@inproceedings{keersmaekers-2021-glaux,
    title = "The {GLAU}x corpus: methodological issues in designing a long-term, diverse, multi-layered corpus of {A}ncient {G}reek",
    author = "Keersmaekers, Alek",
    editor = "Tahmasebi, Nina  and
      Jatowt, Adam  and
      Xu, Yang  and
      Hengchen, Simon  and
      Montariol, Syrielle  and
      Dubossarsky, Haim",
    booktitle = "Proceedings of the 2nd International Workshop on Computational Approaches to Historical Language Change 2021",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/watermark/2021.lchange-1.6/",
    doi = "10.18653/v1/2021.lchange-1.6",
    pages = "39--50",
    abstract = "This paper describes the GLAUx project ({``}the Greek Language Automated''), an ongoing effort to develop a large long-term diachronic corpus of Greek, covering sixteen centuries of literary and non-literary material annotated with NLP methods. After providing an overview of related corpus projects and discussing the general architecture of the corpus, it zooms in on a number of larger methodological issues in the design of historical corpora. These include the encoding of textual variants, handling extralinguistic variation and annotating linguistic ambiguity. Finally, the long- and short-term perspectives of this project are discussed."
}