@inproceedings{groves-etal-2018-treat,
    title = "Treat the system like a human student: Automatic naturalness evaluation of generated text without reference texts",
    author = "Groves, Isabel  and
      Tian, Ye  and
      Douratsos, Ioannis",
    editor = "Krahmer, Emiel  and
      Gatt, Albert  and
      Goudbeek, Martijn",
    booktitle = "Proceedings of the 11th International Conference on Natural Language Generation",
    month = nov,
    year = "2018",
    address = "Tilburg University, The Netherlands",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/iwcs-25-ingestion/W18-6512/",
    doi = "10.18653/v1/W18-6512",
    pages = "109--118",
    abstract = "The current most popular method for automatic Natural Language Generation (NLG) evaluation is comparing generated text with human-written reference sentences using a metrics system, which has drawbacks around reliability and scalability. We draw inspiration from second language (L2) assessment and extract a set of linguistic features to predict human judgments of sentence naturalness. Our experiment using a small dataset showed that the feature-based approach yields promising results, with the added potential of providing interpretability into the source of the problems."
}