Viewing grammar induction as an adaptive control problem

Adaptive control is the design of systems that control an autonomous agent in a changing and uncertain environment. The author argues that many types of real world tasks in which grammar induction is a goal may be viewed in the framework of existing adaptive control techniques and that much is to be gained by doing so. Background on adaptive control is presented, focusing on one algorithm, C.J.C.H. Watkins´ Q-learning (1989). Then it is shown how the problem of learning grammatical structure can be formulated as an adaptive control problem and how Q-learning can be applied to solve the problem. Preliminary results are sketched to support the argument and several proposals are made for extending the analogy. Finally, some related approaches are outlined and conclusions made