@article{napoles-etal-2019-enabling,
    title = "Enabling Robust Grammatical Error Correction in New Domains: Data Sets, Metrics, and Analyses",
    author = "Napoles, Courtney  and
      N{\u{a}}dejde, Maria  and
      Tetreault, Joel",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "7",
    year = "2019",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://aclanthology.org/Q19-1032",
    doi = "10.1162/tacl_a_00282",
    pages = "551--566",
    abstract = "Until now, grammatical error correction (GEC) has been primarily evaluated on text written by non-native English speakers, with a focus on student essays. This paper enables GEC development on text written by native speakers by providing a new data set and metric. We present a multiple-reference test corpus for GEC that includes 4,000 sentences in two new domains (formal and informal writing by native English speakers) and 2,000 sentences from a diverse set of non-native student writing. We also collect human judgments of several GEC systems on this new test set and perform a meta-evaluation, assessing how reliable automatic metrics are across these domains. We find that commonly used GEC metrics have inconsistent performance across domains, and therefore we propose a new ensemble metric that is robust on all three domains of text.",
}