Romanization of Serbian - Incomplete Romanization

Incomplete Romanization

Incomplete romanization of Serbian is written using the English alphabet, also known as ASCII Serbian. It is commonly used in SMS messages, comments on the Internet or e-mails, mainly because users don't have available Serbian keyboard installed. Serbian is a fully phonetic language with 30 sounds that can be represented with 30 Cyrillic letters, or 28 Gaj's Latin letters and two digraphs ("nj" for "њ", and ”lj" for "љ"). In its ASCII form number of used letters drops down to 22, as letters "q", "w", "x" and "y" are not used. Some words morph into the same written form and a good knowledge of Serbian and a sentence context is required for proper understanding of the written text.

Using incomplete romanization does not allow for easy transliteration back to Cyrillic without a significant manual work. Google tried using machine learning approach to solving this problem and developed an interactive text input tool that enable typing Serbian in ASCII and auto-converting to Cyrillic. However manual typing is still required with occasional disambiguation selection from the pop up menu.