@inproceedings{berlot-attwell-rudzicz-2022-relevance,
    title = "Relevance in Dialogue: Is Less More? An Empirical Comparison of Existing Metrics, and a Novel Simple Metric",
    author = "Berlot-Attwell, Ian  and
      Rudzicz, Frank",
    editor = "Liu, Bing  and
      Papangelis, Alexandros  and
      Ultes, Stefan  and
      Rastogi, Abhinav  and
      Chen, Yun-Nung  and
      Spithourakis, Georgios  and
      Nouri, Elnaz  and
      Shi, Weiyan",
    booktitle = "Proceedings of the 4th Workshop on NLP for Conversational AI",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.nlp4convai-1.14/",
    doi = "10.18653/v1/2022.nlp4convai-1.14",
    pages = "166--183",
    abstract = "In this work, we evaluate various existing dialogue relevance metrics, find strong dependency on the dataset, often with poor correlation with human scores of relevance, and propose modifications to reduce data requirements and domain sensitivity while improving correlation. Our proposed metric achieves state-of-the-art performance on the HUMOD dataset while reducing measured sensitivity to dataset by 37{\%}-66{\%}. We achieve this without fine-tuning a pretrained language model, and using only 3,750 unannotated human dialogues and a single negative example. Despite these limitations, we demonstrate competitive performance on four datasets from different domains. Our code, including our metric and experiments, is open sourced."
}