Linguistic Rule Acquisition by Information Maximization: Neural Networks Infer the Use of Donatory Verbs

In this paper, we propose a new information theoretic method for a linguistic rule acquisition problem, and demonstrate that a linguistic rule acquisition process is an instance of realization of information maximization. The new method is based upon unsupervised competitive learning. The unsupervised learning is needed because children acquire rules without any explicit instruction. In the experiments concerning the acquisition of the donatory verb system, we could observe that by maximizing information we can generate internal representations leading to linguistic rule discovery.