@inproceedings{castilho-2020-document,
    title = "Document-Level Machine Translation Evaluation Project: Methodology, Effort and Inter-Annotator Agreement",
    author = "Castilho, Sheila",
    editor = "Martins, Andr{\'e}  and
      Moniz, Helena  and
      Fumega, Sara  and
      Martins, Bruno  and
      Batista, Fernando  and
      Coheur, Luisa  and
      Parra, Carla  and
      Trancoso, Isabel  and
      Turchi, Marco  and
      Bisazza, Arianna  and
      Moorkens, Joss  and
      Guerberof, Ana  and
      Nurminen, Mary  and
      Marg, Lena  and
      Forcada, Mikel L.",
    booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
    month = nov,
    year = "2020",
    address = "Lisboa, Portugal",
    publisher = "European Association for Machine Translation",
    url = "https://preview.aclanthology.org/Add-Cong-Liu-Florida-Atlantic-University-author-id/2020.eamt-1.49/",
    pages = "455--456",
    abstract = "Document-level (doc-level) human eval-uation of machine translation (MT) has raised interest in the community after a fewattempts have disproved claims of {\textquotedblleft}human parity{\textquotedblright} (Toral et al., 2018; Laubli et al.,2018). However, little is known about bestpractices regarding doc-level human evalu-ation. The goal of this project is to identifywhich methodologies better cope with i)the current state-of-the-art (SOTA) humanmetrics, ii) a possible complexity when as-signing a single score to a text consisted of{\textquoteleft}good' and {\textquoteleft}bad' sentences, iii) a possibletiredness bias in doc-level set-ups, and iv)the difference in inter-annotator agreement(IAA) between sentence and doc-level set-ups."
}