@inproceedings{mesgar-etal-2021-improving,
    title = "Improving Factual Consistency Between a Response and Persona Facts",
    author = "Mesgar, Mohsen  and
      Simpson, Edwin  and
      Gurevych, Iryna",
    booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
    month = apr,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.eacl-main.44",
    doi = "10.18653/v1/2021.eacl-main.44",
    pages = "549--562",
    abstract = "Neural models for response generation produce responses that are semantically plausible but not necessarily factually consistent with facts describing the speaker{'}s persona. These models are trained with fully supervised learning where the objective function barely captures factual consistency. We propose to fine-tune these models by reinforcement learning and an efficient reward function that explicitly captures the consistency between a response and persona facts as well as semantic plausibility. Our automatic and human evaluations on the PersonaChat corpus confirm that our approach increases the rate of responses that are factually consistent with persona facts over its supervised counterpart while retains the language quality of responses.",
}