@inproceedings{inaba-2024-personaclr,
    title = "{P}ersona{CLR}: Evaluation Model for Persona Characteristics via Contrastive Learning of Linguistic Style Representation",
    author = "Inaba, Michimasa",
    editor = "Kawahara, Tatsuya  and
      Demberg, Vera  and
      Ultes, Stefan  and
      Inoue, Koji  and
      Mehri, Shikib  and
      Howcroft, David  and
      Komatani, Kazunori",
    booktitle = "Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
    month = sep,
    year = "2024",
    address = "Kyoto, Japan",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.sigdial-1.58/",
    doi = "10.18653/v1/2024.sigdial-1.58",
    pages = "674--685",
    abstract = "Persona-aware dialogue systems can improve the consistency of the system`s responses, users' trust and user enjoyment. Filtering nonpersona-like utterances is important for constructing persona-aware dialogue systems. This paper presents the PersonaCLR model for capturing a given utterance`s intensity of persona characteristics. We trained the model with contrastive learning based on the sameness of the utterances' speaker. Contrastive learning enables PersonaCLR to evaluate the persona characteristics of a given utterance, even if the target persona is not included in training data. For training and evaluating our model, we also constructed a new dataset of 2,155 character utterances from 100 Japanese online novels. Experimental results indicated that our model outperforms existing methods and a strong baseline using a large language model. Our source code, pre-trained model, and dataset are available at https://github.com/1never/PersonaCLR."
}