@inproceedings{vor-der-bruck-etal-2014-collex,
    title = "{C}ol{L}ex.en: Automatically Generating and Evaluating a Full-form Lexicon for {E}nglish",
    author = {vor der Br{\"u}ck, Tim  and
      Mehler, Alexander  and
      Islam, Zahurul},
    editor = "Calzolari, Nicoletta  and
      Choukri, Khalid  and
      Declerck, Thierry  and
      Loftsson, Hrafn  and
      Maegaard, Bente  and
      Mariani, Joseph  and
      Moreno, Asuncion  and
      Odijk, Jan  and
      Piperidis, Stelios",
    booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}`14)",
    month = may,
    year = "2014",
    address = "Reykjavik, Iceland",
    publisher = "European Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/Ingest-2025-COMPUTEL/L14-1075/",
    pages = "3756--3760",
    abstract = "The paper describes a procedure for the automatic generation of a large full-form lexicon of English. We put emphasis on two statistical methods to lexicon extension and adjustment: in terms of a letter-based HMM and in terms of a detector of spelling variants and misspellings. The resulting resource, {\textbackslash}collexen, is evaluated with respect to two tasks: text categorization and lexical coverage by example of the SUSANNE corpus and the {\textbackslash}openanc."
}