A Stochastic Greek-to-Greeklish Transcriber Modeled by Real User Data

Abstract

Greek to Greeklish transcription does not appear to be a difficult task since it can be achieved by directly mapping each Greek character to a corresponding symbol of the Latin alphabet. Nevertheless, such transliteration systems do not simulate efficiently the human way of Greeklish writing, since Greeklish users do not follow a standardized way of transliteration. In this paper a stochastic Greek to Greeklish transcriber modeled by real user data is presented. The proposed transcriber employs knowledge derived from the analytical processing of 9,288 Greek-Greeklish word pairs annotated by real users and achieves the automatic transcription of any Greek word into a valid Greeklish form in a stochastic way (i.e. each Greek symbolset corresponds to a variety of Latin symbols according to the processed data), simulating thus human-like behavior. This transcriber could be used as a real-time Greek-to-Greeklish transcriber and/or as a data generator engine used for the performance evaluation of Greeklish-to-Greek transliteration systems.