@inproceedings{manning-schneider-2021-referenceless,
    title = "Referenceless Parsing-Based Evaluation of {AMR}-to-{E}nglish Generation",
    author = "Manning, Emma  and
      Schneider, Nathan",
    editor = "Gao, Yang  and
      Eger, Steffen  and
      Zhao, Wei  and
      Lertvittayakumjorn, Piyawat  and
      Fomicheva, Marina",
    booktitle = "Proceedings of the 2nd Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2021",
    address = "Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2021.eval4nlp-1.12/",
    doi = "10.18653/v1/2021.eval4nlp-1.12",
    pages = "114--122",
    abstract = "Reference-based automatic evaluation metrics are notoriously limited for NLG due to their inability to fully capture the range of possible outputs. We examine a referenceless alternative: evaluating the adequacy of English sentences generated from Abstract Meaning Representation (AMR) graphs by parsing into AMR and comparing the parse directly to the input. We find that the errors introduced by automatic AMR parsing substantially limit the effectiveness of this approach, but a manual editing study indicates that as parsing improves, parsing-based evaluation has the potential to outperform most reference-based metrics."
}