@inproceedings{diewald-2022-matrix,
    title = "Matrix and Double-Array Representations for Efficient Finite State Tokenization",
    author = "Diewald, Nils",
    editor = {Banski, Piotr  and
      Barbaresi, Adrien  and
      Clematide, Simon  and
      Kupietz, Marc  and
      L{\"u}ngen, Harald},
    booktitle = "Proceedings of the Workshop on Challenges in the Management of Large Corpora (CMLC-10)",
    month = jun,
    year = "2022",
    address = "Marseille, France",
    publisher = "European Language Resources Association",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.cmlc-1.4/",
    pages = "20--26",
    abstract = "This paper presents an algorithm and implementation for efficient tokenization of space-delimited languages based on a deterministic finite state automaton. Two representations of the underlying data structure are presented and a model implementation for German is compared with state-of-the-art approaches. The presented solution is faster than other tools while maintaining comparable quality."
}