@inproceedings{khayrallah-sedoc-2020-smrt,
    title = "{SMRT} Chatbots: {I}mproving Non-Task-Oriented Dialog with {S}imulated {M}ultiple {R}eference {T}raining",
    author = "Khayrallah, Huda  and
      Sedoc, Jo{\~a}o",
    editor = "Cohn, Trevor  and
      He, Yulan  and
      Liu, Yang",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.findings-emnlp.403/",
    doi = "10.18653/v1/2020.findings-emnlp.403",
    pages = "4489--4505",
    abstract = "Non-task-oriented dialog models suffer from poor quality and non-diverse responses. To overcome limited conversational data, we apply Simulated Multiple Reference Training (SMRT; Khayrallah et al., 2020), and use a paraphraser to simulate multiple responses per training prompt. We find SMRT improves over a strong Transformer baseline as measured by human and automatic quality scores and lexical diversity. We also find SMRT is comparable to pretraining in human evaluation quality, and outperforms pretraining on automatic quality and lexical diversity, without requiring related-domain dialog data."
}