@InProceedings{shao-EtAl:2017:EMNLP2017,
  author    = {Shao, Yuanlong  and  Gouws, Stephan  and  Britz, Denny  and  Goldie, Anna  and  Strope, Brian  and  Kurzweil, Ray},
  title     = {Generating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Models},
  booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {2210--2219},
  abstract  = {Sequence-to-sequence models have been applied to the conversation response
	generation problem where the source sequence is the conversation history and
	the target sequence is the response. Unlike translation, conversation
	responding is inherently creative. The generation of long, informative,
	coherent, and diverse responses remains a hard task.
	In this work, we focus on the single turn setting. We add self-attention to the
	decoder to maintain coherence in longer responses, and we propose a practical
	approach, called the glimpse-model, for scaling to large datasets. We introduce
	a stochastic beam-search algorithm with segment-by-segment reranking which lets
	us inject diversity earlier in the generation process. We trained on a combined
	data set of over 2.3B conversation messages mined from the web. In human
	evaluation studies, our method produces longer responses overall, with a higher
	proportion rated as acceptable and excellent as length increases, compared to
	baseline sequence-to-sequence models with explicit length-promotion. A back-off
	strategy produces better responses overall, in the full spectrum of lengths.},
  url       = {https://www.aclweb.org/anthology/D17-1235}
}