@inproceedings{hanneman-dinu-2020-markup,
    title = "How Should Markup Tags Be Translated?",
    author = "Hanneman, Greg  and
      Dinu, Georgiana",
    editor = {Barrault, Lo{\"i}c  and
      Bojar, Ond{\v{r}}ej  and
      Bougares, Fethi  and
      Chatterjee, Rajen  and
      Costa-juss{\`a}, Marta R.  and
      Federmann, Christian  and
      Fishel, Mark  and
      Fraser, Alexander  and
      Graham, Yvette  and
      Guzman, Paco  and
      Haddow, Barry  and
      Huck, Matthias  and
      Yepes, Antonio Jimeno  and
      Koehn, Philipp  and
      Martins, Andr{\'e}  and
      Morishita, Makoto  and
      Monz, Christof  and
      Nagata, Masaaki  and
      Nakazawa, Toshiaki  and
      Negri, Matteo},
    booktitle = "Proceedings of the Fifth Conference on Machine Translation",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2020.wmt-1.138/",
    pages = "1160--1173",
    abstract = "The ability of machine translation (MT) models to correctly place markup is crucial to generating high-quality translations of formatted input. This paper compares two commonly used methods of representing markup tags and tests the ability of MT models to learn tag placement via training data augmentation. We study the interactions of tag representation, data augmentation size, tag complexity, and language pair to show the drawbacks and benefits of each method. We construct and release new test sets containing tagged data for three language pairs of varying difficulty."
}