Rayyan Merchant

Rayyan Merchant

Mentor

Dr. Kevin Tang

College

College of Liberal Arts and Sciences

Major

Computer Science, Linguistics

Minor

N/A

Organizations

Speech, Lexicon, and Modeling Lab

Academic Awards

Benacquisto Scholarship, Boren Scholarship,

Volunteering

NGO Sadoqat Assistant

Research Interests

Computational Linguistics, Language Documentation

Hobbies and Interests

Learning languages, singing, working out

Research Project

Farsi-Tajiki Machine Transliteration

Despite speaking and writing the same language, speakers of Tajik Persian (written in the Cyrillic alphabet) cannot read Iranian and Afghan media, which is written in the Perso-Arabic script. This can be accredited to the many years Tajikistan spent under Soviet rule, during which the writing system switched from Arabic to Cyrillic. Combined with a dependence on other post-Soviet states, much of the news a typical Tajik citizen can access comes from either Russian media or a Tajikistani government viewpoint. As of yet, no group has yet fully addressed this severe gap in communication, leading to a major lack of media diversity.

My research proposal is to utilize my proficiency in the Tajik Persian language to create a machine transliterator that will automatically transliterate websites written in Farsi/Dari to Tajik.  If successful, the proposed project would open doors to all types of written Persian media that so far have been largely inaccessible to citizens of Tajikistan. 

  • Dr. Kevin Tang
  • Computer Science, Linguistics
  • N/A
  • Computational Linguistics, Language Documentation
  • Benacquisto Scholarship, Boren Scholarship,
  • Speech, Lexicon, and Modeling Lab
  • NGO Sadoqat Assistant
  • Learning languages, singing, working out
  • Farsi-Tajiki Machine Transliteration
  • Despite speaking and writing the same language, speakers of Tajik Persian (written in the Cyrillic alphabet) cannot read Iranian and Afghan media, which is written in the Perso-Arabic script. This can be accredited to the many years Tajikistan spent under Soviet rule, during which the writing system switched from Arabic to Cyrillic. Combined with a dependence on other post-Soviet states, much of the news a typical Tajik citizen can access comes from either Russian media or a Tajikistani government viewpoint. As of yet, no group has yet fully addressed this severe gap in communication, leading to a major lack of media diversity.

    My research proposal is to utilize my proficiency in the Tajik Persian language to create a machine transliterator that will automatically transliterate websites written in Farsi/Dari to Tajik.  If successful, the proposed project would open doors to all types of written Persian media that so far have been largely inaccessible to citizens of Tajikistan.