domain.
RuleNet discovers functional categories over elements of the domain,
and, at various points during learning, extracts rules that operate on
these categories. The rules are then injected back into RuleNet and
training continues, in a process called iterative projection. By
incorporating rules in this way, RuleNet exhibits enhanced learning and
generalization performance over alternative neural net approaches. By
integrating symbolic rule learning and subsymbolic category learning,
RuleNet has capabilities that go beyond a purely symbolic system. We
show how this architecture can be applied to the problem of case-role
assignment in natural language processing, yielding a novel rule-based
solution.
Retrieve Paper
(postscript)
(pdf)