@inproceedings{sluban-etal-2012-irregularity,
    title = "Irregularity Detection in Categorized Document Corpora",
    author = "Sluban, Borut  and
      Pollak, Senja  and
      Coesemans, Roel  and
      Lavra{\v{c}}, Nada",
    editor = "Calzolari, Nicoletta  and
      Choukri, Khalid  and
      Declerck, Thierry  and
      Do{\u{g}}an, Mehmet U{\u{g}}ur  and
      Maegaard, Bente  and
      Mariani, Joseph  and
      Moreno, Asuncion  and
      Odijk, Jan  and
      Piperidis, Stelios",
    booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}`12)",
    month = may,
    year = "2012",
    address = "Istanbul, Turkey",
    publisher = "European Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/L12-1409/",
    pages = "1598--1603",
    abstract = "The paper presents an approach to extract irregularities in document corpora, where the documents originate from different sources and the analyst`s interest is to find documents which are atypical for the given source. The main contribution of the paper is a voting-based approach to irregularity detection and its evaluation on a collection of newspaper articles from two sources: Western (UK and US) and local (Kenyan) media. The evaluation of a domain expert proves that the method is very effective in uncovering interesting irregularities in categorized document corpora."
}