@inproceedings{mou-etal-2016-sequence,
    title = "Sequence to Backward and Forward Sequences: A Content-Introducing Approach to Generative Short-Text Conversation",
    author = "Mou, Lili  and
      Song, Yiping  and
      Yan, Rui  and
      Li, Ge  and
      Zhang, Lu  and
      Jin, Zhi",
    editor = "Matsumoto, Yuji  and
      Prasad, Rashmi",
    booktitle = "Proceedings of {COLING} 2016, the 26th International Conference on Computational Linguistics: Technical Papers",
    month = dec,
    year = "2016",
    address = "Osaka, Japan",
    publisher = "The COLING 2016 Organizing Committee",
    url = "https://preview.aclanthology.org/fix-sig-urls/C16-1316/",
    pages = "3349--3358",
    abstract = "Using neural networks to generate replies in human-computer dialogue systems is attracting increasing attention over the past few years. However, the performance is not satisfactory: the neural network tends to generate safe, universally relevant replies which carry little meaning. In this paper, we propose a content-introducing approach to neural network-based generative dialogue systems. We first use pointwise mutual information (PMI) to predict a noun as a keyword, reflecting the main gist of the reply. We then propose seq2BF, a ``sequence to backward and forward sequences'' model, which generates a reply containing the given keyword. Experimental results show that our approach significantly outperforms traditional sequence-to-sequence models in terms of human evaluation and the entropy measure, and that the predicted keyword can appear at an appropriate position in the reply."
}