Experimental Two-Level Morphology of Estonian
Proceedings of the Third International Conference on Language Resources and Evaluation (LREC 2002)
Abstract
The experimental two-level morphology of Estonian is under development at the University of Tartu. The language description, consisting of 45 two-level rules and over 200 lexicons has been implemented and tested using Xerox finite-state tools twolc and lexc. The root lexicons cover 400 most frequent stems at the present stage of development. The software has been designed to update the lexicon automatically with new stems, including the automatic generation of lexical representations of root lexicon entries. The open problems by describing of word formation processes - derivation and compounding are discussed. The advantages and disadvantages of the two-level model with respect to Estonian morphology are pointed out.