@InProceedings{tran-nguyen-tojo:2017:W17-55,
  author    = {Tran, Van-Khanh  and  Nguyen, Le-Minh  and  Tojo, Satoshi},
  title     = {Neural-based Natural Language Generation in Dialogue using RNN Encoder-Decoder with Semantic Aggregation},
  booktitle = {Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue},
  month     = {August},
  year      = {2017},
  address   = {Saarbrücken, Germany},
  publisher = {Association for Computational Linguistics},
  pages     = {231--240},
  abstract  = {Natural language generation (NLG) is an important component in spoken dialogue
	systems. This paper presents a model called Encoder-Aggregator-Decoder which is
	an extension of an Recurrent Neural Network based Encoder-Decoder architecture.
	The proposed Semantic Aggregator consists of two components: an Aligner and a
	Refiner. The Aligner is a conventional attention calculated over the encoded
	input information, while the Refiner is another attention or gating mechanism
	stacked over the attentive Aligner in order to further select and aggregate the
	semantic elements. The proposed model can be jointly trained both sentence
	planning and surface realization to produce natural language utterances.
	The model was extensively assessed on four different NLG domains, in which the
	experimental results showed that the proposed generator consistently
	outperforms the previous methods on all the NLG domains.},
  url       = {http://aclweb.org/anthology/W17-5528}
}