@inproceedings{forst-kaplan-2006-importance,
    title = "The importance of precise tokenizing for deep grammars",
    author = "Forst, Martin  and
      Kaplan, Ronald M.",
    editor = "Calzolari, Nicoletta  and
      Choukri, Khalid  and
      Gangemi, Aldo  and
      Maegaard, Bente  and
      Mariani, Joseph  and
      Odijk, Jan  and
      Tapias, Daniel",
    booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}`06)",
    month = may,
    year = "2006",
    address = "Genoa, Italy",
    publisher = "European Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/L06-1092/",
    abstract = "We present a non-deterministic finite-state transducer that acts as a tokenizer and normalizer for free text that is input to a broad-coverage LFG of German. We compare the basic tokenizer used in an earlier version of the grammar and the more sophisticated tokenizer that we now use. The revised tokenizer increases the coverage of the grammar in terms of full parses from 68.3{\%} to 73.4{\%} on sentences 8,001 through 10,000 of the TiGer Corpus."
}