// hyperparamters for model learning
--max_epochs        : numbers of epochs
--batch_size        : numbers of turns per batch
--lr_rate           : initial learning rate
--clip              : size of clipping
--l2_norm           : l2-regularization weight
--dropout           : dropout rate
--optim             : optimization method

// network structure
--emb_size          : word vectors emedding size
--use_attn          : whether to use attention
--hid_size_enc      : size of RNN hidden cell
--hid_size_pol      : size of policy hidden output
--hid_size_dec      : size of RNN hidden cell
--cell_type         : specify RNN type

// hyperparamters for model learning
--max_epochs        : 20
--batch_size        : 64
--lr_rate           : 0.005
--clip              : 5.0
--l2_norm           : 0.00001
--dropout           : 0.0
--optim             : Adam

// network structure
--emb_size          : 50
--use_attn          : True
--hid_size_enc      : 150
--hid_size_pol      : 150
--hid_size_dec      : 150
--cell_type         : lstm

[Budzianowski et al. 2018]
@inproceedings{budzianowski2018large,
    Author = {Budzianowski, Pawe{\l} and Wen, Tsung-Hsien and Tseng, Bo-Hsiang  and Casanueva, I{\~n}igo and Ultes Stefan and Ramadan Osman and Ga{\v{s}}i\'c, Milica},
    title={MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling},
    booktitle={Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
    year={2018}
}

[Ramadan et al. 2018]
@inproceedings{ramadan2018large,
  title={Large-Scale Multi-Domain Belief Tracking with Knowledge Sharing},
  author={Ramadan, Osman and Budzianowski, Pawe{\l} and Gasic, Milica},
  booktitle={Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics},
  volume={2},
  pages={432--437},
  year={2018}
}