The Syllabifier for Serbian is an interactive Flask-based web app that allows users to test and use the syllabification algorithm developed in collaboration with Prof. dr Maja Marković at the Faculty of Philosophy at the University of Novi Sad in the period between 2018 and 2019. The research behind this app was supported by the Development of Dialog Systems for Serbian and Other South Slavic Languages (TR-32035) project financed by the Serbian Ministry of Science and Technological Development.
The underlying syllabification algorithm presents a rule-based approach to the syllabification of Serbian. Our starting point were the prescriptive rules presented in the grammar book used to teach syllabification at high-school level in schools in Serbia. In the process of our development, we had to adapt and revise these rules as they proved both redundant and insufficient in certain respects to reflect the intuition of native speakers of Serbian. The version of the algorithm in this app is a mixed-principle syllabification algorithm combining our adapted set of rules and the Sonority Sequencing Principle (SSP).
Related publications:
- Kovač, A. & Marković, M. (2019). A Mixed-principle Rule-based Approach to the Automatic Syllabification of Serbian, Contributions to Contemporary History 59(1). Retrieved from http://ojs.inz.si/pnz/article/view/332
- Kovač, A. & Marković, M. (2018). A Rule-Based Syllabifier for Serbian. In Fišer, D. & Pančur, A. (Eds.) Proceedings of the conference on Language Technologies and Digital Humanities 2018 (140–146). Ljubljana, Slovenia: Ljubljana University Press.