A Connectionist Model of Unification

A general approach to encode and unify recursively nested feature structures in connectionist networks is described. The unification algorithm implemented by the net is based on iterative coarsening of equivalence classes of graph nodes. This method allows the reformulation of unification as a constraint satisfaction problem and enables the connectionist implementation to take full advantage of the potential parallelism inherent in unification, resulting in sublinear time complexity. Moreover, the method is able to process any number of feature structures in parallel, searching for possible unifications and making decisions among mutually exclusive unifications where necessary. Keywords and phrases. Unification, constraint satisfaction, connectionism, feature structures. ############ 1 Part of the research reported here is work towards a Diploma thesis at Technische Universitat Munchen, Munich, West Germany. The author is currently affiliated to the Computer Science Division of the ..