Learning Beam Search Policies via Imitation Learning

11/01/2018
by   Renato Negrinho, et al.
0

Beam search is widely used for approximate decoding in structured prediction problems. Models often use a beam at test time but ignore its existence at train time, and therefore do not explicitly learn how to use the beam. We develop an unifying meta-algorithm for learning beam search policies using imitation learning. In our setting, the beam is part of the model, and not just an artifact of approximate decoding. Our meta-algorithm captures existing learning algorithms and suggests new ones. It also lets us show novel no-regret guarantees for learning beam search policies.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset