Dependency Parsing with Energy-based Reinforcement Learning

We present a model which integrates dependency parsing with reinforcement learning based on Markov decision process. At each time step, a transition is picked up to construct the dependency tree in terms of the long-run reward. The optimal policy for choosing transitions can be found with the SARSA algorithm. In SARSA, an approximation of the stateaction function can be obtained by calculating the negative free energies for the Restricted Boltzmann Machine. The experimental results on CoNLL-X multilingual data show that the proposed model achieves comparable results with the current state-of-the-art methods.