@inproceedings{clerice-2021-dont,
    title = "``Don{'}t worry, it{'}s just noise''': quantifying the impact of files treated as single textual units when they are really collections",
    author = "Cl{\'e}rice, Thibault",
    editor = {H{\"a}m{\"a}l{\"a}inen, Mika  and
      Alnajjar, Khalid  and
      Partanen, Niko  and
      Rueter, Jack},
    booktitle = "Proceedings of the Workshop on Natural Language Processing for Digital Humanities",
    month = dec,
    year = "2021",
    address = "NIT Silchar, India",
    publisher = "NLP Association of India (NLPAI)",
    url = "https://preview.aclanthology.org/fix-sig-urls/2021.nlp4dh-1.11/",
    pages = "95--105"
}