@inproceedings{zhu-etal-2019-retrieval,
    title = "Retrieval-Enhanced Adversarial Training for Neural Response Generation",
    author = "Zhu, Qingfu  and
      Cui, Lei  and
      Zhang, Wei-Nan  and
      Wei, Furu  and
      Liu, Ting",
    editor = "Korhonen, Anna  and
      Traum, David  and
      M{\`a}rquez, Llu{\'i}s",
    booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
    month = jul,
    year = "2019",
    address = "Florence, Italy",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/iwcs-25-ingestion/P19-1366/",
    doi = "10.18653/v1/P19-1366",
    pages = "3763--3773",
    abstract = "Dialogue systems are usually built on either generation-based or retrieval-based approaches, yet they do not benefit from the advantages of different models. In this paper, we propose a Retrieval-Enhanced Adversarial Training (REAT) method for neural response generation. Distinct from existing approaches, the REAT method leverages an encoder-decoder framework in terms of an adversarial training paradigm, while taking advantage of N-best response candidates from a retrieval-based system to construct the discriminator. An empirical study on a large scale public available benchmark dataset shows that the REAT method significantly outperforms the vanilla Seq2Seq model as well as the conventional adversarial training approach."
}