@InProceedings{song-EtAl:2017:I17-2,
  author    = {Song, Yiping  and  Tian, Zhiliang  and  Zhao, Dongyan  and  Zhang, Ming  and  Yan, Rui},
  title     = {Diversifying Neural Conversation Model with Maximal Marginal Relevance},
  booktitle = {Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)},
  month     = {November},
  year      = {2017},
  address   = {Taipei, Taiwan},
  publisher = {Asian Federation of Natural Language Processing},
  pages     = {169--174},
  abstract  = {Neural conversation systems, typically using sequence-to-sequence (seq2seq)
	models, are showing promising progress recently. However, traditional seq2seq
	suffer from a severe weakness: during beam search decoding, they tend to rank
	universal replies at the top of the candidate list, resulting in the lack of
	diversity among candidate replies. Maximum Marginal Relevance (MMR) is a
	ranking algorithm that has been widely used for subset selection. In this
	paper, we propose the MMR-BS decoding method, which incorporates MMR into the
	beam search (BS) process of seq2seq. The MMR-BS method improves the diversity
	of generated replies without sacrificing their high relevance with the
	user-issued query. Experiments show that our proposed model achieves the best
	performance among other comparison methods.},
  url       = {http://www.aclweb.org/anthology/I17-2029}
}