@InProceedings{tseng-EtAl:2018:SIGdial,
  author    = {Tseng, Bo-Hsiang  and  Kreyssig, Florian  and  Budzianowski, Paweł  and  Casanueva, Iñigo  and  Wu, Yen-chen  and  Ultes, Stefan  and  Gasic, Milica},
  title     = {Variational Cross-domain Natural Language Generation for Spoken Dialogue Systems},
  booktitle = {Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue},
  month     = {July},
  year      = {2018},
  address   = {Melbourne, Australia},
  publisher = {Association for Computational Linguistics},
  pages     = {338--343},
  abstract  = {Cross-domain natural language generation (NLG) is still a difficult task within spoken dialogue modelling. Given a semantic representation provided by the dialogue manager, the language generator should generate sentences that convey desired information. Traditional template-based generators can produce sentences with all necessary information, but these sentences are not sufficiently diverse. With RNN-based models, the diversity of the generated sentences can be high, however, in the process some information is lost. In this work, we improve an RNN-based generator by considering latent information at the sentence level during generation using conditional variational auto-encoder architecture. We demonstrate that our model outperforms the original RNN-based generator, while yielding highly diverse sentences. In addition, our model performs better when the training data is limited.},
  url       = {http://www.aclweb.org/anthology/W18-5039}
}