Reinforcement Learning with Factored States and Actions
The Journal of Machine Learning Research
CoNLL-X shared task on multilingual dependency parsing
CoNLL-X '06 Proceedings of the Tenth Conference on Computational Natural Language Learning
Labeled pseudo-projective dependency parsing with support vector machines
CoNLL-X '06 Proceedings of the Tenth Conference on Computational Natural Language Learning
On the complexity of non-projective data-driven dependency parsing
IWPT '07 Proceedings of the 10th International Conference on Parsing Technologies
Semi-supervised dependency parsing using generalized tri-training
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics
| Hi-index | 0.00 |
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 state-action 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.