A Morphological Processor Based on Foma for Biscayan (a Basque dialect)

We present a new morphological processor for Biscayan, a dialect of Basque, developed on the description of the morphology of standard Basque. The database for the standard morphology has been extended for dialects and an opensource tool for morphological description named foma is used for building the processor. XuxenB, a spelling checker/corrector for this dialect, is the first application of this work. 1. Basque and Biscayan morphology Basque is an agglutinative language with rich morphology. Standard Basque morphology was described by Alegria et al. (1995; 2002) using finite-state morphology. The Biscayan dialect of Basque (Arejita et al., 2002, 2005), also called Western Basque (Zuazo, 2008), is a dialect of the Basque language spoken in the western part of the Basque speaking area, mainly in the province of Biscay, but also in southwest Guipuzcoa and the Basque speaking areas of Álava. Although it is the most widespread of Basque dialects, it differs considerably from standard Basque, heavily based on the Guipuzcoan dialect. While the standard written Basque is used in all the levels of education and the media intended for the whole Basque speaking population, there is an increasing interest in using Biscayan in local media and informal communication forums (blogs, chats, phones). It is quite difficult to calculate the number of Biscayan speakers, as the majority of surveys done regarding the use of Basque language focus mainly on Basque speakers as a whole. Nevertheless, according to the estimate made by the Labayru institute (www.labayru.org), a cultural institution working for the promotion of Biscayan, speakers of this dialect amount to about 250,000.