This paper describes a finite-state approach to morphological analysis and generation of Gagauz, a Turkic language spoken in the Republic of Moldova. Finite-state approaches are commonly used in morphological modelling, but one of the novelties of our approach is that we explicitly handle orthographic errors and variance, in addition to loan words. The resulting model has a reasonable coverage (above 90\%) over a range of freely-available corpora.
@InProceedings{TYERS18.70, author = {Francis Tyers and Sevilay Bayatli and Güllü Karanfil and Memduh Gokirmak}, title = "{Finite-state morphological analysis for Gagauz}", booktitle = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)}, year = {2018}, month = {May 7-12, 2018}, address = {Miyazaki, Japan}, editor = {Nicoletta Calzolari (Conference chair) and Khalid Choukri and Christopher Cieri and Thierry Declerck and Sara Goggi and Koiti Hasida and Hitoshi Isahara and Bente Maegaard and Joseph Mariani and Hélène Mazo and Asuncion Moreno and Jan Odijk and Stelios Piperidis and Takenobu Tokunaga}, publisher = {European Language Resources Association (ELRA)}, isbn = {979-10-95546-00-9}, language = {english} }