@inproceedings{davis-2012-tajik,
    title = "{T}ajik-{F}arsi {P}ersian Transliteration Using Statistical Machine Translation",
    author = "Davis, Chris Irwin",
    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/ingest-emnlp/L12-1601/",
    pages = "3988--3995",
    abstract = "Tajik Persian is a dialect of Persian spoken primarily in Tajikistan and written with a modified Cyrillic alphabet. Iranian Persian, or Farsi, as it is natively called, is the lingua franca of Iran and is written with the Persian alphabet, a modified Arabic script. Although the spoken versions of Tajik and Farsi are mutually intelligible to educated speakers of both languages, the difference between the writing systems constitutes a barrier to text compatibility between the two languages. This paper presents a system to transliterate text between these two different Persian dialects that use incompatible writing systems. The system also serves as a mechanism to facilitate sharing of computational linguistic resources between the two languages. This is relevant because of the disparity in resources for Tajik versus Farsi."
}