@inproceedings{wicks-post-2022-sentence,
    title = "Does Sentence Segmentation Matter for Machine Translation?",
    author = "Wicks, Rachel  and
      Post, Matt",
    editor = {Koehn, Philipp  and
      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
      Freitag, Markus  and
      Graham, Yvette  and
      Grundkiewicz, Roman  and
      Guzman, Paco  and
      Haddow, Barry  and
      Huck, Matthias  and
      Jimeno Yepes, Antonio  and
      Kocmi, Tom  and
      Martins, Andr{\'e}  and
      Morishita, Makoto  and
      Monz, Christof  and
      Nagata, Masaaki  and
      Nakazawa, Toshiaki  and
      Negri, Matteo  and
      N{\'e}v{\'e}ol, Aur{\'e}lie  and
      Neves, Mariana  and
      Popel, Martin  and
      Turchi, Marco  and
      Zampieri, Marcos},
    booktitle = "Proceedings of the Seventh Conference on Machine Translation (WMT)",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates (Hybrid)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.wmt-1.78/",
    pages = "843--854",
    abstract = "For the most part, NLP applications operate at the sentence level. Since sentences occur most naturally in documents, they must be extracted and segmented via the use of a segmenter, of which there are a handful of options. There has been some work evaluating the performance of segmenters on intrinsic metrics, that look at their ability to recover human-segmented sentence boundaries, but there has been no work looking at the effect of segmenters on downstream tasks. We ask the question, {\textquotedblleft}does segmentation matter?{\textquotedblright} and attempt to answer it on the task of machine translation. We consider two settings: the application of segmenters to a black-box system whose training segmentation is mostly unknown, as well as the variation in performance when segmenters are applied to the training process, too. We find that the choice of segmenter largely does not matter, so long as its behavior is not one of extreme under- or over-segmentation. For such settings, we provide some qualitative analysis examining their harms, and point the way towards document-level processing."
}