@inproceedings{mordido-meinel-2020-mark,
    title = "Mark-Evaluate: Assessing Language Generation using Population Estimation Methods",
    author = "Mordido, Gon{\c{c}}alo  and
      Meinel, Christoph",
    editor = "Scott, Donia  and
      Bel, Nuria  and
      Zong, Chengqing",
    booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
    month = dec,
    year = "2020",
    address = "Barcelona, Spain (Online)",
    publisher = "International Committee on Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2020.coling-main.178/",
    doi = "10.18653/v1/2020.coling-main.178",
    pages = "1963--1977",
    abstract = "We propose a family of metrics to assess language generation derived from population estimation methods widely used in ecology. More specifically, we use mark-recapture and maximum-likelihood methods that have been applied over the past several decades to estimate the size of closed populations in the wild. We propose three novel metrics: $\textrm{ME}_{\textrm{Petersen}}$ and $\textrm{ME}_{\textrm{CAPTURE}}$, which retrieve a single-valued assessment, and $\textrm{ME}_{\textrm{Schnabel}}$ which returns a double-valued metric to assess the evaluation set in terms of quality and diversity, separately. In synthetic experiments, our family of methods is sensitive to drops in quality and diversity. Moreover, our methods show a higher correlation to human evaluation than existing metrics on several challenging tasks, namely unconditional language generation, machine translation, and text summarization."
}