@inproceedings{baldwin-awab-2006-open,
    title = "Open Source Corpus Analysis Tools for {M}alay",
    author = "Baldwin, Timothy  and
      Awab, Su{'}ad",
    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/ingest-emnlp/L06-1421/",
    abstract = "Tokenisers, lemmatisers and POS taggers are vital to the linguistic and digital furtherment of any language. In this paper, we present an open source toolkit for Malay incorporating a word and sentence tokeniser, a lemmatiser and a partial POS tagger, based on heavy reuse of pre-existing language resources. We outline the software architecture of each component, and present an evaluation of each over a 26K word sample of Malay text."
}