Tajik-Farsi Persian Transliteration Using Statistical Machine Translation
Chris Irwin Davis · 2012
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.