@inproceedings{wu-etal-2018-dialog,
    title = "Dialog Generation Using Multi-Turn Reasoning Neural Networks",
    author = "Wu, Xianchao  and
      Mart{\'i}nez, Ander  and
      Klyen, Momo",
    editor = "Walker, Marilyn  and
      Ji, Heng  and
      Stent, Amanda",
    booktitle = "Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)",
    month = jun,
    year = "2018",
    address = "New Orleans, Louisiana",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/N18-1186/",
    doi = "10.18653/v1/N18-1186",
    pages = "2049--2059",
    abstract = "In this paper, we propose a generalizable dialog generation approach that adapts multi-turn reasoning, one recent advancement in the field of document comprehension, to generate responses ({\textquotedblleft}answers{\textquotedblright}) by taking current conversation session context as a {\textquotedblleft}document{\textquotedblright} and current query as a {\textquotedblleft}question{\textquotedblright}. The major idea is to represent a conversation session into memories upon which attention-based memory reading mechanism can be performed multiple times, so that (1) user`s query is properly extended by contextual clues and (2) optimal responses are step-by-step generated. Considering that the speakers of one conversation are not limited to be one, we separate the single memory used for document comprehension into different groups for speaker-specific topic and opinion embedding. Namely, we utilize the queries' memory, the responses' memory, and their unified memory, following the time sequence of the conversation session. Experiments on Japanese 10-sentence (5-round) conversation modeling show impressive results on how multi-turn reasoning can produce more diverse and acceptable responses than state-of-the-art single-turn and non-reasoning baselines."
}